tuesday, june 24

November 1 – 5, 2014

Pocket Guide

University Town

Stephen Riady Centre (ACCV Tutorials and Workshops) First Floor

Stephen Riady Centre (ACCV Tutorials and Workshops) Second Floor

ACCV Shuttle Bus Stops at Drop Off Area

Registration Venue

Workshop\Tutorial Venue

Message from the General Chairs

1

Message from the General Chairs

Welcome to the 12th Asian Conference on Computer Vision (ACCV 2014) held at the National University of Singapore on 1-5 November 2014, supported by the Asian Federation of Computer Vision Societies (AFCV).

ACCV 2014 continues a proud tradition that began in 1993 with the first ACCV in Osaka, Japan, in which many scattered computer vision events and initiatives in the Asian region were first combined to form a major conference with the scope and quality comparable to ECCV in Europe and CVPR in the United States. It was followed by the highly successful ACCV’95 in Singapore, ACCV’98 in Hong Kong, ACCV’00 in Taiwan, ACCV’02 in Melbourne, ACCV’04 in Jeju Island, ACCV’06 in Hyderabad, ACCV’07 in Tokyo, ACCV’09 in Xian, ACCV’10 in Queenstown, and ACCV’12 in Daejeon.

We offer an outstanding scientific program that was put together by the Program Chairs, and we are grateful for their excellent work. They assembled and guided an international group of 36 Area Chairs, comprising top experts in computer vision, to deliberate and reach decisions on paper acceptance. In addition to the main conference, we also received a record number of 26 workshop proposals, from which 15 were selected, as well as 6 tutorials and 9 demos. We thank all the workshop and tutorial organizers and demo presenters for their proposals and efforts in enriching ACCV 2014.

There are a number of people who have dedicated many hours (mostly in the evening and on weekends) to make ACCV 2014 happen. This event simply could not be possible without the time and effort from the Program Chairs, Workshop Chairs, Tutorial Chairs, Demo Chairs, Publication Chairs, Organizing Chairs (local arrangements), Area Chairs and Reviewers. There are also a number of administrative staff and an army of student volunteers who have worked quietly behind the scenes to ensure the conference runs smoothly. We are grateful for all their efforts. We would like to also thank all authors for contributing to ACCV with their high quality paper submissions.

We are also honored to have three distinguished keynote speakers, Prof. Stéphane Mallat (École Normale Supérieure, France), Dr. Minoru Etoh (NTT Docomo, Japan) and Prof. Dieter Fox (University of Washington, USA), who have taken time to come to Singapore to address the ACCV 2014 audience. We truly appreciate their presence. We are pleased to receive the support from the following sponsors: Samsung, Omron, nVidia, Garena, Adobe, Visenze, Lee Foundation, Morpx, Microsoft Research, and NICTA. We also have very generous support from the Singapore Exhibition and Convention Bureau.

Finally, we would like to thank all ACCV 2014 attendees for taking the time to come to Singapore and participate in ACCV 2014. Singapore is a vibrant, cosmopolitan city-state with a harmonious mix of diverse ethnic groups. Besides attending the conference, we do encourage you to take time to experience the many tourist attractions and culinary offerings available here in Singapore.

Wishing you a pleasant stay in Singapore!

Michael S. Brown, Tat-Jen Cham, Yasuyuki Matsushita General Chairs for ACCV 2014

Message from the Program Chairs

2

Message from the Program Chairs

ACCV 2014 received a total of 814 submissions, a reflection of the growing strength of Computer Vision in Asia. We note, particularly, that a number of Areas Chairs commented very positively on the overall quality of the submissions. The conference had submissions from all continents (except Antarctica, a challenge for the 2016 organisers perhaps) with 64% from Asia, 20% from Europe and 10% from North America.

The Program Chairs assembled a geographically diverse team of 36 Area Chairs who handled between 20 and 30 papers each. Area Chairs recommended reviewers for papers, and each paper received at least three reviews from the 638 reviewers who participated in the process. Paper decisions were finalised at an Area Chair meeting held in Singapore in September. At this meeting, Area Chairs worked in triples to reach collective decisions about acceptance, and in panels of 12 to decide on the oral/poster distinction. The total number of papers accepted was 227, an overall acceptance rate of 28%. Of these, 32 were selected for oral presentation.

We must acknowledge and extend our thanks to those responsible for local arrangements for the Area Chair meeting, hosted at Nanyang Technological University. In particularly we are grateful to Tat-Jen Cham and Junsong Yuan, and their team of student volunteers, who handled the local arrangements and helped everything run smoothly.

We naturally also wish to extend our immense gratitude to the Area Chairs and Reviewers for their generous participation in the process -- the conference would not be possible if it were not for this huge voluntary investment of time and effort. We acknowledge particularly the contribution of 35 reviewers designated as "Outstanding Reviewers" (see page 6 in this booklet for a full list) who were nominated by Area Chairs and Program Chairs for having provided a large number of helpful, high quality reviews.

The Program Chairs are also extremely grateful for the support, sage advice and occasional good-natured prompting provided by the General Chairs. Each of them helped with matters that in other circumstances might have been left to the Program Chairs, so that it regularly felt as if we had a team of 7, not 4 Program Chairs. The PCs are very grateful for this.

Finally, we wish to thank the authors and delegates. Without your participation there would be no conference. Computer Vision in Asia is growing, and the quality of ACCV steadily climbing so that it is now, rightly, considered as one of the top conferences in the field. We look forward to an outstanding conference.

Daniel Cremers Ian Reid Hideo Saito Ming-Hsuan Yang Program Chairs for ACCV 2014

Keynote Speakers

3

Monday Nov 3, Stéphane Mallat, École Normale Supérieure

Title: Deep Convolution Networks as Geometric Image Representations

Until recently, computer vision algorithms mostly resulted from geometric considerations over shapes, textures, motion, and 3D perspective projections. Deep learning algorithms seem to ignore these geometric considerations, while providing state of the art classification results on complex image databases. It is thus time to wonder what type of image information is extracted by these deep neural networks and why do they work so well.

We show that deep convolution networks provide remarkable architectures to represent geometric image information, including shapes, textures and complex structured objects. They compute descriptors having appropriate invariance and stability to geometric transformations. The properties of these deep representations have strong similarities with Gestalt perception. However, the network filters do not need to be learned and can be adapted to prior information on geometry, with multiscale wavelets. This brings us back from learning everything to more traditional computer vision approaches. Classification results will be shown on multiple image data bases, with linear SVM applied to network outputs.

Tuesday Nov 4, Minoru Etoh, NTT Docomo

Title: How Changing Mobile and Media Technologies is Changing the Way We Create Innovations

According to Schumpeter's definition of "Innovation," all the innovation instances are combinations of technologies that already exist. In that context, this talk covers the combination of progress of mobile network technologies and media understanding technologies. When the first mobile phones of 2nd Generation came out, people thought it was only for speech communication and texting. Then the phones got cameras, GPS. accelerometers, near filed communication devices together with fat communication pipes, people in all walks of life started using mobile phones in various opportunities. It is noteworthy that the progress of media understanding applications remarkably creates big data in a way of virtuous cycle by service and technology developments. This talk also highlights big-data driven service developments and API strategies for mobile innovations as well as technologies.

Wednesday Nov 5, Dieter Fox, University of Washington

Title: RGB-D Perception in Robotics

RGB-D cameras provide per pixel color and depth information at high frame rate and resolution. Gaming and entertainment applications such as the Microsoft Kinect system resulted in the mass production of RGB-D cameras at extremely low cost, also making them available for a wide range of robotics applications. In this talk, I will provide an overview of depth camera research done in the Robotics and State Estimation Lab over the last five years. This work includes 3D mapping, autonomous object modeling, unsupervised feature learning for object recognition, and articulated object tracking.

Overview: Workshops and Tutorials (Nov 1-2)

4

Saturday, November 1

Room Global

Learning Room

LT50 LT51 LT52 LT53 SR2 SR4 SR6 SR7 SR8

AM

T6

- Min

ing

Im

age a

nd

Vid

eo

Data

W2

- 2n

d In

ternatio

nal W

orksh

op

on

Big

Data in

3D C

om

pu

ter Visio

n

W6

- Ro

Lo

D: R

ob

ust L

ocal D

escripto

rs

for C

om

pu

ter Visio

n

W12

- Featu

re an

d S

imilarity L

earnin

g

for C

om

pu

ter Visio

n

W1 - H

um

an G

ait

and

Actio

n

An

alysis in th

e

Wild

: Ch

alleng

es an

d A

pp

lication

s

W7 - E

merg

ing

To

pics In

Imag

e

Resto

ration

and

En

han

cem

ent

W15 - C

om

pu

ter Visio

n fo

r Affective

Co

mp

utin

g

W9

- 2n

d W

orksh

op

on

User-C

entred

Co

mp

uter V

ision

(UC

CV

20

14)

PM

T3 - R

ieman

nian

Geo

metry in

C

om

pu

ter Visio

n

T1 - C

olo

r

Tran

sfer

Sunday, November 2

Room Global

Learning Room

LT50 LT51 LT52 LT53 SR2 SR4 SR6 SR7 SR8

AM

W11 - M

y Car H

as Eyes - In

telligen

t Veh

icles w

ith V

ision

Tech

no

log

y

W16

- Wo

rksho

p o

n H

um

an Id

entifica

tion

for

Su

rveillance

W4

- Wo

rksho

p o

n S

cen

e Un

derstan

din

g fo

r A

uto

no

mo

us S

ystems

T2

- Ad

vance

d

Sp

arse R

epresen

tation

Mo

dels fo

r Imag

e an

d V

ideo

An

alysis

W8

- 1st Intern

ation

al Wo

rksho

p o

n R

ob

ust

Rea

din

g

W10

- Intern

ation

al Wo

rksho

p o

n V

ide

o

Seg

men

tation

in C

om

pu

ter Visio

n

W13 - 3rd

AC

CV

Wo

rksho

p o

n e

-Heritag

e

W14

- 3rd In

ternatio

nal W

orksh

op

on

Intellig

ent M

ob

ile an

d E

go

cen

tric Visio

n

PM

W3 - D

eep L

earnin

g

on

Visu

al D

ata

T5 - M

etric Learn

ing

fo

r Visu

al

Reco

gn

ition

T4

- Essen

ce o

f

Geo

metric A

lgeb

ra

Overview: Main Conference (Nov 3-5)

5

Day 1: Monday, November 3 Day 2: Tuesday, November 4 Day 3: Wednesday, November 5

0800 Registration Starts 0800 Registration Starts 0800 Registration Starts

0815 – 0900 Breakfast 0815 – 0900 Breakfast 0815 – 0900 Breakfast

0900 – 1015 Keynote 0900 – 1015 Keynote 0900 – 1015 Keynote

1015 – 1100 Coffee break 1015 – 1100 Coffee break 1015 – 1100 Coffee break

1100 – 1230 Oral Session 1 1100 – 1230 Oral Session 3 1100 – 1230 Oral Session 5

1230 – 1330 Lunch 1230 – 1330 Lunch 1230 – 1330 Lunch

1330 – 1515 Poster Session 1 1330 – 1515 Poster Session 2 1330 – 1515 Poster Session 3

1515 – 1600 Coffee Break 1515 – 1600 Coffee Break 1515 – 1600 Coffee Break

1600 – 1715 Oral Session 2 1600 – 1700 Oral Session 4 1600 – 1715 Oral Session 6

1830 BANQUET – HILTON HOTEL

(Grand Ballroom / 3rd Floor)

Organizing Committee, Area Chairs, & Outstanding Reviewers

6

ACCV 2014 Organizing Committee

General Chairs: Michael Brown Tat-Jen Cham Yasuyuki Matsushita

Program Chairs: Daniel Cremers

Ian Reid

Hideo Saito Ming-Hsuan Yang

Organizing Chairs: Teck Khim Ng Junsong Yuan

Workshops Chairs: CV Jawahar

Shiguang Shan

Demo Chairs: Bohyung Han

Koichi Kise

Tutorial Chairs: Cho-Song Chen

Brenden McCane

Publications Chairs: Terence Sim

Jianxin Wu

Industry Chairs: Hongcheng Wang

Brian Price

Antonio Robles-Kelly

Steering Committee: In-So Kweon

Yasushi Yagi

Hongbin Zha

Honorary Chair: Katushi Ikeuchi

ACCV 2014 Area Chairs Lourdes Agapito Thomas Brox Tat-Jun Chin Yung-Yu Chuang Larry Davis Yasutaka Furukawa Bastian Goldluecke Bohyung Han

Hiroshi Ishikawa C.V. Jawahar Jana Kosecka David Kriegman Shang-Hong Lai Ivan Laptev Kyoung Mu Lee Vincent Lepetit

Jongwoo Lim Simon Lucey Ajmal Mian Hajime Nagahara Ko Nishino Shmuel Peleg Imari Sato Shin'ichi Satoh

Stefano Soatto Jamie Shotton Ping Tan Lorenzo Torresani Manik Varma Xiaogang Wang Shuicheng Yan Qing-Xiong Yang

Jingyi Yu Junsong Yuan Hongbin Zha Lei Zhang

ACCV 2014 Outstanding Reviewers

We are pleased to recognize the following 35 researchers as "Outstanding Reviewers for ACCV 2014". These reviewers were

selected from over 600 reviewers for their hard work in providing detailed reviews for the papers assigned to them. These

reviewers were identified by one or more of the ACCV Area Chairs or Program Chairs who found their reviews of high quality.

Emre Akbas Jonathan Balzer Steve Branson Sanderson Conrad Marco Cristani Alessio Del Bue Anthony Dick

Bruce Draper Katerina Fragkiadaki Tatsuya Harada Mehrtash Harandi Nazli Ikizler-Cinbis Catalin Ionsecu Suha Kwak

Junseok Kwon Fuxin Li Chen-Change Loy Scott McCloskey Xing Mei Yasushi Makihara Guy Rosman

Mathieu Salzmann Pramod Sankar Walter Scheirer Bernt Schiele Chunhua Shen Sudipta Sinha Deqing Sun

Yuichi Taguchi Toru Tamaki Dong Wang Yu-Chiang Frank Wang Paul Wohlhart John Wright Bangpeng Yao

Saturday, November 1 Workshops

7

Saturday, November 1

0800–1700 Registration (Stephen Riady Centre−University Town)

W1 - Human Gait and Action Analysis in the Wild: Challenges and Applications

Organizers: Mark Nixon Liang Wang Jian Zhang Qiang Wu Zhaoxiang Zhang Yasushi Makihara

Location: SR2, Stephen Riady Centre at University Town, NUS

Schedule: Half Day

0855 Opening Remarks

0900 Invited Talk: Robust Gait Recognition, Yasushi

Makihara, Osaka University, Japan

0930 Real Time Gait Recognition System based on Kinect

Skeleton Feature, Shuming Jiang, Yufei Wang,

Yuanyuan Zhang, and Jiande Sun

0945 2-D Structure-Based Gait Recognition in Video Using

incremental GMM-HMM, Rui Pu, Yunhong Wang

1000 A new gait-based identification method using local

Gauss maps, Hazem El-Alfy, Ikuhisa Mitsugami and

Yasushi Yagi

1015 Enhancing Person Re-identication by Integrating Gait

Biometric, Zheng Liu, Zhaoxiang Zhang, Qiang Wu,

Yunhong Wang

1030 Coffee Break

1100 Gait Recognition based Online Person Identification in a

Camera Network, Ayesha Choudhary and Santanu

Chaudhury

1115 Hand Detection and Tracking in Videos for Fine-

grained Action Recognition, Nga H. Do and Keiji Yanai

1130 Unsupervised Temporal Ensemble Alignment for Rapid

Annotation, Ashton Fagg, Sridha Sridharan and Simon

Lucey

1145 Motion Boundary Trajectory for Human Action

Recognition, Sio-Long Lo and Ah-Chung Tsoi

1200 Action Recognition Using Hybrid Feature Descriptor

and VLAD Video Encoding, Dong Xing, Xianzhong

Wang, Hongtao Lu

1215 Gesture Recognition Performance Score: A New Metric

to Evaluate Gesture Recognition Systems, Pramod

Kumar Pisharady and Martin Saerbeck

1230 Human Action Recognition Based on Oriented Motion

Salient Regions, Baoxin Wu, Shuang Yang, Chunfeng

Yuan, Weiming Hu, and Fangshi Wang

1245 3D Activity Recognition using Motion History and

Binary Shape Templates, Saumya Jetley, Fabio Cuzzoli

W2 - 2nd International Workshop on Big Data in 3D Computer Vision Organizers: Jian Zhang Mohammed Bennamoun Fatih Porikli Ping Tan Hongdong Li Lixin Fan Qiang Wu

Location: LT50, Stephen Riady Centre at University Town, NUS

Schedule: Full Day

0915 Invited Talk: Textured Mesh Surface Reconstruction

of Large Buildings with Multi-View Stereo, Wee Kheng

Leow, NUS


8

0945 Global Volumetric Image Registration Using Local

Linear Property of Image Manifold, Hayato Itoh,

Atsushi Imiya, Tomoya Sakai

1000 3D Reconstruction of Planar Surface Patches: A Direct

Solution, Jozsef Molnar, Rui Huang, and Zoltan Kato

1015 A Comparative Study of GPU-Accelerated Multi-View

Sequential Reconstruction Triangulation Methods for

Large-Scale Scenes, Jason Mak, Mauricio Hess-Flores,

Sean Recker, John D. Owens, Kenneth I. Joy

1030 Coffee Break

1100 Depth-based real-time hand tracking with occlusion

handling using Kalman Filter and DAM-Shift, Kisang

Kim, Hyung-Il Choi

1115 Evaluation of Depth-Based Super Resolution on

Compressed Mixed Resolution 3D Video, Michal

Joachimiak, Payman Aflaki, Miska M. Hannuksela,

Moncef Gabbouj

1130 Completed Dense Scene Flow in RGB-D Space, Yucheng

Wang, Jian Zhang, Zicheng Liu, Qiang Wu1, Philip Chou,

Zhengyou Zhang, and Yunde Jia

1145 Indoor Objects and Outdoor Urban Scenes Recognition

by 3D Visual Primitives, Junsheng Fu, Joni-Kristian

Kämäräinen, Anders Glent Buch, Norbert Krüger

1200 Object Recognition in 3D Point Cloud of Urban Street

Scene, Pouria Babahajiani, Lixin Fan, Moncef Gabbouj

1215 Online Learning of Binary Feature Indexing for Real-

time SLAM Relocalization, Youji Feng, Yihong Wu, Lixin

Fan

W6 - RoLoD: Robust Local Descriptors for Computer Vision Organizers: Jie Chen Zhen Lei Li Liu Guoying Zhao Matti Pietikainen


Schedule: Full Day


0910 Opening Keynote: PASCAL VOC Classification: Local

Features vs. Deep Features, Shuicheng Yan

1015 Coffee Break

1040 Local Associated Features for Pedestrian Detection,

Song Shao, Hong Liu, Xiangdong Wang, Yueliang Qian

1100 Incorporating two first order moments into LBP-based

operator for texture categorization, Thanh Phuong

Nguyen, Antoine Manzanera

1120 Log-Gabor Weber Descriptor for Face Recognition, Jing

Li, Nong Sang, Changxin Gao

1140 Robust Line Matching Based on Ray-Point-Ray

Structure Descriptor, Kai Li, Jian Yao, Xiaohu Lu

1200 Lunch

1330 Evaluation of descriptors and distance measures on

benchmarks and first-person-view videos for face

identification, Bappaditya Mandal, Wang Zhikai, Liyuan

Li, Ashraf Kassim

1350 Performance evaluation of local descriptors for affine

invariant region detector, Man Hee Lee, In Kyu Park

1410 Local Feature based Multiple Object Instance

Identification using Scale and Rotation Invariant

Implicit Shape Model, Ruihan Bao, Kyota Higa, Kota

Iwamoto

1430 Local-to-Global Signature Descriptor for 3D Object

Recognition, Isma Hadji, Guilherme Desouza

1450 Efficient Detection for Spatially Local Coding, Sancho

McCann, David Lowe

1510 Hierarchical Local Binary Pattern for Branch Retinal

Vein Occlusion Recognition, Zenghai Chen, Hui Zhang,

Zheru Chi, Hong FU

1530 Coffee Break & Poster


9

Posters:

1. Unsupervised Footwear Impression Analysis and

Retrieval from Crime Scene Data, Adam Kortylewski,

Thomas Albrecht, Thomas Vetter (Board #01)

2. Reliable Point Correspondences in Scenes Dominated by

Highly Reflective and Largely Homogeneous Surfaces,

Srimal Jayawardena, Stephen Gould, Hongdong Li,

Marcus Hutter, Richard Hartley (Board #02)

3. ORB in 5ms: An efficient SIMD friendly implementation,

Prashanth Viswanath, Pramod Swami, Kumar Desappan,

Anshu Jain, Anoop Pathayapurakkal (Board #03)

4. Extended Keypoint Description and the Corresponding

Improvements in Image Retrieval, Andrzej Sluzek (Board

#04)

5. An Efficient Face Recognition Scheme Using Local

Zernike Moments (LZM) Patterns, Emrah Basaran,

Muhittin Gokmen (Board #05)

6. Face Detection Based on Multi-Block Quad Binary

Pattern, Zhubei Ge, Canhui Cai, Huanqiang Zeng, Jianqing

Zhu, Kai-Kuang Ma (Board #6)

1630 Closing Remarks

W7 - Emerging Topics on Image Restoration and Enhancement

Organizers: Zhe Hu, Oliver Cossairt, Yu-Wing Tai, Sunghyun Cho, Chih-Yuan Yang, Robby Tan


Schedule: Full Day


0940 Multi-view Image Restoration From Plenoptic Raw

Image, Shan Xu, Zhi-Liang Zhou, Nicholas Devaney

1000 Image Interpolation Based on Weighted and Blended

Rational Function, Yifang Liu, Yunfeng Zhang, Qiang

Guo, Caiming Zhang

1020 Coffee Break

1100 Invited Talk: Sai-Kit Yeung (Singapore Univ. of

Technology and Design)

1140 Image Enhancement by Gradient Distribution

Specification, Yuanhao Gong, Ivo Sbalzarini

1200 On the Choice of Tensor Estimation for Corner

Detection, Optical Flow and Denoising, Freddie Åström,

Michael Felsberg

1220 Lunch

1350 Invited Talk: Tentative

1430 Feature-preserving Image Restoration from Adaptive

Triangular Meshes, Ke Liu, Ming Xu,Zeyun Yu

1450 A Two-step Image Inpainting Algorithm using Tensor

SVD, Mrinmoy Ghorai, Bhabatosh Chanda, Sekhar

Mandal

1510 Coffee Break

1550 Rock Image Denoising by Fast Bilateral Filtering,

Giuseppe Papari, Nasiru Idowu, Trond Varslot

1610 Adaptive Transmission Compensation via Human

Visual System for Robust Single Image Dehazing,

Zhigang Ling, Shutao Li, Yaonan Wang, Xiao Lu


W9 - User-Centred Computer Vision

Organizers: Gregor Miller Darren Cosker Kenji Mase


Schedule: Full Day


10

0900 Introduction to UCCV, Gregor Miller

0930 An Abstraction for Correspondence Search using Task-

Based Controls, Gregor Miller, Sidney Fels

0950 Towards Efficient Feedback Control in Streaming

Computer Vision Pipelines, Mohamed A. Helala, Ken Q.

Pu, Faisal Z. Qureshi

1010 Debugging Object Tracking Results by a Recommender

System with Correction Propagation, Mingzhong Li,

Zhaozheng Yin

1030 Coffee Break

1100 Interactive Shadow Editing from Single Images, Han

Gong, Darren Cosker

1120 Colour Matching Between Stereo Pairs of Images,

Stephen Willey, Phil Willis, Jeff Clifford, Ted Waine

1140 User Directed Multi-View-Stereo, Yotam Doron, Neill

Campbell, Jon Starck, Jan Kautz

1200 3D Interaction Through a Real-Time Gesture Search

Engine, Shahrouz Yousefi, Haibo Li

1220 Lunch Break

1330 Invited Talk:

(TBC, see http://www.openvl.org/UCCV/ for updates)

1430 Hand Part Classification using Single Depth Images,

Myoung-Kyu Sohn, Dong-Ju Kim, Hyunduk Kim

1450 Human Tracking using a Far-Infrared Sensor Array and

a Thermo-Spatial Sensitive Histogram, Takashi

Hosono, Tomokazu Takahashi, Daisuke Deguchi, Ichiro

Ide, Hiroshi Murase, Tomoyoshi Aizawa, Masato Kawade

1510 Feature Point Tracking Algorithm Evaluation for

Augmented Reality in Handheld Devices, Amila Perera,

Akila Pemasiri, Sameera Wijayarathna, Chameera

Wijebandara, Chandana Gamage

1530 Closing Remarks & Discussion

(with Coffee Break)

W12- Feature and Similarity Learning for Computer Vision (FSLCV) Organizers: Jiwen Lu Shenghua Gao Gang Wang Weihong Deng

Location: LT52, Stephen Riady Centre at U Town, NUS

Schedule: Full Day


0910 Invited Talk: Prof. Xudong Jiang (Nanyang

Technologival University, Singapore)

0955 Oral 1: Everything is in the Face? Represent Faces with

Object Bank, Xin Liu, Shiguang Shan, Shaoxin Li,

Alexander G. Hauptmann

1010 Oral 2: Feature Learning for the Image Retrieval Task,

Aakanksha Rana, Joaquin Zepeda, Patrick Perez

1025 Coffee Break

1100 Oral 3: A Simple Stochastic Algorithm for Structural

Features Learning, Jan Macak, Ondrej Drbohlav

1115 Oral 4: Learning Discriminative Hidden Structural Parts

for Visual Tracking, Longyin Wen, Zhaowei Cai, Dawei

Du, Zhen Lei, Stan Z. Li

1130 Oral 5: 3D Laplacian Pyramid Signature, Kaimo Hu, Yi

Fang

1145 Lunch Break + Poster Session (15 papers)

1. Spectral Shape Decomposition by Using a Constrained

NMF Algorithm, Foteini Fotopoulou, Emmanouil Psarakis

2. Inter-Concept Distance Measurement with Adaptively

Weighted Multiple Visual Features, Kazuaki Nakamura,

Noboru Babaguchi

3. Extended Supervised Descent Method for Robust Face

Alignment, Liu Liu, Jiani Hu, Shuo Zhang, Weihong Deng


11

4. Evaluation of Smile Detection Methods with Images in

Real-world Scenarios, Zhoucong Cui, Shuo Zhang, Jiani

Hu, Weihong Deng

5. Adaptive Region Merging Approach for Morphological

Color Image Segmentation, Huang-Chia Shih, En-Rui Liu

6. Local Similarity based Linear Discriminant Analysis for

Face Recognition with Single Sample per Person, Fan

Liu, Ye Bi, Yan Cui, Zhenmin Tang

7. Person Re-identification Using Clustering Ensemble

Prototypes, Aparajita Nanda, Pankaj K Sa

8. Automatic Lung Tumor Detection Based on GLCM

Features, Mir Rayat Imtiaz Hossain, Imran Ahmed, Md.

Hasanul Kabir

9. Metric Tensor and Christoffel Symbols based 3D Object

Categorization, Syed Altaf Ganihar, Shreyas Joshi,

Shankar Setty, Uma Mudenagudi

10. Quasi Cosine Similarity Metric Learning, Xiang Wu, Zhi-

guo Shi, Lei Liu

11. Hand gesture recognition based on the parallel edge

finger feature and angular projection, Yimin Zhou, Guolai

Jiang, Guoqing Xu, Yaorong Lin

12. Image Retrieval by Using Non-Subsampled Shearlet

Transform and Krawtchouk Moment Invariants, Cheng

Wan, Yiquan Wu

13. Image Based Visibility Estimation During Day and Night,

Sami Varjo, Jari Hannuksela

14. Symmetric Feature Extraction for Pose Neutralization, S

G Charan

15. Commonality Preserving Multiple Instance Clustering

Based On Diverse Density, Takayuki Fukui, Toshikazu

Wada

1430 Oral 6: Learning Partially Shared Dictionaries for

Domain Adaptation, Viresh Ranjan, Gaurav Harit, C. V.

Jawahar

1445 Oral 7: Curve Matching from the View of Manifold for

Sign Language Recognition, Yushun Lin, Xiujuan Chai,

Yu Zhou, Xilin Chen

1500 Oral 8: Blur-Robust Face Recognition via

Transformation Learning, Jun Li, Chi Zhang, Jiani Hu,

Weihong Deng

1515 Coffee Break

1545 Invited talk: Dr. Jialin Pan (Institute of Infocomm

Research, Singapore)

1630 Oral 9: A Flexible Semi-Supervised Feature Extraction

Method for Image Classification, Fadi Dornaika, Youssof

El Traboulsi

1645 Oral 10: Discovering Multi-Relational Latent Attributes

by Visual Similarity Networks, Fatemeh Shokrollahi

Yancheshmeh, Joni-Kristian Kamarainnen, Ke Chen

1700 ZTE Best Paper Award and Closing Remark

W15- First Workshop on Computer Vision for Affecive Computing

Organizers: Abhinav Dhall Roland Goecke Nicu Sebe


Schedule: Full Day

0850 Invited Talk: Simon Lucey (Carnegie Mellon

University)

Trading Feature Complexity with Alignment Accuracy:

A Question for Computer Vision?

0950 Deeply Learning Deformable Facial Action Parts Model

for Dynamic Expression Analysis, Mengyi Liu, Ruiping

Wang, Shiguang Shan, Xilin Chen


12

1010 Recognition of Facial Action Units with Action Unit

Classifiers and an Association Network, Junkai Chen,

Zenghai Chen, Zheru Chi , Hong Fu,

1030 Coffee Break

1050 Invited Talk: Xiaogong Wang (Chinese University of

Hong Kong) Deep Learning for Face Analysis

1150 A Non-invasive Facial Visual-Infrared Stereo Vision

Based Measurement as an Alternative for Physiological

Measurement, Mohd Norzali Haji Mohd, Masayuki

Kashima, Kiminori Sato, Mutsumi Watanabe

1210 A Delaunay-Based Temporal Coding Model for Micro-

expression Recognition, Zhaoyu Lu, Ziqi Luo, Huicheng

Zheng, Jikai Chen, Weihong Li

1230 Lunch

1330 Invited Talk: Guoying Zhao (University of Oulu)

Facial expression and micro-expression analysis:

progress and challenges (Tentative)

1430 A Robust Learning Framework Using PSM and

Ameliorated SVMs for Emotional Recognition, Jinhui

Chen, Tetsuya Takiguchi, Yasuo Ariki

1450 Subtle Expression Recognition using Optical Strain

Weighted Features, Sze Teng Liong, John See, Raphael

C.-W. Phan, Anh Cat Le Ngo, Yeehui Oh, KokSheik Wong

1510 Coffee Break

1540 Task-driven Saliency Detection on Music Video,

Shunsuke Numano, Naoko Enami, Yasuo Ariki

1600 Facial Expression Recognition based on Multi-view

Observations with Application to Social Robotics,

Bogdan Raducanu, Alireza Bossaghzadeh, Fadi Dornaika

1620 Spontaneous Subtle Expression Recognition:

Imbalanced Databases & Solutions, Anh Cat Le Ngo,

Raphael C.-W. Phan, John See

Saturday, November 1 Tutorials

13

T1 - Color Transfer Organizers: Sira Ferradans Marcelo Bertalmio

Time: 1330 − 1700 (Half Day)


Description: Color transfer is the problem of imposing the

color palette of an image I1 on an image I2, without changing

the spatial geometry of I2. It may be the case that the color

distribution or the target characteristics are predefined, such

as an equalized histogram, or an image without a colored

illuminant. Both problems are computationally challenging

since they need to take into account the color and spatial

domain information.

This tutorial will present a state-of-the-art and unifying

perspective of the color transfer problem between two or

more images. We will also relate them to other important

problems such as illuminant change or object recolorization.

Our goal is to give a rigorous approach, that allows to

understand the challenges of these problems, how the

different assumptions made in the literature affect the final

result, and how these problems are related together.

Moreover, after the tutorial the audience should have an

intuition of when and why the different algorithms in the

literature can be applied, and the issues that still remain to be

solved.

T3- Riemannian Geometry in Computer Vision

Organizers: Fatih Porikli Mehrtash Harandi Conrad Sanderson

Time: 1330 − 1700 (Half Day)


Description: In computer vision, it is general practice to

consider constraints and models to make a problem tractable.

We can see many traces of such simplifying assumptions from

the front-end (pinhole camera model or the Lambertian

reflectance model), to data modelling and decision making.

One of the biggest, yet unjustified, assumptions in computer

vision is the notion of flat (non-curved) spaces — most of the

time we tend to solve our tasks using the traditional

Euclidean space.

Recent research in machine learning and computer vision

shows that improved discrimination accuracies (lower error

rates) can be achieved by explicitly taking into account the

curved nature of many representations. This includes

applications such as texture classification, action recognition,

video-based face recognition, identity re-identification, and

object tracking.

The use of Riemannian geometry to handle curved spaces has

been fundamental in physics since Einstein and perhaps

earlier. Traditionally, ‘manifold-learning’ methods have been

at the forefront of these applications where an analytical

characterisation of non-flat spaces cannot be found. In the

past few years, computer vision researchers have made

significant advancement in the analytical and geometric

understanding of the non-flat spaces. This makes an

important development in computer vision by moving away

from purely data-driven approaches to incorporate more prior

information via geometry-based approaches. This tutorial will

address the key points in developing efficient learning

methods and tools for image/video content analysis using

Riemannian manifolds.

Saturday, November 1 Tutorials

14

T6 - Mining Image and Video Data

Organizers: Junsong Yuan Ying Wu

Time: 0900 − 1230 (Half Day)

Location: Global Learning Room, Stephen Riady Centre at University Town, NUS

Description: Motivated by the previous success in mining

structured data (e.g., transaction data) and semi-structured

data (e.g., text), it has aroused our curiosity in mining

meaningful patterns in non-structured multimedia data like

images and videos. Although the discovery of visual patterns

from images and videos appears to be quite exciting, data

mining techniques that are successful in business and text

data may not be simply applied to image and video data that

contain high-dimensional features and have spatial or spatio-

temporal structures. Unlike transaction and text data that are

composed of discrete elements without much ambiguity (i.e.

predefined items and vocabularies), visual patterns generally

exhibit large variabilities in their visual appearances, thus

challenge existing data mining and pattern discovery

algorithms. This tutorial will discuss the state of the art of

image and video data mining, and provide in-depth studies on

some of the recently developed techniques. The topics cover

the co-occurrence visual pattern discovery, context-aware

clustering of visual primitives, topic model for pattern

discovery, as well as their applications in image search and

recognition, scene understanding, video summarization and

anomaly detection, intelligent video surveillance, etc.

Sunday, November 2 Workshops

15

Sunday, November 2

0800–1700 Registration (Stephen Riady Centre−University Town)

W3 - Deep Learning on Visual Data Organizers: Wanli Ouyang Xiaogang Wang Kai Yu Quoc Le Shuicheng Yan


Schedule: Half Day

1330 Opening Talk

1335 Invited Talk: Chen Change Loy (CUHK)

1400 Invited Talk: Yi Li (NICTA)

1425 Hybrid CNN-HMM Model for Street View House

Number Recognition, Qiang Guo, Dan Tu, Guohui Li,

Jun Lei

1440 View and illumination invariant object classification

based on 3D Color Histogram using Convolutional

Neural Networks, Earnest Paul Ijjina, Krishna Mohan C

1455 Human action recognition using action bank features

and convolutional neural networks, Earnest Paul Ijjina,

Krishna Mohan C

1515 Coffee Break and poster session

1545 Invited Talk: Hanlin Goh (Astar)

1610 Invited Talk: Cris Jia (University of Macau)

1635 Deep Learning in the EEG Diagnosis of Alzheimer's

Disease, Yilu Zhao

1650 Pedestrian Detection with Deep Convolutional Neural

Network, Xiaogang Chen, Pengxu Wei, Wei Ke, Qixiang

Ye, Jianbin Jiao

1705 Poster session

1. Deep Representations to Model User 'Likes', Sharath

Chandra Guntuku, Joey Tianyi Zhou, Sujoy Roy, Weisi Lin,

Ivor W. Tsang

2. Deep Convolutional Neural Networks for Efficient Pose

Estimation in Gesture Videos, Tomas Pfister, Karen

Simonyan, James Charles, Andrew Zisserman

3. Robust Online Visual Tracking with a Single

Convolutional Neural Network, Hanxi Li, Yi Li, Fatih

Porikli

4. Topic-aware Deep Auto-encoders (TDA) for Face

Alignment, Jie Zhang, Meina Kan, Shiguang Shan,

Xiaowei Zhao, Xilin Chen

5. Part Detector Discovery in Deep Convolutional Neural

Networks, Marcel Simon, Erik Rodner, Joachim Denzler

6. MoNet: A Deep Learning Framework Using Motion

Features for Human Pose Estimation, Arjun Jain,

Jonathan Tompson, Christoph Bregler

7. 3D Human Pose Estimation from Monocular Images

with Deep ConvolutionalNeural Network, Sijin LI, Antoni

Chan

8. Plant Leaf Identification via A Growing Convolution

Neural Network with Progressive Sample Learning,

Zhong-Qiu Zhao, Bao-Jian Xie

9. Deeply Learning Deformable Facial Action Parts Model

for Dynamic Expression Analysis, Mengyi Liu, Shaoxin Li,

Shiguang Shan, Ruiping Wang, Xilin Chen

10. Understanding Convolutional Neural Networks in Terms

of Category-level Attributes, Makoto Ozeki, Takayuki

Okatani

11. Robust Scene Classification with Cross-level LLC Coding

on CNN Features, Zequn Jie, Shuicheng Yan


16

W4 - Scene Understanding for Autonomous Systems

Organizers: Sebastian Ramos Raquel Urtasun Antonio Torralba Nick Barnes Markus Enzweiler David Vazquez Antonio M. Lopez


Schedule: Full Day


0905 Invited Talk: Making Bertha See, David Pfeiffer

(Daimler Research, Germany)

0955 Poster Spotlights (2min per poster)

1015 Coffee Break

1100 Invited Talk: How to Rule the World with Your Smart

Phone, Simon Lucey (Carnegie Mellon University, USA)

1150 Poster Session:

1. Surface Prediction for a Single Image of Urban

Scenes, Foat Akhmadeev (KPFU)

2. Scene parsing and fusion-based continuous

traversable region formation, Xuhong Xiao (DSO), Gee

Wah Ng (DSO), Yuan Sin Tan (DSO), Ye Chuan Yeo

(DSO)

3. Combining Multiple Shape Matching Techniques with

Application to Place Recognition Task, Karel Košnar

(ČVUT), Vojtěch Vonásek (ČVUT), Miroslav Kulich

(ČVUT), Libor Přeučil (ČVUT)

4. A Model-based Approach for Fast Vehicle Detection

in Continuously Streamed Urban LIDAR Point Clouds,

Attila Börcs (MTA SZTAKI), Balázs Nagy (MTA SZTAKI),

Milán Baticz (MTA SZTAKI), Csaba Benedek (MTA

SZTAKI)

5. Large-scale Indoor/Outdoor Image Classification via

Expert Decision Fusion (EDF), Chen Chen (USC),

Yuzhuo Ren (USC), C.-C. Jay Kuo (USC)

6. Search Guided Saliency, Shijian Lu (I2R), Byung Uck

Kim (I2R), Nicolas Lomenie (I2R), Joo-Hwee Lim (I2R),

Jianfei Cai (NUT)

7. Salient Object Detection via Saliency Spread, Dao

Xiang (USTC), ZiLei Wang (USTC)

8. Biologically Inspired Composite Vision System for

Multiple Depth-of-field Vehicle Tracking and Speed

Detection, Lin Lin (NUS), Bharath Ramesh (NUS),

Cheng Xiang (NUS)

9. Robust Maximum Margin Correlation Tracking, Han

Wang (NLPR), Yancheng Bai (NLPR), Ming Tang (NLPR)

10. Scene Classification by Feature Co-occurrence Matrix,

Haitao Lang (BUCT & TU Philadelphia), Yuyang Xi

(BUCT), Jianying Hu (BUCT), Liang Du (TU

Philadelphia), Haibin Ling TU Philadelphia)

11. Invited Paper: Stixmantics: A Medium-Level Model for

Real-Time Semantic Scene Understanding, Timo

Scharwächter (Daimler), Markus Enzweiler (Daimler),

Uwe Franke (Daimler) and Stephan Roth (TU

Darmstadt)

12. Invited Paper: Vision-based Offline-Online Perception

Paradigm for Autonomous Driving, German Ros (CVC

& UAB), Sebastian Ramos (CVC & UAB), Manuel

Granados (UAB), Amir Bakhtiary (UOC), David Vazquez

(CVC & UAB), Antonio M. Lopez (CVC & UAB)

1230 Lunch Break

1335 Invited Talk: Sensors, Maps, and Prior Knowledge:

Perception for Automated Vehicles, Michael James

(Toyota Research, USA)

1425 Invited Talk: Photometric Analysis for Autonomous

Systems, Katsushi Ikeuch (University of Tokyo, Japan)

1515 Coffe Break

1600 Invited Talk: Autonomous Driving Technologies and

Scene Understanding, Abdelaziz Khiat (Nissan

Research, Japan)



17

W8 - 1st International Workshop on Robust Reading (IWRR2014) Organizers: Masakazu Iwamura Dimosthenis Karatzas Faisal Shafait Pramod Sankar Kompalli


Schedule: Full Day

900 Opening Remarks

905 Introductory Talk: Introduction to Robust Reading

Problem, Organizers

930 Keynote Talk: Text Reading in the Wild - How to make

it useful?, Lukáš Neumann, Jiří Matas (Czech Technical

University in Prague)

1030 Coffee Break

1100 Text Localization Based on Fast Feature Pyramids and

Multi-Resolution Maximally Stable Extremal Regions,

Alessandro Zamberletti, Lucia Noce, Ignazio Gallo

1120 A Hybrid Approach to Detect Texts in Natural Scenes by

Integration of a Connected-Component Method and a

Sliding-Window Method, Yojiro Tonouchi, Kaoru Suzuki,

Kunio Osada

1140 Robust Text Segmentation in Low Quality Images via

Adaptive Stroke Width Estimation and Stroke based

Superpixel Grouping, Anna Zhu, Guoyou Wang, Yangbo

Dong

1200 Efficient Character Skew Rectification in Scene Text

Images, Michal Busta, Tomas Drtina, David Helekal,

Lukas Neumann and Jiri Matas

1230 Lunch

1400 Performance Improvement of Dot-Matrix Character

Recognition by Variation Model Based Learning, Koji

Endo, Wataru Ohyama, Tetsushi Wakabayashi and

Fumitaka Kimura

1420 Scene Text Recognition: No Country for Old Men?, Lluis

Gomez, Dimosthenis Karatzas

1440 A Machine Learning Approach to Hypothesis Decoding

in Scene Text Recognition, Jindrich Libovicky, Lukas

Neumann, Pavel Pecina, Jiri Matas

1500 Perspective Scene Text Recognition with Feature

Compression and Ranking, Yu Zhou, Shuang Liu,

Yongzheng Zhang, Yipeng Wang, Weiyao Lin

1530 Coffee Break

1600 Keynote Talk: PhotoOCR: Reading Text in

Uncontrolled Conditions, Alessandro Bissacco (Google

Inc.)

1700 Panel Discussion


W10- International Workshop on Video Segmentation in Computer Vision

Organizers: Michael Ying Yang Jason Corso


Schedule: Full Day


0910 Adaptive Foreground Extraction for Crowd Analytics

Surveillance on Unconstrained Environments,

Mohamed Abul Hassan, Aamir Saeed Malik, Walter

Nicolas, Ibrahima Faye

0940 A Fast Object Detecting-Tracking Method in

Compressed Domain, Zenglei Qian, Jiuzhen Liang,

Zhiguo Niu, Yongcun Xu, Qin Wu

1010 Coffee Break

1100 Keynote Talk: Jianfei Cai (NTU)

1200 Automatic RoI Detection for Camera-based Pulse-rate

Measurement, Ron van Luijtelaar, Wenjin Wang, Sander

Stuijk, Gerard de Haan


18

1230 Lunch Break

1340 Sparse Optimization for Motion Segmentation, Michael

Ying Yang, Sitong Feng, Bodo Rosenhahn

1410 Keynote Talk: Joern Jachalsky (Technicolor)

1510 Coffee Break

1600 Background Subtraction: Model-sharing Strategy

Based on Temporal Variation Analysis, Yufeng Chen,

Kun Zhao, Wenzhe Wu, Shikai Liu

1630 Panel Discussion

W11 - My Car Has Eyes - Intelligent Vehicles with Vision Technology

Organizers: Xue Mei Andreas Geiger Michael James Yi-Ping Hung Fatih Porikli Danil Prokhorov

Location: Global Learning, Stephen Riady Centre at University Town, NUS

Schedule: Full Day


0910 Invitied Talk: (TBD), Seiichi Mita

1000 Path Planning for Unmanned Vehicle Motion based on

Road Detection using Online Road Map and Satellite

Image, Van-Dung Hoang, Danilo Caceres Hernandez,

Alexander Filonenko, and Kang-Hyun Jo

1020 Part-based RDF for Direction Classification of

Pedestrians, and a Benchmark, Junli Tao and Reinhard

Klette

1040 Coffee Break

1100 Invitied Talk, Building Blocks for Visual 3D Scene

Understanding towards Autonomous Driving, Yuanqing

Lin

1150 Detection and Recognition of Road Markings in

Panoramic Images, Cheng Li, Ivo Creusen, Lykele

Hazelho, and Peter H.N. de With

1210 Lunch

1345 Invitied Talk, Visual Tracking with Uncertainty of

Probabilistic Models, Kyoung Mu Lee

1435 Uncertainty Estimation for KLT Tracking, Sameer

Sheorey, Shalini Keshavamurthy, Huili Yu, Hieu Nguyen

and Clark N. Taylor

1455 A Two Phase Approach for Pedestrian Detection,

Soonmin Hwang, Tae-Hyun Oh, In So Kweon

1515 Coffee Break

1545 Invitied Talk: Four-Dimensional Virtual City and

Autonomous Driving, Katsushi Ikeuchi

1635 Driver Assistance System Providing an Intuitive

Perspective View of Vehicle Surrounding, Yen-Ting Yeh,

Chun-Kang Peng, Kuan-Wen Chen, Yong-Sheng Chen,

and Yi-Ping Hung


W13 - 3rd ACCV Workshop on E-Heritage

Organizers: Takeshi Oishi Ioannis Pitas Bo Zheng Manjunath Joshi Anupama Mallik


Schedule: Full Day

0905 Welcome Talk: Katsushi Ikeuchi (The University of

Tokyo, Japan)


19

0950 A BRDF Representing Method Based on Gaussian

Process, Jianying Hao, Yue Liu, Dongdong Weng

1010 A Performance Evaluation of Feature Descriptors for

Image Stitching in Architectural Images, Prashanth

Balasubramanian, Vinay Kumar Verma, Anurag Mittal

1030 Coffee Break

1045 Invited Talk: Kyoko Sengoku-Haga (Tohoku

University, Japan)

1130 Enhancement and Retrieval of Historic Inscription

Images, S. Indu, Ayush Tomar, Aman Raj, Santanu

Chaudhury

1150 Categorization of Aztec Potsherds using 3D Local

Descriptors, Edgar Roman-Rangel ,Diego Jimenez-

Badillo, Estibaliz Aguayo-Ortiz

1210 Lunch Break

1330 Invited Talk: Santanu Chaudhury (Indian Institute of

Technology Delhi, India)

1415 Image Parallax based Modeling of Depth-layer

Architecture, Yong Hu, Bei Chu, Yue Qi

1435 Combined hapto-visual and auditory rendering of

cultural heritage objects, Praseedha Aniyath, Sreeni

K.G., Priyadarshini Kumari , Subhasis Chaudhuri

1500 Coffee Break

1520 Realistic Walkthrough of Cultural Heritage Sites-

Hampi, Uma Mudenagudi, Syed Altaf Ganihar, Shreyas

Joshi, Shankar Setty, Rahul G., Somashekhar Dhotrad

Meera NatampallyPrem Kalra

1540 3D model automatic exploration: Smooth and

Intelligent Virtual Camera Control, Zaynab Habibi,

Guillaume Caron, El Mustapha Mouaddib

1600 A Method for Extracting Text from Stone Inscriptions

using Character spotting, Shashaank Aswatha, Ananth

Nath Talla, Jayanta Mukhopadhyay, Partha Bhowmick

1620 Mesh Denoising Using Multi-scale Curvature-based

Saliency, Somnath Dutta, Sumandeep Banerjee, Prabir

Biswas, Partha Bhowmick


W14 - 3rd International Workshop on Intelligent Mobile and Egocentric Vision

Organizers: Chu-Song Chen Shang-Hong Lai Joo Hwee Lim Vijay Chandrasekhar Liyuan Li Yu-Chiang Frank Wang Cheston Tan Zhao Qi


Schedule: Full Day


0910 Hybrid Feature and Template Based Tracking for

Augmented Reality Application, Gede Putra Kusuma

Negara, Fong Wee Teck, Li Yiqun

0930 A Mobile Augmented Reality Framework for Post-

stroke Patient Rehabilitation, Sujay Babruwad, Rahul

Avaghan, Uma Mudenagudi

0950 Invited Talk: Crossing between Reality and Virtuality,

Yi-Ping Hung (National Taiwan University)

1030 Coffee Break

1100 Interactive RGB-D SLAM on Mobile Devices, Nicholas

Brunetto, Nicola Fioraio, Luigi Di Stefano

1120 3D Reconstruction with Automatic Foreground

Segmentation from Multi-View images Acquired from

a Mobile Device, Ping-Cheng Kuo, Chao-An Chen, Hsing-

Chun Chang, Te-Feng Su, Shang-Hong Lai

1140 Collaborative Mobile 3D Reconstruction of Urban

Scenes, Attila Tanacs, Andras Majdik, Levente Hajder,

Jozsef Molnar, Zsolt Santa, Zoltan Kato

1200 Estimation of 3-D Foot Parameters Using Hand-Held

RGB-D Camera, Yang-Sheng Chen, Yu-Chun Chen,

Peng-Yuan Kao, Sheng-Wen Shih, Yi-Ping Hung

1220 Lunch


20

1330 Invited Talk: Continuous Action and Gesture

Recognition in Real-Time, Junsong Yuan (NTU,

Singapore)

1410 A Wearable Face Recognition System on Google Glass

for Assisting Social Interactions, Bappaditya Mandal,

Shue Ching Chia, Liyuan Li, Vijay Chandrasekhar,

Cheston Tan, Joo Hwee Lim

1430 Lifelog Scene Change Detection Using Cascades of

Audio and Video Detectors, Katariina Mahkonen, Joni-

Kristian Kamarainen, Tuomas Virtanen

1450 Activity Recognition in Egocentric Life-logging Videos,

Sibo Song, Vijay Chandrasekhar, Ngai-Man Cheung,

Sanath Narayan, Liyuan Li, Joo Hwee Lim

1510 Coffee Break

1540 Accelerating Local Feature Extraction Using Two Stage

Feature Selection and Partial Gradient Computation,

Keundong Lee, Seungjae Lee, Weon-Geun Oh

1600 Integrated Vehicle and Lane Detection with Distance

Estimation, Yu-Chun Chen, Te-Feng Su, Shang-Hong Lai

1620 3D Line Segment Based Model Generation by RGB-D

Camera for Camera Pose Estimation, Yusuke

Nakayama, Hideo Saito, Masayoshi Shimizu, Nobuyasu

Yamaguchi

1640 Demos

1. Wearable cognitive assistant on Google Glass for

Social Interaction based on Face Recognition (video &

real world demo)

2. Collaborative 3D reconstruction of planar surfaces

from mobile camera on Android devices

3. Wearable Visual Usher for Cognitive Indoor Navigation

(video demo)

W16- Workshop on Human Identification for Surveillance (HIS)

Organizers: Tao Xiang Nalini K. Ratha Venu Govindaraju Meina Kan Wei-Shi Zheng Marco Cristani


Schedule: Full Day


0900 Invited Talk: Learning Metric on Riemannian Manifold

for Video based Face Recognition (Ruiping Wang).

0945 Gait-assisted Person Re-identification in Wide Area

Surveillance. Apurva Bedagkar-Gala and Shishir K.

Shah.

1000 People Re-identification Based on Bags of Semantic

Features. Zhi Zhou, Yue Wang and Eam Khwang Teoh.

1015 Gaussian Descriptor based on Local Features for

Person Re-identification. Bingpeng Ma, Qian Li and

Hong Chang.

1030 Coffee Break

1100 Cross Dataset Person Re-identification. Yang Hu, Dong

Yi, Shengcai Liao, Zhen Lei and Stan Z. Li.

1115 Privacy Preserving Multi-target Tracking. Anton Milan,

Stefan Roth, Konrad Schindler and Mineichi Kudo.

1130 Tracking Pedestrians across Multiple Cameras via

Partial Relaxation of Spatio-Temporal Constraint and

Utilization of Route Cue. Toru Kokura, Yasutomo

Kawanishi, Masayuki Mukunoki and Michihiko Minoh.

1145 Multi-Target Tracking with Sparse Group Features and

Position using Discrete-Continuous Optimization. Billy

Peralta and Alvaro Soto.


21

1200 Lunch

1330 Face Recognition with Image Misalignment via

Structure Constraint Coding. Ying Tai, Jianjun Qian, Jian

Yang and Zhong Jin.

1345 Pose-Independent Identity-based Facial Image

Retrieval using Contextual Similarity. Islam Almasri.

1400 Discovering Person Identity via Large-Scale

Observations. Yongkang Wong, Lekha Chaisorn and

Mohan S. Kankanhalli.

1415 Spatio-temporal Consistency for Head Detection in

High-Density Scenes. Emanuel Aldea, Davide Marastoni

and Khurom H. Kiyani.

1430 Robust Ear Recognition using Gradient Ordinal

Relationship Pattern. Aditya Nigam and Phalguni

Gupta.

1445 Full-Body Human Pose Estimation from Monocular

Video Sequence via Multi-Dimensional Boosting

Regression. Yonghui Du, Yan Huang and Jingliang Peng.

1500 Coffee Break

1530 Improve Pedestrian Attribute Classification by

Weighted Interactions from Other Attributes. Jianqing

Zhu, Shengcai Liao, Zhen Lei and Stan Z. Li.

1545 Hybrid Focal Stereo Networks for Pattern Analysis in

Homogeneous Scenes. Emanuel Aldea1 and Khurom H.

Kiyani.


Sunday, November 2 Tutorials

22

T2 - Advanced Sparse Representation Models for Image and Video Analysis

Organizers: Shenghua Gao Kui Jia Tianzhu Zhang Weisheng Dong

Time: 0900 −1230 (Half Day)


Description: Intrinsic structures of high-dimensional visual

data often have the properties of low dimensionality,

sparsity, or degeneracy. By discovering and properly

harnessing these intrinsic structures, groundbreaking results

have been achieved in the past decade on diverse applications

in the domains of signal/image processing, computational

neuroscience, computer vision, and machine learning.

Mathematical concepts that characterize these intrinsic

structures include, but not limited to, sparsity, group sparsity,

structured sparsity, and low-rank. Besides, other low-

complexity structures of visual data also prevail in practical

applications and systems. We term these models considering

data sparsity and low-complexity structures as Advanced

Sparse Representation Models. This tutorial aims to present

the very recent breakthroughs in computer vision and image

processing research. These results are achieved by leveraging

new powerful, more advanced sparse representation models

and by developing efficient large-scale optimization

algorithms.

The tutorial will start with introducing the basic theory of

sparse/low-rank recovery, with its generalization to more

advanced sparse models which considers other structures of

the data, for example, locality information, group sparse

structure, nonlinear structure, tree-guided structure, etc. We

introduce these concepts in the context of signal processing

and from the perspectives of geometric intuition, formal

definition, and recovery conditions, with motivating

applications. Following introduction of basic theory, we

present choices of algorithms that can better cope with the

issues of non-smoothness and scale, commonly occurring in

the large-scale optimization problems of sparsity/low-rank

models. Intrinsic low-dimensional structures are among the

most fundamental phenomena in natural images due to rich

local regularities, global symmetries, repetitive textures, or

redundant sampling. This tutorial will continue with

presenting the very recent breakthroughs in image

processing. These results are essentially obtained by properly

harnessing these rich low-dimensional structures prevailing in

natural images, using carefully designed more advanced

models with sparsity/low-rank constraints, for various low-

level vision tasks including image de-noising, de-blurring,

super-resolution, and compressive sensing, etc. We will

specially show that how local sparsity/low-rank models and

non-local self-similarity of natural images are exploited to

achieve these breakthrough results.

Intrinsic low-dimensional structures are not limited to low-

level image processing. High-level semantic concepts, which

may be hidden in massive high-dimensional and less

organized visual data, can also be discovered by learning low-

dimensional invariant representations of the concepts of

interest. In the third session of this tutorial, we will present

striking results recently obtained in computer vision research.

We cover a variety of mainstream vision applications ranging

from face/object recognition, object alignment, feature

correspondence/matching, tracking, to unsupervised object

discovery and ambiguous learning. We will introduce the

respective nature of these problems and explain the principles

in designing more advanced sparse representation models in

order to harness their problem nature and achieve striking

performance. In the fourth part, we will also discuss how the

advanced sparse representation models can be used for video

tracking tasks.

Sunday, November 2 Tutorials

23

T4 - Essence of Geometric Algebra Organizers: Kenichi Kanatani



Description: I introduce “geometric algebra”, which recently

has been attracting attention of many computer vision and

graphics researchers. Many b o oks and articles on geometric

algebra start with definitions of symbols and terminologies

followed by identities and relationships among them. This

often makes beginners shy away. My tutorial takes an

alternative approach: the emphasis is on the background

mathematics, including the Hamilton algebra, the Grassmann

algebra, and the Clifford algebra. In the end, I show how these

are combined as geometric algebra.

In order to illustrate the close connection to computer vision

applications, I also describe imaging geometry of fisheye lens

and omnidirectional cameras using parabolic, hyperbolic, and

elliptic mirrors, which play more and more important roles in

computer vision and robotics applications as their price goes

down.

T5 - Metric Learning for Visual Recognition

Organizers: Jiwen Lu

Ruiping Wang

Weihong Deng



Description: One of the fundamental issues of visual

recognition is how to measure the similarity or compute the

distance between pairs of examples. While the conventional

distance metrics are convenient and well‐defined, they

usually ignore the fact that the semantic meaning of

“similarity” is inherently task‐dependent and data‐

dependent. This simple observation has led to the idea that

the distance metric should change adaptively to be better suit

to the problem. With this strategy even simple classifiers can

be competitive with the state‐of‐the‐art because the distance

measure locally adapts to the structure of the data. During

the past two decades, we have witnessed how metric learning

techniques significantly improved the state‐of‐the‐arts of

many important visual recognition tasks. In this tutorial, we

will overview the trend of metric learning techniques and

discuss how they advance different visual recognition tasks.

First, we briefly introduce the basic concept of metric

learning, and show how they are used to improve the

performance of different visual recognition tasks in previous

work. Second, we introduce some of our newly proposed

metric learning method from two aspects: single‐metric

learning and multi‐metric learning, which differ in assuming

that the learned metric is unified or changes smoothly

throughout different regions of the feature space. Lastly, we

will present how these proposed metric learning methods are

used to improve different computer vision tasks and discuss

some open problems to understand how to develop more

advanced metric learning algorithms for visual recognition in

the future.

Monday, November 3 Program

24

Monday, November 3

Location: University Cultural Centre

0745–0800 Registration Opens

0800–0900 Breakfast + Poster setup

0900–0915 Welcome + Announcements

0915–1015 Keynote: Deep Convolution Networks as Geometric Image Representations

Speaker: Stéphane Mallat, École Normale Supérieure (France) Chair: Michael S. Brown, National University of Singapore

1015–1100 Coffee Break

1100–1230 Oral Session 1 (Recognition) Chair: C. V. Jawahar, IIIT-Hyderabad

[15 minutes each: 12 minute talk + 2-3 minute Q&A]

1. Deep Representations to Model User 'Likes', Sharath

Chandra Guntuku, Nanyang Technological University,

Singapore; Joey Tianyi Zhou, Nanyang Technological

University, Singapore; Sujoy Roy, Institute for Infocomm

Research, Singapore; Lin Weisi, Nanyang Technological

University, Singapore; Ivor Tsang, University of

Technology, Australia

2. Submodular Reranking with Multiple Feature

Modalities for Image Retrieval, Fan Yang, University of

Maryland; Zhuolin Jiang, Huawei Technologies; Larry S.

Davis, University of MarylandTrinocular Geometry

Revisited, Jean Ponce, Martial Hebert

3. Accurate Scene Text Recognition based on Recurrent

Neural Network, Bolan Su, Institute for Infocomm

Research; Shijian Lu, Institute for Infocomm Research

4. Massive City-scale Surface Condition Analysis using

Ground and Aerial Imagery, Ken Sakurada, Tohoku

University; Takayuki Okatani, Tohoku Univervisty; Kris

Kitani, Carnegie Mellon University

5. Can Visual Recognition Benefit from Auxiliary

Information in Training? Qilin Zhang, Stevens Institute

of Technology; Gang Hua, Stevens Institute of

Technology; Wei Liu, IBM Thomas J. Watson Research

Center; Zicheng Liu, Microsoft Research; Zhengyou

Zhang, Microsoft Research

6. Low Rank Representation on Grassmann Manifolds,

Boyue WANG, Beijing University of Technology; Yongli

Hu, Beijing University of Technology; Junbin

GAO,Charles Sturt University ; Yanfeng SUN, Beijing

University of Technoloy; Baocai YIN, Beijing University of

Technoloy

1230–1330 Lunch

1330 –1515 Poster Session 1 (Recognition, 3D Vision, Performance)

1. Learning Detectors Quickly with Stationary Statistics,

Jack Valmadre, Queensland University of Technolgy;

Sridha Sridharan, Queensland University of

Technology; Simon Lucey, Carnegie Mellon University

2. Age Estimation Based on Complexity-Aware Features,

Haoyu Ren, Simon Fraser University; Ze-Nian Li, Simon

Fraser University

3. Efficient On-the-fly Category Retrieval using ConvNets

and GPUs, Ken Chatfield, University of Oxford; Karen

Simonyan, University of Oxford; Andrew Zisserman,

University of Oxford

4. A Latent Clothing Attribute Approach for Human Pose

Estimation, Weipeng Zhang, Shanghai Jiao Tong

University; Jie Shen, Shanghai Jiao Tong University;

Guangcan Liu, Nanjing University of Information Science

and Technology; Yong Yu, Shanghai Jiao Tong University

5. NOKMeans: Non-Orthogonal K-means Hashing, Xiping

Fu, University of Otago; Brendan McCane, University of

Otago; Steven Mills, University of Otago; Michael Albert,

University of Otago


25

6. Visual Vocabulary with a Semantic Twist, Relja

Arandjelovic, University of Oxford; Andrew Zisserman,


7. Context Based Re-ranking for Object Retrieval, Yanzhi

Chen, United Technologies Research Center, University of

Adelaide; Anthony Dick, University of Adelaide; Xi Li,

University of Adelaide, Zhejiang University; Rhys Hill,

University of Adelaide

8. Adaptive Structural Model for Video Based Pedestrian

Detection, Junjie Yan, Chinese Academy of Sciences; Bin

Yang, Chinese Academy of Sciences; Zhen Lei, Chinese

Academy of Sciences; Stan Li, Chinese Academy of

Sciences

9. Fusion of Auxiliary Imaging Information for Robust,

Scalable and Fast 3D Reconstruction, Hainan Cui,

Chinese Academy of Sciences; Shuhan Shen, Chinese

Academy of Sciences; Wei Gao, Chinese Academy of

Sciences; Zhanyi Hu, Chinese Academy of Sciences

10. What Visual Attributes Characterize an Object Class?

Jianlong Fu, Chinese Academy of Sciences; Jinqiao

Wang, Chinese Academy of Sciences ; xin-Jing Wang,

Microsoft Research; yong Rui, Microsoft Research;

Hanqing Lu, Chinese Academy of Sciences

11. Accurate Object Detection with Location Relaxation

and Regionlets Re-localization, Chengjiang Long,

Stevens Institute of Technology; Xiaoyu Wang, NEC

Laboratories America, Canada; Gang Hua, Stevens

Institute of Technology; Ming Yang, Facebook; Yuanqing

Lin, NEC Laboratories America

12. Unsupervised Feature Learning for RGB-D Image

Classification, I-Hong Jhuo, Institute of Information

Science; Shenghua Gao, ShanghaiTech University;

Liansheng Zhuang, USTC; D. Lee, Institute of

Information Science, National Chung Hsing University; Yi

Ma, ShanghaiTech University, University of Illinois

13. Non-Maximum Suppression for Object Detection by

Passing Messages between Windows, Rasmus Rothe,

ETH Zurich; Matthieu Guillaumin, ETH Zurich; Luc Van

Gool, ETH Zurich, ESAT-PSI

14. Stable Radial Distortion Calibration by Polynomial

Matrix Inequalities Programming, Jan Heller, Czech

Technical University; Didier Henrion, CNRS-LAAS,

Universite de Toulouse, France, Czech Technical

University; Tomas Pajdla, Czech Technical University

15. Pedestrian Verification for Multi-Camera Detection,

Scott Spurlock, University of North Carolina; Richard

Souvenir, University of North Carolina

16. Color Photometric Stereo Using a Rainbow Light for

Non-Lambertian Multicolored Surfaces, Sejuti Rahman,

Carnegie Mellon University; Antony Lam, Saitama

University; Imari Sato, National Institute of Informatics;

Antonio Robles-Kelly, National ICT

17. Predicting the location of “interactees” in novel human-

object interactions, Chao Yeh Chen, University of Texas;

Kristen Grauman, University of Texas

18. Robust Stereo Matching Using Probabilistic Laplacian

Surface Propagation, Seungryong Kim, Yonsei

University; Bumsub Ham, Inria; Seungchul Ryu, Yonsei

University; Seon Joo Kim, Yonsei University; Kwanghoon

Sohn, Yonsei University

19. Imposing Differential Constraints on Radial Distortion

Correction, Xianghua Ying, Peking University; Xiang Mei,

Peking University; Sen Yang, Peking University; Ganwen

Wang, Peking University; Jiangpeng Rong, Peking

University; Hongbin Zha, Peking University

20. Automatic Shoeprint Retrieval Algorithm for Real

Crime Scenes, Xinnian Wang, Dalian Maritime

University; Huihui Sun, Dalian Maritime University; Qing

Yu, Dalian Maritime University; Chi Zhang, Dalian

Maritime University

21. Lane Detection in Unstructured Environments for

Autonomous Navigation Systems, Manh Cuong Le,

University of Wollongong; Son Lam Phung, University of

Wollongong; Abdesselam Bouzerdoum, University of

Wollongong

22. Multiple Stage Residual Model for Accurate Image

Classification, Song Bai, Huazhong University of Science

and Technology; Xinggang Wang, Huazhong University

of Science and Technology; Cong Yao, Huazhong

University of Science and Technology; Xiang Bai,

Huazhong University of Science and Technology


26

23. Hybrid-Indexing Multi-type Features for Large-scale

Image Search, Qingjun Luo, Peking University; Shiliang

Zhang, University of Texas; Tiejun Huang, Peking

University; Wen Gao, Peking University; Qi Tian,

University of Texas

24. Look Closely: Learning Exemplar Patches for

Recognizing Textiles from Product Images, Quoc Phan,

City Univesity of Hong Kong; Hongbo Fu, City University

of Hong Kong; Antoni Chan, City University of Hong Kong

25. Action Recognition from a Single Web Image Based on

an Ensemble of Pose Experts, Peihao Zhang, Nanjing

University of Aeronautics and Astronautics; Xiaoyang

Tan, Nanjing University of Aeronautics and Astronautics;

Xin Jin, Nanjing University of Aeronautics and

Astronautics

26. Scene Text Recognition and Retrieval for Large

Lexicons, Udit Roy, IIIT Hyderabad; Anand Mishra, IIIT

Hyderabad; Karteek Alahari, Inria; C.V. Jawahar, IIIT

Hyderabad

27. Planar Structures from Line Correspondences in a

Manhattan World, Chelhwon Kim, University of

California Santa Cruz; Roberto Manduchi, University of

California Santa Cruz

28. LBP with Six Intersection Points: Reducing Redundant

Information in LBP-TOP for Micro-expression

Recognition, Yandan Wang, Multimedia University; John

See, Multimedia University; Raphael C.-W. Phan,

Multimedia University; Yee-Hui Oh, Multimedia

University

29. Deep Convolutional Neural Networks for Efficient Pose

Estimation in Gesture Videos, Tomas Pfister, University

of Oxford; Karen Simonyan, University of Oxford; James

Charles, University of Leeds; Andrew Zisserman,


30. Robust Edge Aware Descriptor for Image Matching,

Rouzbeh Maani, University of Alberta; Sanjay Kalra,

University of Alberta; Yee-Hong Yang, University of

Alberta

31. Robust Binary Feature Using Intensity Order, Yukyung

Choi, KAIST; Chaehoon Park, KAIST; Joon-Young Lee,

KAIST; In So Kweon, KAIST

32. Minimal solution for computing pairs of lines in non-

central cameras, Jesus Bermudez-Cameo, University of

Zaragoza; Joao Barreto, University of Coimbra; Gonzalo

Lopez-Nicolas, University of Zaragoza; Jose J. Guerrero,

University of Zaragoza

33. Asymmetric Feature Representation for Object

Recognition in Client Server System, Yuji Yamauchi,

Chubu University ; Mitsuru Ambai, Denso IT Laboratory;

Ikuro Sato, Denso IT Laboratory; Yuichi Yoshida, Denso IT

Laboratory; Hironobu Fujiyoshi, Chubu University;

Takayoshi Yamashita, Chubu University

34. Leveraging High Level Visual Information for Matching

Images and Captions, Fei Yan, University of Surrey;

Krystian Mikolajczyk, University of Surrey

35. Efficient Feature Coding based on Auto-Encoder

Network for Image Classification, Guo-Sen Xie, Chinese

Academy of Sciences; Xu-Yao Zhang, Chinese Academy

of Sciences; Cheng-Lin Liu, Chinese Academy of Sciences

36. Learning a Representative and Discriminative Part

Model with Deep Convolutional Features for Scene

Recognition, Bingyuan Liu, Chinese Academy of

Sciences; Jing Liu, Chinese Academy of Sciences; Jinqiao

Wang, Chinese Academy of Sciences; Hanqing Lu,

Chinese Academy of Sciences

37. Image Representation Learning by Deep Appearance

and Spatial Coding, Bingyuan Liu, Chinese Academy of

Sciences; Jing Liu, Chinese Academy of Sciences; Zechao

Li, Nanjing University of Science and Technology;

Hanqing Lu, Chinese Academy of Sciences

38. On the Exploration of Joint Attribute Learning for

Person Re-identification, Joseph Roth, Michigan State

University; Xiaoming Liu, Michigan State University

39. Complimentary geometric and optical information for

match-propagation-based 3D reconstruction, Patricio

A. Galindo, Inria; Rhaleb Zayer, Inria

40. Exploring Image Specific Structured Loss for Image

Annotation with Incomplete Labelling, Xing Xu, Kyushu

University; Atsushi Shimada, Kyushu University; Rin-

ichiro Taniguchi, Kyushu University

41. Multi-View Geometry Compression, Siyu Zhu, HKUST;

Tian Fang, HKUST; Runze Zhang, HKUST; Long Quan,

HKUST


27

42. Camera Calibration Based on the Common Self-polar

Triangle of Sphere Images, Haifei Huang, Hong kong

Baptist University, BNU-HKBU; Hui Zhang, BNU-HKBU,

PKU-HKUST Shenzhen Hong Kong Institution; Yiu-ming

Cheung, Hong Kong Baptist Univerity, BNU-HKBU

43. Multi-scale Tetrahedral Fusion of a Similarity

Reconstruction and Noisy Positional Measurements,

Runze Zhang, HKUST; Tian Fang, HKUST; Siyu Zhu,

HKUST; Long Quan, HKUST

44. DEPT: Depth Estimation by Parameter Transfer for

Single Still Images, Xiu Li, Tsinghua University; Hongwei

Qin, Tsinghua University; Yangang Wang, Microsoft

Research Asia; Yongbing Zhang, Tsinghua University;

Qionghai Dai, Tsinghua University

45. Object Ranking on Deformable Part Models with

Bagged LambdaMART, Chaobo Sun, Beijing University

of Posts and Telecommunications; Xiaojie Wang, Beijing

University of Posts and Telecommunications; Peng Lu,

Beijing University of Posts and Telecommunications

46. Representation learning with Smooth Autoencoder,

Kongming Liang, Chinese Academy of Sciences; Hong

Chang, Chinese Academy of Sciences; zhen Cui, Chinese

Academy of Sciences; Shiguang Shan, Chinese Academy

of Sciences; Xilin Chen,Chinese Academy of Sciences

47. Single Image Smoke Detection, Hongda Tian, University

of Wollongong; Wanqing Li, University of Wollongong;

Philip Ogunbona, University of Wollongong; Lei Wang,

University of Wollongong

48. Adaptive Sparse Coding for Painting Style Analysis, Zhi

Gao, National University of Singapore; Mo Shan,

National University of Singapore; Loong-Fah Cheong,

National University of Singapore; Qingquan Li, Wuhan

University, Shenzhen University

49. Efficient Image Detail Mining, Andrej Mikulik, Czech

Technical University in Prague; Filip Radenovic, Czech

Technical University in Prague; Ondrej Chum, Czech

Technical University in Prague; Jiri Matas, Czech

Technical University in Prague

50. Accuracy and specificity trade-off in k-nearest

neighbors classification, Luis Herranz, Chinese Academy

of Sciences; Shuqiang Jiang, Chinese Academy of

Sciences

51. Multi-view Point Cloud Registration using Affine Shape

Distributions, Jia Du, Institute for Infocomm Research;

Wei Xiong , Institute for Infocomm Research; Jierong

Cheng, Institute for Infocomm Research; Yue Wang,

Institute for Infocomm Research ; Wenyu Chen, Institute

for Infocomm Research; Shue Ching Chia, Institute for

Infocomm Research; Ying Gu, Institute for Infocomm

Research

52. Part Detector Discovery in Deep Convolutional Neural

Networks, Marcel Simon, Friedrich Schiller University of

Jena; Erik Rodner, Friedrich Schiller University of Jena;

Joachim Denzler, Friedrich Schiller University of Jena

53. Performance Evaluation of 3D Local Feature

Descriptors, Yulan Guo, National University of Defense

Technology,The University of Western Australia;

Mohammed Bennamoun, The University of Western

Australia; Ferdous Sohel, The University of Western

Australia; Min Lu, National University of Defense

Technology; Jianwei Wan, National University of Defense

Technology; Jun Zhang, National University of Defense

Technology

54. Scene Text Detection Based on Robust Stroke Width

Transform and Deep Belief Network, Hailiang Xu,

Nanjing University; Like Xue, Nanjing University; Feng

Su, Nanjing University

55. Cross-Modal Face Matching: Beyond Viewed Sketches,

Shuxin Ouyang, Beijing University of Posts and

Telecommunications; Timothy Hospedales, Queen Mary

University of London; Yi-zhe Song, Queen Mary

University of London; Xueming Li, Beijing University of

Posts and Telecommunications

56. 3D Aware Correction and Completion of Depth Maps in

Piecewise Planar Scenes, Ali Thabet, King Abdullah

University of Science and Technology; Bernard Ghanem,

King Abdullah University of Science and Technology;

Daniel Asmar, American University of Beirut; Bernard

Ghanem, King Abdullah University of Science and

Technology

57. Regularity Guaranteed Human Pose Correction, Wei

Shen, Shanghai University; Rui Lei, Shanghai University;

Dan Zeng, Shanghai University; Zhijiang Zhang,

Shanghai University


28

58. Accelerated kmeans Clustering using Binary Random

Projection, Yukyung Choi, Korea Advanced Institute of

Science and Technology; Cheahoon Park, Korea

Advanced Institute of Science and Technology; In So

Kweon, Korea Advanced Institute of Science and

Technology

59. Divide and Conquer: Efficient large-scale structure from

motion using graph partitioning, Brojeshwar Bhowmick,

Indian Institute of Technology Delhi; Suvam Patra, Indian

Institute of Technology Delhi; Avishek Chatterjee, Indian

Institute of Science Bangalore; Venu Madhav Govindu,

Indian Institute of Science Bangalore; Subhashis

Banerjee, Indian Institute of Technology Delhi

60. A homography formulation to the 3pt plus a common

direction relative pose problem, Olivier Saurer, ETH

Zürich; Pascal Vasseur, Université de Rouen; Cedric

Demonceaux, Université de Bourgogne; Friedrich

Fraundorfer, Technische Universitat Munchen

61. MoNet: A Deep Learning Framework Using Motion

Features for Human Pose Estimation, Arjun Jain, New

York University; Jonathan Tompson, New York

University; Christoph Bregler, New York University

62. Accelerating Cost Volume Filtering Using Salient

Subvolumes and Robust Occlusion Handling, Mohamed

Helala, University of Ontario Institute of Technology

Oshawa; Faisal Qureshi, University of Ontario Institute of

Technology Oshawa

63. 3D Human Pose Estimation from Monocular Images

with Deep Convolutional Neural Network, Sijin LI, City

University of Hong Kong; Antoni Chan, City University

Hong Kong

64. Plant Leaf Identification via A Growing Convolution

Neural Network with Progressive Sample Learning,

Zhong-Qiu Zhao, Hefei University of Technology, Hong

Kong Baptist University; Bao-Jian Xie, Hefei University of

Technology; Yiu-ming Cheung, Hong Kong Baptist

University,Beijing Normal University-Hong Kong Baptist

University; Xindong Wu, Hefei University of

Technology, University of Vermont

65. Understanding Convolutional Neural Networks in

Terms of Category-level Attributes, Makoto Ozeki,

Tohoku University; Takayuki Okatani, Tohoku Univervisty

66. Robust Scene Classification with Cross-level LLC

Coding on CNN Features, Zequn Jie, National University

of Singapore; Shuicheng Yan, National University of

Singapore

67. A Graphical Model for Rapid Obstacle Image-map

Estimation from Unmanned Surface Vehicles, Matej

Kristan, University of Ljubljana, Slovenia; Janez Pers,

University of Ljubljana, Slovenia; Vildana Sulic,

University of Ljubljana, Slovenia; Stanislav Kovacic,

University of Ljubljana, Slovenia

68. On the Performance of Pose-based RGB-D Visual

Navigation Systems, Dominik Belter, Poznan University

of Technology; Michal Nowicki, Poznan University of

Technology; Piotr Skrzypczynski, Poznan University of

Technology

69. Elastic Shape Analysis of Boundaries of Planar Objects

with Multiple Components and Arbitrary Topologies,

Sebastian Kurtek, Ohio State University; Hamid Laga,

University of South Australia, Australian Centre for Plant

Functional Genomics; Qian Xie, Florida State University

1230–1315 Demo Session 1 (Concurrent with Poster Session 1)

1. Robust Real Time 6-DOF Tracking via Object

Coordinate Regression

Alexander Krull, Frank Michel, Eric Brachmann, Stefan

Gumhold, Stephan Ihrke, and Carsten Rother (Technical

University Dresden)

2. "i-Bolt": Image-based Individual Identification of Metal

Parts without Tag

Rui Ishiyama and Toru Takahashi (NEC Corporation)

3. Efficient Image Detail Mining

Andrej Mikulik, Filip Radenovic, Ondrej Chum, and Jiri

Matas (Czech Technical University in Prague)



29

1600–1715 Oral Session 2 (3D Vision) Chair: Simon Lucey, CMU

[15 minutes each: 12 minutes talk + 2-3 minutes Q&A]

1. A Minimal Solution to Relative Pose with Unknown

Focal Length and Radial Distortion, Fangyuan Jiang,

Lund University; Yubin Kuang, Lund University; Kalle

Åström, Lund University

2. Simultaneous Entire Shape Registration of Multiple

Depth Images Using Depth Difference and Shape

Silhouette, Takuya Ushinohama,Kagoshima University;

Yosuke Sawai, Kagoshima University; Satoshi Ono,

Kagoshima University; Hiroshi Kawasaki, Kagoshima

University

3. Joint Camera Pose Estimation and 3D Human Pose

Estimation in a Multi-Camera Setup, Jens Puwein,

ETHZ; Luca Ballan, ETHZ; Remo Ziegler, Vizrt; Marc

Pollefeys, ETHZ

4. Singly-Bordered Block-Diagonal Form for Minimal

Problem Solvers, Zuzana Kukelova, Czech Technical

University, Microsoft Research Cambridge ; Martin

Bujnak, Capturing Reality s.r.o.; Jan Heller, Czech

Technical University; Tomas Pajdla, Czech Technical

University

5. Stereo Fusion using a Refractive Medium on a Binocular

Base, Seung-Hwan Baek, KAIST; Min H. Kim, KAIST

1715–1745 Shuttle Buses to MRT Station

Tuesday, November 4 Program

30

Tuesday, November 4


0745 Registration Opens

0800–0900 Breakfast + Poster Setup

0900 Announcements

0915–1015 Keynote: How Changing Mobile and Media Technologies is Changing The Way We Create Innovations

Speaker: Dr. Minoru (Mick) Etoh, NTT Docomo (Japan) Chair: Hideo Saito, Keio University


1100–1220 Oral Session 3 (Low-Level Vision and Features) Chair: Ondrej Chum, Czech Technical University


1. Saliency Detection via Nonlocal L0 Minimization, Yiyang Wang, Dalian University of Technology, China; Risheng Liu, Dalian University of Technology, China; Xiaoliang Song, Dalian University of Technology, China; Zhixun Su, Dalian University of Technology, China

2. N4-Fields: Neural Network Nearest Neighbor Fields for Image Transforms, Yaroslav Ganin, Skoltech; Victor Lempitsky, Skoltech

3. Super-Resolution Using Sub-Band Self-Similarity, Abhishek Singh, University of Illinois at Urbana-Champaign; Narendra Ahuja, University of Illinois at Urbana-Champaign

4. Raindrop Detection and Removal from Long Range Trajectories, Shaodi You, University of Tokyo, Japan; Robby Tan, SIM University, Singapore; Rei Kawakami, University

of Tokyo, Japan; Yasuhiro Makaigawa, Nara Institute of Science and Technology, Japan; Katsushi Ikeuchi, University of Tokyo, Japan

5. Interest Points via Maximal Self-Dissimilarities, Federico Tombari, University of Bologna, Italy; Luigi Di Stefano, University of Bologna, Italy

6. Improving Local Features by Dithering-based Image Sampling, Christos Varytimidis, National Technical University of Athens, Greece; Konstantinos Rapantzikos, National Technical University of Athens, Greece; Yannis Avrithis, National Technical University of Athens, Greece; Stefanos Kollias, National Technical University of Athens, Greece

1230–1330 Lunch

1330–1515 Poster Session 2 (Face and Gesture, Low-Level Vision, Statistical Methods, Medical)


1. Sparse Kernel Learning for Image Set Classification, Muhammad Uzair, University of Western Australia; Arif Mahmood, University of Western Australia; Ajmal Mian, University of Western Australia

2. Automatic Feature Learning to Grade Nuclear Cataracts Based on Deep Learning, Xinting Gao, Institute for Infocomm Research, Singapore; Stephen Lin, Microsoft Research, China; Tien Yin Wong, Singapore Eye Research Institute

3. Texture Classification using Dense Micro-block Difference (DMD), Rakesh Mehta, Tampere University of Technology, Finland; Karen Egiazarian, Tampere University of Technology, Finland

4. Nuclear-L1 Norm Joint Regression for Face Reconstruction and Recognition, Lei Luo, Nanjing University of Science and Technology, China; Jian Yang, Nanjing University of Science and Technology, China; Jianjun Qian, Nanjing University of Science and Technology, China; Ying Tai, Nanjing University of Science and Technology, China

5. Segmentation of X-ray Images by 3D-2D Registration based on Multibody Physics, Jerome Schmid, University of Applied Sciences of Western Switzerland; Christophe


31

Chenes, University of Applied Sciences of Western Switzerland

6. View-Adaptive Metric Learning for Multi-view Person Re-identification, Canxiang Yan, Institute of Computing Technology, CAS, China, University of Chinese Academy of Sciences; Shiguang Shan, Institute of Computing Technology, CAS, China; Dan Wang, University of Chinese Academy of Sciences, Institute of Computing Technology, CAS, China; Hao Li, Institute of Computing Technology, CAS, China, University of Chinese Academy of Sciences; Xilin Chen, Institute of Computing Technology, CAS, China

7. Accurate Vessel Segmentation with Progressive Contrast Enhancement and Canny Refinement, Xin Yang, HUST,China, UCSB, USA; Tim Cheng, UCSB, USA; Aichi Chien, UCLA, USA

8. Eigen-PEP for Video Face Recognition, Haoxiang Li, Stevens Institute of Technology, USA; Gang Hua, Stevens Institute of Technology, USA; Xiaohui Shen, Adobe Systems Inc.; Zhe Lin, Adobe Systems Inc.; Jonathan Brandt, Adobe Systems Inc.

9. Local Generic Representation for Face Recognition with Single Sample per Person, Pengfei Zhu, Hong Kong Polytechnic University; Meng Yang, Shenzhen University, China; Lei Zhang, Hong Kong Polytechnic University; Il-Yong Lee, LG Electronics, Yonsei University, Korea

10. Unsupervised Image Co-segmentation Based on Cooperative Game, Bo-Chen Lin, National Tsing Hua University, Taiwan; Ding-Jie Chen, National Tsing Hua University; Long-Wen Chang, National Tsing Hua University, Taiwan

11. A High Performance CRF Model for Clothes Parsing, Edgar Simo-Serra, IRI (CSIC-UPC); Sanja Fidler, University of Toronto, Canada; Francesc Moreno-Noguer, IRI (CSIC-UPC); Raquel Urtasun, University of Toronto, Canada

12. Real-time Head Orientation from a Monocular Camera using Deep Neural Network, Byungtae Ahn, KAIST, Korea; Jaesik Park, KAIST, Korea; In So Kweon, KAIST, Korea

13. Jointly Learning Dictionaries and Subspace Structure for Video-based Face Recognition, Guangxiao Zhang, University of Maryland, USA; Ran He, Chinese Academy of Sciences; Larry Davis, University of Maryland, USA

14. Visual Salience Learning via Low Rank Matrix Recovery, Junxia Li, Nanjing University of Science and Technology, China; Jundi Ding, Nanjing University of Science and Technology, China; Jian Yang, Nanjing University of Science and Technology, China

15. A New Framework for Multiclass Classification Using Multiview Assisted Adaptive Boosting, Avisek Lahiri, Indian Institute of Technology; Prabir Biswas, Indian Institute of Technology

16. Age Estimation by Multi-scale Convolutional Network, Dong Yi, Chinese Academy of Sciences; Zhen Lei, Chinese Academy of Sciences; Stan Li, Chinese Academy of Sciences

17. Photorealistic Face de-Identification by Agregating Donors' Face Components, Saleh Mosaddegh, University of Caen, France; Loic Simon, University of Caen, France; Frederic Jurie, University of Caen, France

18. Which Image Pairs Will Cosegment Well? Predicting Partners for Cosegmentation, Suyog Dutt Jain, University of Texas at Austin; Kristen Grauman, University of Texas at Austin

19. Image Restoration via Multi-Prior Collaboration, Feng Jiang, Harbin Institute of Technology, Princeton University; Shengping Zhang, Harbin Institute of Technology; Debin Zhao, Harbin Institute of Technology; S.Y. Kung, Princeton University

20. Modeling the Temporality of Saliency, Ye Luo, NUS; Loong-Fah Cheong, NUS; John-John Cabibihan, Qatar University

21. Salient Object Detection using Window Mask Transferring with Multi-layer Background Contrast, Quan Zhou, Nanjing University of Posts and Telecommunications; Shu Cai, Nanjing University of Posts and Telecommunications; Shaojun Zhu, University of Pennsylvania; Baoyu Zheng, Nanjing University of Posts and Telecommunications

22. A Patch Aware Multiple Dictionary Framework for Demosaicing, Meiqing Zhang, Tsinghua University; Linmi Tao, Tsinghua University

23. Large Margin Multi-Metric Learning for Face and Kinship Verification in the Wild, Junlin Hu, NTU; Jiwen Lu, Advanced Digital Sciences Center; Junsong Yuan, NTU; Yap-Peng Tan, NTU

24. A Three-color Coupled Level-Set Algorithm for Simultaneous Multiple Cell Segmentation and Tracking, Jierong Cheng, Institute for Infocomm Research; Wei Xiong, Institute for Infocomm Research; Ying Gu, Institute for Infocomm Research; Shue-Ching Chia, Institute for Infocomm Research; Yue Wang, Institute for Infocomm Research; Joo-Hwee Lim, Institute for Infocomm Research

25. OR-PCA with MRF for Robust Foreground Detection in Highly Dynamic Backgrounds, Sajid Javed, Kyungpook National University;Seon Ho Oh, Kyungpook National


32

University; Andrews Sobral, University of La Rochelle; Thierry Bouwmans, University of La Rochelle; Soon Ki Jung, Kyungpook National University

26. Segmentation of Cells from Spinning Disk Confocal Images Using a Multi-stage Approach, Saad Ullah Akram, University of Oulu; Juho Kannala, University of Oulu; Mika Kaakinen, University of Oulu; Lauri Eklund, University of Oulu; Janne Heikkilä, University of Oulu

27. Head Motion Signatures from Egocentric Videos, Yair Poleg, Hebrew University of Jerusalem; Chetan Arora, IIIT Delhi; Shmuel Peleg, Hebrew University of Jerusalem

28. Improving Saliency Models by Predicting Human Fixation Patches, Rachit Dubey, King Abdullah University of Science and Technology; Akshat Dave, University of California San Diego; Bernard Ghanem, King Abdullah University of Science and Technology

29. Fast Super-Resolution via Dense Local Training and Inverse Regressor Search, Eduardo Pérez-Pellitero, Technicolor R&I Hannover, Leibniz Universität Hannover; Jordi Salvador, Technicolor R&I Hannover; Iban Torres-Xirau, Technicolor R&I Hannover; Javier Ruiz-Hidalgo, Universitat Politècnica de Catalunya; Bodo Rosenhahn, Leibniz Universität Hannover

30. PSPGC: Part-Based Seeds for Parametric Graph-Cuts, Bharat Singh, University of Maryland; Xintong Han, University of Maryland; Zhe Wu, University of Maryland; Larry S. Davis, University of Maryland

31. Multi-cue mid-level grouping, Tom Lee, University of Toronto; Sanja Fidler, University of Toronto; Sven Dickinson, University of Toronto

32. Simple-to-Complex Discriminative Clustering for Hierarchical Image Segmentation, Haw-Shiuan Chang, Academia Sinica; Yu-Chiang Frank Wang, Academia Sinica

33. Learning One-Shot Exemplar SVM from the Web for Face Verification, Fengyi Song, Nanjing University of Aeronautics and Astronautics; Xiaoyang Tan, Nanjing University of Aeronautics and Astronautics

34. Unsupervised Segmentation of RGB-D Images, Zhuo Deng, Temple University; Longin Jan Latecki, Temple University

35. Class-driven Color Transformation for Semantic Labeling, Arash Shahriari, Australian National University; Jose M. Alvarez, Australian National University, NICTA; Antonio Robles-Kelly, Australian National University, NICTA

36. Discovering Harmony: A Hierarchical Colour Harmony Model for Aesthetic Assessment, Peng Lu, Beijing

University of Posts and Telecommunications; Zhijie Kuang, Beijing University of Posts and Telecommunications; Xujun Peng, Raytheon BBN Technologies; Ruifan Li, Beijing University of Posts and Telecommunications

37. Deconstructing Binary Classifiers in Computer Vision, Mohsen Ali, Information Technology University, University of Florida; Jeffrey Ho, Information Technology University, University of Florida

38. Effective Drusen Segmentation from Fundus Images for Age-related Macular Degeneration Screening, Huiying Liu, A-STAR; Yanwu Xu, A-STAR; Damon W.K. Wong, A-STAR; Jiang Liu, A-STAR

39. Recognizing People by Their Personal Aesthetics: A Statistical Multi-level Approach, Cristina Segalin, University of Verona; Alessandro Perina, Istituto Italiano di Tecnologia; Marco Cristani, University of Verona

40. FASA: Fast, Accurate, and Size-Aware Salient Object Detection, Gokhan Yildirim, EPFL; Sabine Süsstrunk, EPFL

41. Gesture Modeling by Hanklet-based Hidden Markov Model, Liliana Lo Presti, University of Palermo; Marco La Cascia, University of Palermo; Stan Sclaroff, Boston University; Octavia Camps, Northeastern University

42. A Novel Face Spoofing Detection Method based on Gaze Estimation, Lijun Cai, Chinese Academy of Sciences; Chunshui Xiong, Chinese Academy of Sciences;Lei Huang, Chinese Academy of Sciences

43. Hybrid Euclidean-and-Riemannian Metric Learning for Image Set Classification, Zhiwu Huang, Chinese Academy of Sciences; Ruiping Wang, Chinese Academy of Sciences; Shiguang Shan,Chinese Academy of Sciences; Xilin Chen, Chinese Academy of Sciences

44. Size and Location Matter: a New Baseline for Salient Object Detection, Long Zhao, Tongji University; Shuang Liang, Tongji University; Yichen Wei, Microsoft Research Asia; Jinyuan Jia, Tongji University

45. Learning Hierarchical Feature Representation in Depth Image, Yazhou Liu, Nanjing University of Science and Technology; Panasonic R&D Center Singapore; Quansen Sun, Nanjing University of Science and Technology; Mel Siegel, Carnegie Mellon University

46. Automatic Wrinkle Detection using Hybrid Hessian Filter, Choon Ching Ng, Manchester Metropolitan University; Moi Hoon Yap, Manchester Metropolitan University; Nicholas Costen, Manchester Metropolitan University; Baihua Li, Manchester Metropolitan University


33

47. Transductive Transfer Machine, Nazli Farajidavar, University of Surrey; Teofilo deCampos, University of Surrey; Josef Kittler, University of Surrey

48. Fully Automatic Segmentation of Hip CT Images via Random Forest Regression-based Atlas Selection and Optimal Graph Search-based Surface Detection, Chengwen Chu, University of Bern; Junjie Bai, University of Iowa; Li Liu, University of Bern; Xiaodong Wu, University of Iowa; Guoyan Zheng, University of Bern

49. Optimal Transportation for Example-Guided Color Transfer, Oriel Frigo, Technicolor Research and Innovation; Neus Sabater, Technicolor Research and Innovation; Pierre Hellier, Technicolor Research and Innovation; Vincent Demoulin, Technicolor Research and Innovation

50. Evaluation of Discriminative Models for the Reconstruction of Hand-Torn Documents, Fabian Richter, University of Augsburg; Christian Ries, University of Augsburg; Rainer Lienhart, University of Augsburg

51. Hand segmentation with structured convolutional learning, Natalia Neverova, Universit e de Lyon, Institut national des sciences Appliquées de Lyon; Christian Wolf, Universit e de Lyon, Institut national des sciences Appliquées de Lyon; Graham Taylor, University of Guelph; Florian Nebout, Awabot

52. Topic-aware Deep Auto-encoders (TDA) for Face Alignment, Jie Zhang, Chinese Academy of Sciences, University of Chinese Academy of Sciences; Meina Kan, Chinese Academy of Sciences; Shiguang Shan, Chinese Academy of Sciences; Xiaowei Zhao, Imperial College London; Xilin Chen, Chinese Academy of Sciences

53. Accelerating the Distribution Estimation for the Weighted Median/Mode Filters, Lu Sheng, the Chinese University of Hong Kong; King Ngi Ngan, The Chinese University of Hong Kong; Tak-Wai Hui, the Chinese University of Hong Kong

54. Saliency aggregation: Does unity make strength?, Olivier LE MEUR, University of Rennes 1; Zhi LIU, University of Rennes 1, Shanghai University

55. Spontaneous Subtle Expression Recognition: Imbalanced Databases & Solutions, Anh Cat Le Ngo, Multimedia University; Raphael C.-W. Phan, Multimedia University; John See, Multimedia University

56. EPML: Expanded Parts based Metric Learning for Occlusion Robust Face Verification, Gaurav Sharma, Technicolor; Frederic Jurie, University of Caen Basse-Normandie; Patrick Perez, Technicolor

57. Pixel-Level Hand Detection with Shape-aware Structured Forest, Xiaolong Zhu, The University of Hong Kong; Kwan-Yee Kenneth Wong, The University of Hong Kong; Xuhui Jia, The University of Hong Kong

58. Beyond procedural facade parsing: Bidirectional alignment via linear programming, Mateusz Kozinski, Universite Paris-Est; Guillaume Obozinski, Universite Paris-Est; Renaud Marlet,Universite Paris-Est

59. Shape Matching Using Point Context and Contour Segments, Christian Feinen, University of Siegen; Cong Yang, University of Siegen; Oliver Tiebe, University of Siegen; Marcin Grzegorzek, University of Siegen

60. A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution, Radu Timofte, ETH Zurich; Vincent De Smet, KU Leuven; Luc Van Gool, ETH Zurich

61. Multiple Ocular Diseases Classification with Graph Regularized Probabilistic Multi-label Learning, Xiangyu Chen, Institute for Infocomm Research; Yanwu Xu, Institute for Infocomm Research; Lixin Duan, Institute for Infocomm Research; Shuicheng Yan, National University of Singapore; Zhuo Zhang, Institute for Infocomm Research ; Damon Wing Kee Wong, Institute for Infocomm Research; Jiang Liu, Institute for Infocomm Research

62. Deeply Learning Deformable Facial Action Parts Model for Dynamic Expression Analysis, Mengyi Liu, Chinese Academy of Sciences, University of Chinese Academy of Sciences; Shaoxin Li, Chinese Academy of Sciences, University of Chinese Academy of Sciences; Shiguang Shan, Chinese Academy of Sciences; Ruiping Wang, Chinese Academy of Sciences; Xilin Chen, Chinese Academy of Sciences, University of Oulu

63. A Novel Context-Aware Topic Model for Category Discovery in Natural Scenes, Zehuan Yuan, Nanjing University; Tong Lu, Nanjing University

64. Robust Sharpness Metrics using Reorganized DCT Coefficients for Auto-Focus Application, ZHENG ZHANG, National University of Defense Technology; Yu Liu, National University of Defense Technology; Xin Tan, National University of Defense Technology; Maojun Zhang, National University of Defense Technology

65. DisLocation: Scalable Descriptor Distinctiveness for Location Recognition, Relja Arandjelovic, University of Oxford, UK; Andrew Zisserman, University of Oxford, UK

66. Discriminative Collaborative Representation for Classification, Yang Wu, Kyoto University; Wei Li, Osaka University; Masayuki Mukunoki, Kyoto University;


34

Muchihiko Minoh, Kyoto University; Shihong Lao, OMRON Social Solutions

67. Thread-Safe: Towards Recognizing Human Action Across Shot Boundaries, Minh Hoai, University of Oxford, Stony Brook University; Andrew Zisserman, University of Oxford

1330–1515 Demo Session 2 (Runs Concurrent with Poster Session 2)

1. Novel Continuous-Multi-Class Cascade for Real-Time Emotional Recognition, Jinhui Chen, Tetsuya Takiguchi and Yasuo Ariki (Kobe University)

2. Scyllarus: A Matlab toolbox aimed at supporting the research on imaging spectroscopy for scene analysis, Nariman Habili, Ran Wei and Antonio Robles-Kelly (NICTA, Australian National University)

3. Automatic Real Crime Scene Shoeprint Retrieval System, Xinnian Wang, Huihui Sun, Qing Yu and Chi Zhang (Dalian Maritime University)


1600–1700 Oral Session 4 (Segmentation) Chair: Vijay Chandrasekhar, Institute for Infocomm Research

[15 minutes each: 12 minute talk + 2-3 minute Q&A] 1. Consistent Foreground Co-segmentation, Jiaming Guo,

National University of Singapore; Loong-Fah Cheong, National University of Singapore; Robby Tan, SIM University; Steven Zhiying Zhou, National University of Singapore

2. On Multiple Image Group Cosegmentation, Fanman Meng, University of Electronic Science and Technology of China; Jianfei Cai, Nanyang University of Technology; Hongliang Li, University of Electronic Science and Technology of China

3. Reconstructive Sparse Code Transfer for Contour Detection and Semantic Labeling, Michael Maire, TTI Chicago, California Institute of Technology; Stella X. Yu, UC Berkeley-ICSI; Pietro Perona, California Institute of Technology

4. A Message Passing Algorithm for MRF Inference with Unknown Graphs and Its Applications, Zhenhua Wang, The University of Adelaide, Australia; Zhiyi Zhang,

Northwest A&F University, China; Geng Nan, Northwest A&F University, China

1700–1730 Transfer to Banquet

1830–2100 Conference Banquet Hilton Hotel Grand Ballroom, Level 3

Wednesday, November 5 Program

35

Wednesday, November 5


0745–1715 Registration Opens

0730–0900 Breakfast + PosterSetup

0900-0915 Announcements

0915-1015 Keynote: RGB-D Perception in Robotics

Speaker: Prof. Dieter Fox, University of Washington (USA) Chair: Ian Reid, University of Adelaide


1100–1230 Oral Session 5 (Face and Gesture, Tracking) Chair: Bohyung Han, POSTECH


1. Joint Estimation of Pose and Face Landmark,

Donghoon Lee, KAIST; Junyoung Chung, KAIST; Chang

D. Yoo, KAIST

2. Probabilistic Subpixel Temporal Registration for Facial

Expression Analysis, Evangelos Sariyanidi, Queen Mary

University of London; Hatice Gunes, Queen Mary

University of London; Andrea Cavallaro, Queen Mary

University of London

3. Depth Recovery with Face Priors, hongyu Chen, Xidian

University, Nanyang Technological University; Hai Xuan

Pham, Rutgers University; Vladimir Pavlovic, Rutgers

University; Jianfei Cai, Nanyang Technological

University; Guangming Shi, Xidian University

4. Inlier Estimation for Moving Camera Motion

Segmentation, Xuefeng Liang, Kyoto University; Cuicui

Zhang, Kyoto University; Takashi Matsuyama, Kyoto

University

5. Real-time Tracking of Multiple Objects by Linear

Motion and Repulsive Motion, Lejun Shen, Chengdu

sport university, China; Zhisheng You, Sichuan

University, China; Qing Liu, Chengdu sport university,

China

6. 6-DOF Model Based Tracking via Object Coordinate

Regression, Alexander Krull, TU Dresden; Frank Michel,

TU Dresden; Eric Brachmann, TU Dresden; Stefan

Gumhold, TU Dresden; Carsten Rother, TU Dresden

1230-1330 Lunch

1330-1515 Poster Session 3 (Video & Activities, Motion and Tracking, Vision for X)

1. Probabilistic State Space Decomposition for Human

Motion Capture, Prabhu Kaliamoorthi, Nanyang

Technological University, Singapore; Ramakrishna

Kakarala, Nanyang Technological University, Singapore

2. Spectral Graph Skeletons for 3D Action Recognition,

Tommi Kerola, Tokyo Institute of Technology, Japan;

Nakamasa Inoue, Tokyo Institute of Technology, Japan

3. Robust Point Matching using Mixture of Asymmetric

Gaussians for Nonrigid Transformation, Gang Wang,

Tongji University, China; Zhicheng Wang, Tongji

University, China; Weidong Zhao,Tongji University,

China; Qiangqiang Zhou, Tongji University, China

4. Multiple Object Tracking by Efficient Graph

Partitioning, Ratnesh Kumar, INRIA, France; Guillaume

Charpiat, INRIA, France; Monique Thonnat, INRIA,

France

5. Fast Approximate Nearest-Neighbor Field by Cascaded

Spherical Hashing, Iban Torres-Xiran, Technicolor R&I

Hannover; Jordi Salvador, Technicolor R&I Hannover;

Eduardo Pérez-Pellitero, Technicolor R&I Hannover


36

6. Coupling Semi-supervised Learning and Example

Selection for Online Object Tracking, Min Yang, Beijing

Institute of Technology, China; Yuwei Wu, Beijing

Institute of Technology, China; Mingtao Pei, Beijing

Institute of Technology, China; Bo Ma, Beijing Institute of

Technology, China; Yunde Jia, Beijing Institute of

Technology, China

7. Reconstructing Shape and Appearance of Thin Film

Objects with Hyper Spectral Sensor, Yoshie Kobayashi,

University of Tokyo, Japan; Tetsuro Morimoto, Toppan

Printing Co., Japan; Imari Sato, National Institute of

Informatics, Japan; Yasuhiro Mukaigawa, Nara Institute

of Science and Technology, Japan; Katsushi Ikeuchi,

University of Tokyo, Japan

8. A Two-Stage Approach for Bag Detection in Pedestrian

Images, Yuning Du, Tsinghua University, China; Haizhou

Ai, Tsinghua University, China; Shihong Lao, OMRON

Social Solutions Co., Japan

9. Recognizing Daily Activities from First-person Videos

with Multi-task Clustering, Yan Yan, University of

Trento, Italy; Elisa Ricci, Fondazione Bruno Kessler,

University of Perugia, Italy; Gaowen Liu, University of

Trento, Italy; Nicu Sebe, University of Trento, Italy

10. Multi-View Recognition Using Weighted View

Selection, Scott Spurlock, University of North Carolina,

USA; Hui Wu, University of North Carolina, USA; Richard

Souvenir, University of North Carolina, USA

11. Graph Transduction Learning of Object Proposals for

Video Object Segmentation, Tinghuai Wang, Nokia

Technologies, Finland; Huiling Wang, Nokia

Technologies, Finland

12. Forecasting Events using an Augmented Hidden

Conditional Random Field, Xinyu Wei, Queensland

University of Technology, Australia, Disney Research,

Pittsburgh; Patrick Lucey, Disney Research, Pittsburgh;

Stephen Vidas, Queensland University of Technology,

Australia, Nanyang Technological University, Singapore;

Stuart Morgan, Australian Institute of Sport; Sridha

Sridharan, Queensland University of Technology,

Australia

13. Camera Motion and Surrounding Scene Appearance as

Context for Action Recognition, Fabian Caba Heilbron,

King Abdullah University of Science and Technology,

Saudi Arabia, Universidad del Norte, Colombia; Ali

Thabet, King Abdullah University of Science and

Technology, Saudi Arabia; Juan Carlos Niebles,

Universidad del Norte, Colombia; Bernard Ghanem, King

Abdullah University of Science and Technology, Saudi

Arabia

14. Semi-Supervised Ranking for Re-Identification with

Few Labeled Image Pairs, Andy Ma, Rutgers University,

USA; Ping Li, Rutgers University, USA

15. Robust Visual Tracking with Dual Group Structure, Fu

Li, Dalian University of Technology, China; Huchuan Lu,

Dalian University of Techology, China; Dong Wang,

Dalian University of Technology, China

16. 3D Reconstruction of Specular Objects with Occlusion:

A Shape-from-Scattering Approach, Yuki Hirofuji, Kyoto

University, Japan; Masaaki Iiyama, Kyoto University,

Japan; Takuya Funatomi, Kyoto University, Japan;

Michihiko Minoh, Kyoto University, Japan

17. 2D Or Not 2D: Bridging the Gap Between Tracking and

Structure from Motion, Karel Lebeda, University of

Surrey, UK; Simon Hadfield, University of Surrey, UK;

Richard Bowden, University of Surrey, UK

18. Clouds in The Cloud, Dmitry Veikherman, Israel Institute

of Technology, Israel; Amit Aides, Israel Institute of

Technology, Israel; Yoav Schechner, Israel Institute of

Technology, Israel; Aviad Levis, Israel Institute of

Technology, Israel

19. Fast Segmentation of Sparse 3D Point Trajectories

using Group Theoretical Invariants, Vasileios Zografos,

Linkoping University, Sweden; Reiner Lenz, Linkoping

University, Sweden; Erik Ringaby, Linkoping University,

Sweden; Michael Felsberg, Linkoping University, Sweden;

Klas Nordberg, Linkoping University, Sweden

20. Superpixels for Video Content Using a Contour-based

EM Optimization, Matthias Reso, Leibniz University of

Hannover, Germany; Jörn Jachalsky, Technicolor

Research & Innovation, Germany; Bodo Rosenhahn,

Leibniz University of Hannover, Germany; Jörn

Ostermann, Leibniz University of Hannover, Germany


37

21. Transformed Principal Gradient Orientation for Robust

and Precise Batch Face Alignment, Weihong Deng,

Beijing University of Posts and Telecommunications; Jiani

Hu,Beijing University of Posts and Telecommunications;

Liu Liu, Beijing University of Posts and

Telecommunications; Jun Guo, Beijing University of Posts

and Telecommunications

22. Improving Human Action Recognition using Score

Distribution and Ranking, Minh Hoai, University of

Oxford, Stony Brook University; Andrew Zisserman,


23. Context-Aware Activity Forecasting, Anirban

Chakraborty, University of California Riverside; Amit K.

Roy-Chowdhury, University of California

24. DMM-Pyramid Based Deep Architetures for Action

Recognition with Depth Cameras, Rui Yang, Nanjing

University; Ruoyu Yang, Nanjing University

25. Discriminative Orderlet Mining For Real-time

Recognition of Human-Object Interaction, Gang Yu,

NTU; Zicheng Liu, Microsoft Research; Junsong Yuan,

NTU

26. Anomaly Detection via Local Coordinate Factorization

and Spatio-temporal Pyramid, Tan Xiao,

Communication and Information Corporation; Chao

Zhang, Peking University; Hongbin Zha, Peking

University; Fangyun Wei, Peking University

27. Intrinsic Image Decomposition from Pair-wise Shading

Ordering, Yuanliu Liu, Xi'an Jiaotong University; Zejian

Yuan, Xi'an Jiaotong University; Nanning Zheng, Xi'an

Jiaotong

28. Never Get Lost Again: Vision Based Navigation using

StreetView Images, Aparna Taneja, ETHZ; Luca Ballan,

ETHZ; Marc Pollefeys, ETHZ

29. Qualitative and Quantitative Spatio-Temporal

Relations in Daily Living Activity Recognition, Jawad

Tayyub, University of Leeds; Aryana Tavanai, University

of Leeds; Yiannis Gatsoulis, University of Leeds; Anthony

G. Cohn, University of Leeds; David C. Hogg, University

of Leeds

30. Blur-Resilient Tracking Using Group Sparsity, Pengpeng

Liang, Temple University; Yi Wu, Temple University,

Nanjing University of Information Science and

Technology; Xue Mei, Toyota Research Institute; Jingyi

Yu, University of Delware; Erik Blasch, Air Force Research

Lab; Danil Prokhorov, Nanjing University of Information

Science and Technology; Chunyuan Liao, HiScene

Information Technologies; Haitao Lang, Temple

University, Beijing University of Chemical Technology;

Haibin Ling, Temple University

31. Visual Tracking via Supervised Similarity Matching, Ji

Zhang, University of Washington Tacoma; Jie Sheng,

University of Washington Tacoma; Ankur Teredesai,

University of Washington Tacoma

32. Multi-State Discriminative Video Segment Selection for

Complex Event Classification, Prithviraj Banerjee,

University of Southern California; Ram Nevatia,

University of South California

33. Action Recognition in the Presence of One Egocentric

and Multiple Static Cameras, Bilge Soran, University of

Washington; Ali Farhadi, University of Washington;

Linda Shapiro, University of Washington

34. Robust Online Visual Tracking with a Single

Convolutional Neural Network, Hanxi Li, Jiangxi Normal

University, NICTA; Yi Li, NICTA, Australian National

University; Fatih Porikli, NICTA, Australian National

University

35. Bi-Stage Large Point Set Registration Using Gaussian

Mixture Models, Junfen Chen, Universiti Sains Malaysia;

Munir Zaman, University of Nottingham; Iman Yi Liao,

University of Nottingham; Bahari Belaton, Universiti

Sains Malaysia

36. Enhanced Sequence Matching for Action Recognition

from 3D Skeletal Data, Hyun-Joo Jung, POSTECH; Ki

Sang Hong, POSTECH

37. Multi-label Discriminative Weakly-Supervised Human

Activity Recognition and Localization, Ehsan Adeli

Mosabbeb, Iran University of Science and Technology.;

Ricardo Cabral, Carnegie Mellon University; Fernando De

la Torre, Carnegie Mellon University; Mahmood Fathy,

Iran University of Science and Technology


38

38. Action-Gons: Action Recognition with A Discriminative

Dictionary of Structured Elements with Varying

Granularity, Yuwang Wang, Tsinghua University;

Baoyuan Wang, Microsoft Research; Yizhou Yu, HKU;

Zhuowen Tu, UCSD

39. Fast Inference of Contaminated Data for Real Time

Object Tracking, Hao Zhu, 3M Cogent Beijing R&D

Center; Yi Li, NICTA, Australian National University

40. Data mining for Action Recognition, Andrew Gilbert,

University of Surrey; Richard Bowden, University of

Surrey

41. A Rotation-Invariant Regularization Term for Optical

Flow Related Problems, Roberto Palomares, Pompeu

Fabra University; Gloria Haro, Pompeu Fabra University;

Coloma Ballester, Pompeu Fabra University

42. Landmark-based Inductive Model for Robust

Discriminative Tracking, Yuwei Wu, Beijing Institute of

Technology; Mingtao Pei, Beijing Institute of Technology;

Min Yang, Beijing Institute of Technology; Yang He,

Beijing Institute of Technology; Yunde Jia, Beijing

Institute of Technology

43. Extended Co-occurrence HOG with Dense Trajectories

for Fine-grained Activity Recognition, Hirokatsu

Kataoka, The University of Tokyo; Kiyoshi Hashimoto,

Keio University; Kenji Iwata, National Institute of

Advanced Industrial Science and Technology; Yutaka

Satoh, National Institute of Advanced Industrial Science

and Technology; Nassir Navab, Technical University of

Munich; Slobodan Ilic, Technical University of Munich;

Yoshimitsu Aoki, Keio University

44. Motion Based Foreground Detection and Poselet

Motion Features for Action Recognition, Erwin Kraft,

Fraunhofer-Institut für Techno- und

Wirtschaftsmathematik; Thomas Brox, University of

Freiburg

45. Global Motion Estimation from Relative Measurements

in the Presence of Outliers, Guillaume Bourmaud,

University of Bordeaux; Rémi Mégret, University of

Bordeaux; Audrey Giremus, University of Bordeaux;

Yannick Berthoumieu, University of Bordeaux

46. Clustering Ensemble Tracking, Guibo Zhu, Chinese

Academy of Sciences ; Jinqiao Wang, Chinese Academy

of Sciences ; Hanqing Lu, Chinese Academy of Sciences

47. Query Based Adaptive Re-Ranking for Person Re-

Identification, Andy Jinhua Ma, Rutgers University; Ping

Li, Rutgers University

48. Improved Color Patch Similarity Measure Based

Weighted Median Filter, Zhigang Tu, Utrecht University;

Remco Veltkamp, Utrecht University; Coert Van

Gemeren, Utrecht University

49. Efficient Pose-based Action Recognition, Andrew

Gilbert, Abdalrahman Eweiwi, University of Bonn;

Muhammed S. Cheema, University of Bonn; Christian

Bauckhage, University of Bonn, Fraunhofer; Juergen

Gall, University of Bonn

50. Tracking Multiple People Online and in Real Time,

Ergys Ristani, Duke University; Carlo Tomasi, Duke

University

51. Optimizing Storage Intensive Vision Applications to

Device Capacity, Rohit Girdhar, Indian Institutes of

Technology Hyderabad; Jayaguru Panda, Indian

Institutes of Technology Hyderabad; C.V. Jawahar,

Indian Institutes of Technology Hyderabad

52. MTS: A Multiple Temporal Scale Tracker Handling

Occlusion and Abrupt Motion Variation, Muhammad

Haris Khan, University of Nottingham; Michel Valstar,

University of Nottingham; Tony Pridmore, University of

Nottingham

53. Video Annotation by Incremental Learning from

Grouped Heterogeneous Sources, Han Wang, Beijing

Institute of Technology; Hao Song, Beijing Institute of

Technology; Xinxiao Wu, Beijing Institute of Technology;

Yunde Jia, Beijing Institute of Technology

54. A Novel Group Sparsity Optimization based Feature

Selection Model for Complex Interaction Recognition,

Luyu Yang, University of Posts and Telecommunications;

Chenqiang Gao, University of Posts and

Telecommunications ; Deyu Meng, Xi'an Jiaotong

University; Jiang Lu, Carnegie Mellon University

55. Boosting-based Visual Tracking using Structural Local

Sparse Descriptors, angbiao Liu, Beijing Institute of

Technology; Ma Bo,Beijing Institute of Technology ;

Hongwei Hu, Beijing Institute of Technology; Yin

Han,Beijing Institute of Technology


39

56. Coupling Multiple Alignments and Re-ranking for Low-

Latency Online Multi-target Tracking, Yingkun Xu,

Chinese Academy of Sciences; Lei qin, Chinese Academy

of Sciences; qingming Huang, Chinese Academy of

Sciences, University of Chinese Academy of Sciences

57. Determining Interacting Objects in Human-Centric

Activities via Qualitative Spatio-Temporal Reasoning,

Hajar Sadeghi Sokeh, Australian National University;

Stephen Gould, Australian National University; Jochen

Renz, Australian National University

58. Enhanced Laplacian Group Sparse Learning with

Lifespan Outlier Rejection for Visual Tracking, Behzad

Bozorgtabar, University of Canberra; Roland Goecke,

University of Canberra, Australian National University

59. Cross-view Action Recognition via Dual-Codebook and

Hierarchical Transfer Framework, Chengkun Zhang, Sun

Yat-sen University; Huicheng Zheng, Sun Yat-sen

University; Jianhuang Lai, Sun Yat-sen University

1330–1515 Demo Session 3 (Runs Concurrent with Poster Session 3)

1. Stereo Fusion using a Refractive Medium on a Binocular

Base, Seung-Hwan Baek and Min H. Kim (KAIST)

2. VideoSum: A Video Storing, Processing and

Summarization Platform, Vasileios Chasanis, Costas

Voglis Antonios Ioannidis, Aristidis Likas (University of

Ioannia), Aris Lanaridis, Eleni Vathi, Geogios Siolas, and

Andreas Stafylopatis (University of Athens)

3. Audio and Video Surveillance System for Public Safety,

Takeshi Arikuma, Masahiro Tani and Tsunehisa

Kawamata (NEC Labatorites Singapore)

1515–1600 Coffee Break 1600-1715 Oral Session 6 (Stereo, Physics,

Video & Events) Chair: Junosng Yuan, Nanyang Technology University

1. Stereo Ground Truth With Error Bars, Daniel

Kondermann, Universität Heidelberg; Rahul Nair,

Universität Heidelberg; Stephan Meister, Universität

Heidelberg; Wolfgang Mischler, Universität Heidelberg;

Burkhard Güssefeld, Universität Heidelberg; Katrin

Honauer, Universität Heidelberg; Sabine Hofmann,

Leibniz Universität Hannover; Claus Brenner, Leibniz

Universität Hannover; Bernd Jaehne, Universität

Heidelberg

2. Separation of Reflection Components by Sparse Non-

negative Matrix Factorization, Yasuhiro Akashi, Tohoku

University; Takayuki Okatani, Tohoku University

3. Spatiotemporal Derivative Pattern: A Dynamic Texture

Descriptor for Video Matching, Farshid Hajati, Tafresh

University, Iran; Mohammad Tavakolian, Tafresh

University, Iran; Soheila Gheisari, Tafresh University,

Iran, Islamic Azad University, Tehran, Iran; Ajmal Mian,

University of Western Australia

4. Weakly Supervised Action Recognition and

Localization using Web Images, Cuiwei Liu, Beijing

Institute of Technolog, China; Xinxiao Wu, Beijing

Institute of Technology, China; Yunde Jia, Beijing

Institute of Technology, China

5. A Game-Theoretic Probabilistic Approach for Detecting

Conversational Groups, Sebastiano Vascon, Istituto

Italiano di Tecnologia; Eyasu Zemene Mequanint,

University Ca' Foscari of Venice; Marco Cristani, Istituto

Italiano di Tecnologia, University of Verona; Hayley

Hung, Technical University of Delft; Marcello Pelillo,

University Ca' Foscari of Venice; Vittorio Murino, Istituto

Italiano di Tecnologia, University of Verona


42

Banquet Details

The conference banquet will be held on Tuesday, Nov 4, 1830 hrs at the Hilton Hotel – Grand Ballroom (located on the 3rd Floor). There will be chartered buses to take participants from the UCC to the Hilton Hotel. For particpants who wish to go there by themselves, directions are provided below.

Directions to Hilton Singapore

1. The closest MRT station is Orchard (NS22). Exit the station and walk through the underpass towards Wheelock Place (there is no street level crossing).

2. Take the first escalator that you see to the street level. 3. Walk for approximately 3 minutes along Orchard Road to Hilton Singapore.

Additional Notes

Please note that NO return shuttle buses are available after the banquet. Participants have to return to their respective hotels using public transportation.

Gold Sponsors

Silver Sponsors

Bronze Sponsors

Supported By