wacv 2015 pocket program guide
TRANSCRIPT
Sponsors
Silver Donors
Bronze Donors
Sponsors & Corporate Donors
Message from the General and Program Chairs
1
Welcome to Waikoloa Beach, Hawaii, and the 15th edition of WACV (renamed as IEEE Winter Conference on Applications of Computer Vision, since 2014). In addition to the main three-day program of oral and poster presentations, keynote talks, a special session, demos and social functions, WACV 2015 has, for the first time, a number of co-located events, including three workshops, two tutorials and a PhD forum. WACV 2015 is a single track conference in which each accepted paper has the opportunity of both a short oral and a poster presentation.
This year, we received 425 original unpublished submissions to the main conference in a two round submission/review process. Out of these, 156 (35 in Round 1, 121 in Round 2) papers were accepted, resulting in an acceptance rate of 36.7%. Compared to WACV 2014, this year’s WACV has an increase of 46 submissions and a reduction of 3.3% in the acceptance rate.
We used the CMT conference management service provided by Microsoft Research to manage the submission and selection of papers from the beginning to the end. To select papers from these submissions, we invited 32 researchers to act as Area Chairs (ACs). We recruited 395 experienced reviewers from the broader computer vision community.
WACV 2015 adopted a two-round review process that is similar to journal submissions to provide the authors with an additional chance of defending and revising their papers, to make the best use of reviewers’ time, and to achieve an overall quality and consistency among the accepted papers. For Round 1, the decisions were accept, revise and resubmit, or reject. For Round 2, authors were invited to submit either a new, previously un-submitted paper -or- resubmit a paper that was submitted in Round 1 and received a decision of “revise and resubmit”. Papers that received a “reject” decision in Round 1 were not allowed to be re-submitted in Round 2. We hoped that the authors would utilize the reviewers’ comments on papers rejected in Round 1 and Round 2 to enhance their manuscript and submit elsewhere.
We strongly encouraged the authors of resubmitted papers (only “revise and resubmit” category from Round 1 to prepare a ‘rebuttal and list of changes’ in response to the reviewers’ comments in the first round. In the submission process, authors were asked if the paper was a resubmission which was verified by the CMT system. For the resubmitted papers, we assigned the same reviewers and AC’s as from the first round whenever possible. The page limit for the ‘rebuttal and list of changes’ was set at 2. This was in addition to the body of the resubmitted paper. Thus, the total length of the submitted document would not exceed 10 pages, i.e., 8 pages max of the paper plus 2 pages max of ‘rebuttal and list of changes’. This did not apply to new papers submitted in Round 2.
After the submission deadlines, for both Round 1 and Round 2, the Program Chairs (PCs) assigned the papers to the reviewers and ACs. Almost all the papers were reviewed by at least three reviewers. Once the reviews were returned, ACs and PCs made the final decision about the paper selection. The revise and resubmit process allowed by the two stage process served as a better proxy for the rebuttal process. Authors who submitted early, i.e. in Round 1, received this opportunity. The papers by the organizers were handled by other experienced people who made sure that there was absolutely no conflict of interest regarding any submission. Additionally, the ACs were excluded from any decisions associated with papers from their research groups, affiliated institutions or collaborators.
The main conference WACV 2015 includes two invited speakers, Prof. Steven Seitz from the University of Washington and Google and Mr. Mike Geertsen from DARPA. In addition, we have organized a special session on Life Sciences Applications with three invited speakers: Prof. Andre Obenaus (Loma Linda University Medical Center), Dr. Bahram Parvin (Lawrence Berkeley National Laboratory) and Dr. Ankur Kapoor (Siemens).
The proceedings of WACV 2015 are being provided on a USB drive at the conference. All papers in the main conference and associated workshops will be made
Message from the General and Program Chairs
2
available through the IEEE Computer Society Digital Library and through IEEE Xplore.
We wish to thank all members of the Organizing Committee, the Area Chairs, reviewers, authors, and the CMT for the immense amount of hard work and professionalism that have gone into making WACV 2015 a first-rate conference on the applications of Computer Vision. Our thanks also go to the organizers of WACV 2014 and the steering committee for their helpful advice and support. We are also grateful to the sponsors for their generous support.
Finally, we wish all the attendees a highly stimulating, informative, and enjoyable conference.
Bir Bhanu, Gerard Medioni, Rakesh (Teddy) Kumar, Dorin Comaniciu (General Co-Chairs)
Sudeep Sarkar, Subhodev Das, Bahram Parvin, Fatih Porikli (Program Co-Chairs)
WACV 2015 Organizing Committee
General Chairs: Bir Bhanu Gerard Medioni Rakesh (Teddy) Kumar Dorin Comaniciu
Program Chairs: Sudeep Sarkar Subhodev Das Bahram Parvin Fatih Porikli
Steering Committee: David Michael Anthony Hoogs Bryan Morse Terrance Boult
Workshops/Tutorials/Demos Chair: Nuno Vasconcelos
Publicity Chairs: Ambrish Tyagi Charless Fowlkes Yuan Li
Publications Chair: Eric Mortensen
Finance/Local Arrangments Chair: Ninad Thakoor
Ph.D. Forum Chair: Amit Roy-Chowdhury
WACV 2015 Area Chairs
Amir Amini Mohammed Bennamoun Thierry Bouwmans Francois Bremond Michael Brown Peter Carr Andrea Cavallaro
Tsuhan Chen Marco Cristani Kristin Dana Shiloh Dockstrader Bruce Draper James Ferryman Riad Hammoud
Mark Keck Jia Li Yi Li Jingen Liu Scott McCloskey Xue Mei Ram Nevatia
Federico Pernici Massimo Piccardi Robert Pless Conrad Sanderson Vinay Sharma Min Shin Peter Tu
Oncel Tuzel Senem Velipasalar Hongcheng Wang Zhigang Zhu
Organizing Committee & Area Chairs
Tuesday, January 6 Program
3
Tuesday, January 6
0730–1700 Registration (Paniolo Ocean Terrace)
Tutorial: Exploiting Low-Rank Properties of Visual Data for Low-, Mid-, and High-Level Computer Vision Applications
Organizer: Kui Jia Tianzhu Zhang Weisheng Dong
Time: 0800-1200 (Half Day — Morning)
Location: Naupaka Salon 1-4
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, 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.
This tutorial aims to present the very recent breakthroughs in
computer vision and image processing research. These results
are achieved by leveraging new powerful low-rank/sparsity
models and by developing efficient large-scale optimization
algorithms. We cover a variety of mainstream vision
applications ranging from low-level image processing,
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 how
sparsity/low-rank models can be designed to harness their
problem nature and achieve striking performance.
1000–1100 Coffee Break (Naupaka Pre-function)
1200–1300 Lunch (On your own)
1300–1310 Welcome by the General Chairs (Naupaka Salon 1-4)
1310–1400 Invited Talk (Naupaka Salon 1-4)
Death of the Camera, Steven Seitz (Univ. of Washington)
Abstract: The last roll of Kodachrome was developed on Dec. 30 2010 in at Dwayne's Photo in Parsons Kansas. My beloved Canon AE-1 that I got for my bar mitzvah is officially a relic. Much more surprising, our “digital” cameras are fast becoming relics. In this talk, I'll discuss the rise and fall of the consumer camera and speculate on what's next.
1400–1415 Coffee Break (Naupaka Pre-function)
1415–1640 Oral Session 1: Tracking (Naupaka Salon 1-4)
Format (5 min. short presentation)
1. Visual Recognition to Access and Analyze People Density
and Flow Patterns in Indoor Environments, Cristian Ruz,
Christian Pieringer, Billy Peralta, Ivan Lillo, Pablo Espinace,
Rodrigo Gonzalez, Bruno Wendt, Domingo Mery, Alvaro
Soto
2. Online Visual Tracking Using Temporally Coherent Part
Clusters, Wenbo Li, Longyin Wen, Mooi-Choo Chuah, Yi
Zhang, Zhen Lei, Stan Z. Li
3. Real Time Multi-Vehicle Tracking and Counting at
Intersections from a Fisheye Camera, Wei Wang, Tim Gee,
Jeff Price, Hairong Qi
4. Adaptive Local Movement Modelling for Object Tracking,
Baochang Zhang, Zhigang Li, Alessandro Perina, Alessio Del
Bue, Vittorio Murino
5. Bayesian Multi-Object Tracking Using Motion Context
from Multiple Objects, Ju Hong Yoon, Ming-Hsuan Yang,
Jongwoo Lim, Kuk-Jin Yoon
Tuesday, January 6 Program
4
6. Multi-Person Tracking Based on Body Parts and Online
Random Ferns Learning of Thermal Images, Joon-Young
Kwak, ByoungChul Ko, Jae-Yeal Nam
7. Generalized Sum of Gaussians for Real-Time Human Pose
Tracking from a Single Depth Sensor, Meng Ding, Guoliang
Fan
8. Qualitative Tracking Performance Evaluation without
Ground-Truth, Bohyung Han, Jihun Hamm
9. Lie-Struck: Affine Tracking on Lie Groups using Structured
SVM, Gao Zhu, Fatih Porikli, Yansheng Ming, Hongdong Li
10. Enhancing Linear Programming with Motion Modeling for
Multi-target Tracking, Niall McLaughlin, Jesus Martinez Del
Rincon, Paul Miller
11. Multi-Person Tracking Based on Body Parts and Online
Random Ferns Learning of Thermal Images, Joon-Young
Kwak; ByoungChul Ko; Jae-Yeal Nam
12. Part-based Tracking via Salient Collaborating Features,
Wassim Bouachir, Guillaume-Alexandre Bilodeau
13. Key-Pose Prediction in Cyclic Human Motion, Dan Zecha,
Rainer Lienhart
14. Non-rigid Articulated Point Set Registration for Human
Pose Estimation, Song Ge, Guoliang Fan
15. Co-operative Pedestrians Group Tracking in Crowded
Scenes using an MST Approach, Achint Setia, Anurag
Mittal
16. Tracking People by Evolving Social Groups: An Approach
with Social Network Perspective, Linan Feng, Bir Bhanu
17. Efficient Training of Multiple Ant Tracking, Lance Rice,
Anna Dornhaus, Min C. Shin
18. Spatially Stratified Correspondence Sampling for Real-
Time Point Cloud Tracking, Jeremie Papon, Markus
Schoeler, Florentin Wörgötter
19. Beyond Pedestrians: A Hybrid Approach of Tracking
Multiple Articulating Humans, Weijun Wang, Ram Nevatia,
Bo Yang
20. 3D Pictorial Structures for Human Pose Estimation with
Supervoxels, Alexander Schick, Rainer Stiefelhagen
21. Analyzing Tracklets for the Detection of Abnormal Crowd
Behavior, Hossein Mousavi, Seyed Mohammadi, Alessandro
Perina, Ryad Chellali, Vittorio Murino
22. Adaptive Deformation Handling for Pedestrian Detection,
Hak Kyoung Kim, YongHyun Kim, DaiJin Kim
23. Face Alignment Refinement, Andy Zeng, Vishnu Naresh
Boddeti, Kris M. Kitani, Takeo Kanade
24. Training a Scene-Specific Pedestrian Detector Using
Tracklets, Yunxiang Mao, Zhaozheng Yin
25. Joint Detection and Tracking of Moving Objects Using
Spatio-Temporal Marked Point Processes, Paula Crăciun,
Mathias Ortner, Josiane Zerubia
26. Autonomous Driving Simulation for Unmanned Vehicles,
Danchen Zhao, Yuehu Liu, Chi Zhang, Yaochen Li
27. Forecasting Human Pose and Motion with Multibody
Dynamic Model, Song Cao, Ram Nevatia
28. Automatic 4D Facial Expression Recognition Using DCT
Features, Mingliang Xue, Ajmal Mian, Wanquan Liu, Ling Li
29. Touch Gesture-Based Active User Authentication Using
Dictionaries, Heng Zhang, Vishal M. Patel, Mohammed
Fathy, Rama Chellappa
1640–1800 Poster Session 1 (Naupaka Salon 5-7)
Posters for Oral Session 1
1640–1800 Demo (Naupaka Salon 5-7)
Progressive 3D Model Acquisition with a Commodity Hand-held Camera, Zhuoliang Kang, Gerard Medioni (Univ. of Southern California)
1800–1900 Dinner (Luau Grounds)
Tuesday, January 6 Program
5
1900–2115 Oral Session 2: Robotic Vision, 3D, and Surveillance (Naupaka Salon 1-4)
Format (5 min. short presentation)
1. Mimicking Human Camera Operators, Jianhui Chen, Peter
Carr
2. Efficiently Constructing Mosaics from Video Collections,
Frank Liu, Rob Hess, Alan Fern
3. Vision-based Offline-Online Perception Paradigm for
Autonomous Driving, German Ros, Sebastian Ramos,
Manuel Granados, Amir Bakhtiary, David Vazquez, Antonio
M. Lopez
4. Real-time Barcode Detection in the Wild, Clement Creusot,
Asim Munawar
5. Structured Hough Voting for Vision-based Highway Border
Detection, Zhiding Yu, Wende Zhang, Bhagavatula V. K.
Vijaya Kumar, Dan Levi
6. A Motion Blur Resilient Fiducial For Quadcopter Imaging,
Meghshyam G. Prasad, Sharat Chandran, Michael S. Brown
7. Inertial Optical Flow for Throw-And-Go Micro Air Vehicles,
Stephan Weiss, Roland Brockers, Sigurd Albrektsen, Larry
Matthies
8. Progressive 3D Model Acquisition with a Commodity
Hand-held Camera, Zhuoliang Kang, Gérard Medioni
9. Geometry-Aware Feature Matching for Structure from
Motion Applications, Rajvi Shah, Vanshika Srivastava, P J
Narayanan
10. Visual Gyroscope for Accurate Orientation Estimation,
Wilfried Hartmann, Michal Havlena, Konrad Schindler
11. Fast Approximate Matching of Videos from Hand-Held
Cameras for Robust Background Subtraction, Raffay
Hamid, Atish Das Sarma, Dennis DeCoste, Neel Sundaresan
12. Photometric Stereo in the Wild, Chun-Ho Hung, Tai-pang
Wu, Yasuyuki Matsushita, Li Xu, Jiaya Jia, Chi-Keung Tang
13. High-Breakdown Bundle Adjustment, Anders Eriksson,
Mats Isaksson, Tat-Jun Chin
14. 3D Reconstruction from Hyperspectral Images, Ali Zia, Jie
Liang, Jun Zhou, Yongsheng Gao
15. Flexible Trajectory Indexing for 3D Motion Recognition,
Jianyu Yang, Junsong Yuan, Y.F. Li
16. A Low-noise Fluttering Shutter Camera Handling
Accelerated Motion, Scott McCloskey, Sharath Venkatesha,
Kelly Muldoon, Ryan Eckman
17. A Sequential Online 3D Reconstruction System Using
Dense Stereo Matching, Sosuke Yamao, Mamoru Miura,
Shuji Sakai, Koichi Ito, Takafumi Aoki
18. Detecting Building-level Changes of a City Using Street
Images and a 2D City Map, Daiki Tetsuka, Takayuki Okatani
19. Robot-Centric Activity Recognition from First-Person
RGB-D Videos, Lu Xia, Ilaria Gori, J. K. Aggarwal, Michael S.
Ryoo
20. A Camera Network Tracking (CamNeT) Dataset and
Performance Baseline, Shu Zhang, Elliot Staudt, Tim
Faltemier, Amit K. Roy-Chowdhury
21. Multi-Shot Re-Identification with Random-Projection-
Based Random Forests, Yang Li, Ziyan Wu, Richard J.
Radke
22. A Global-to-Local Framework for Infrared and Visible
Image Sequence Registration, Michael Ying Yang, Yu
Qiang, Bodo Rosenhahn
23. Anomaly Localization in Topic-based Analysis of
Surveillance Videos, Deepak Pathak, Abhijit Sharang,
Amitabha Mukerjee
24. 3-D Mediated Detection and Tracking in Wide Area Aerial
Surveillance, Bor-Jeng Chen, Gérard Medioni
25. Improving Vision-based Self-positioning in Intelligent
Transportation Systems via Integrated Lane and Vehicle
Detection, Parag S. Chandakkar, Yilin Wang, Baoxin Li
26. The Information in Temporal Histograms, Yedid Hoshen,
Shmuel Peleg
27. Estimating Drivable Collision-Free Space from Monocular
Video, Jian Yao, Srikumar Ramalingam, Yuichi Taguchi,
Yohei Miki, Raquel Urtasun
2115–2230 Poster Session 2 (Naupaka Salon 5-7)
Posters for Oral Session 2
2115–2230 Demo (Naupaka Salon 5-7)
Progressive 3D Model Acquisition with a Commodity Hand-held Camera, Zhuoliang Kang, Gerard Medioni (Univ. of Southern California)
Wednesday, January 7 Program
6
Wednesday, January 7
0730–1700 Registration (Paniolo Ocean Terrace)
Tutorial: Image Noise Removal using Fuzzy Sets and Fuzzy Logic
Organizer: Mike Nachtegael
Time: 0800-1200 (Half Day — Morning)
Location: Naupaka Salon 1-4
Description: Noise removal is an important research branch
within image processing. Quite often images are disturbed by
noise due to external circumstances, and algorithms to detect
and remove that noise are required to improve the quality of
the images. Applications of noise removal are wide, and can
be found in the commercial, satellite, medical and military
field. The tutorial will provide insight in the way fuzzy set
theory and fuzzy logic can be applied in image processing
(both still images and video). Since fuzzy filters mimic the
behaviour of experts, they usually lead to good results, as will
be demonstrated.
1000–1100 Coffee Break (Naupaka Pre-function)
1200–1300 Lunch (On your own)
1300–1445 Special Session: Life Sciences Applications (Naupaka Salon 1-4)
1. Use of Computer Vision for Improving Detection of
Traumatic Brain Injury, Andre Obenaus
2. Identifying Predictive Markers of Tumor Composition from
a Large Cohort of Histology Sections, Bahram Parvin
3. Toward Image-based Personalized Cardiac Modeling for
Therapy, Ankur Kapoor
1445–1500 Coffee Break (Naupaka Pre-function)
1500–1640 Oral Session 3: Vision and Learning (Naupaka Salon 1-4)
Format (5 min. short presentation)
1. De-Correlating CNN Features for Generative
Classification, Chaitanya Desai, Jayan Eledath, Harpreet
Sawhney, Mayank Bansal
2. Classification of 3D Multicellular Organization in Phase
Microscopy for High Throughput Screening of Therapeutic
Targets, Hang Chang, Bahram Parvin
3. Sequential Boosting for Learning a Random Forest
Classifier, Florian Baumann, Wei Liu, Arne Ehlers, Bodo
Rosenhahn
4. Learning an Aesthetic Photo Cropping Cascade, Peng
Wang, Zhe Lin, Radomír Měch
5. Learned Collaborative Representations for Image
Classification, Jiqing Wu, Radu Timofte, Luc Van Gool
6. Scalable Similarity Learning using Large Margin
Neighborhood Embedding, Zhaowen Wang, Jianchao
Yang, Zhe Lin, Jonathan Brandt, Shiyu Chang, Thomas
Huang
7. Tree-based Locally Linear Regression for Image Denoising,
Xin Lu, Zhe Lin, Hailin Jin
8. Convergence of Iteratively Re-weighted Least Squares to
Robust M-estimators, Khurrum Aftab, Richard Hartley
9. Image Classification using Generative NeuroEvolution for
Deep Learning, Phillip Verbancsics, Josh Harguess
10. Interleaved Regression Tree Field Cascades for Blind
Image Deconvolution, Kevin Schelten, Sebastian Nowozin,
Jeremy Jancsary, Carsten Rother, Stefan Roth
11. Learning Localized Perceptual Similarity Metrics for
Interactive Categorization, Catherine Wah, Subhransu Maji,
Serge Belongie
12. Learning to Select and Order Vacation Photographs,
Fereshteh Sadeghi, J. Rafael Tena, Ali Farhadi, Leonid Sigal
13. A Multi-Modal Sparse Coding Classifier Using Dictionaries
with Different Number of Atoms, Soheil Shafiee, Farhad
Kamangar, Vassilis Athitsos
Wednesday, January 7 Program
7
14. A Linear Chain Markov Model for Detection and
Localization of Cells in Early Stage Embryo Development,
Aisha Khan, Stephen Gould, Mathieu Salzmann
15. Deeply-Learned Feature for Age Estimation, Xiaolong
Wang, Rui Guo, Chandra Kambhamettu
16. Unsupervised Feature Extraction Inspired by Latent Low-
Rank Representation, Yaming Wang, Vlad I. Morariu, Larry
S. Davis
17. Predicting Geo-informative Attributes in Large-scale
Image Collections using Convolutional Neural Networks,
Stefan Lee, Haipeng Zhang, David J. Crandall
18. Hierarchical Spherical Hashing for Compressing High
Dimensional Vectors, Sravanthi Bondugula, Larry S. Davis
19. Bank of Quantization Models: A Data-Specific Approach
to Learning Binary Codes for Large-Scale Retrieval
Applications, Frederick Tung, Julieta Martinez, Holger H.
Hoos, James J. Little
20. Re-ranking by Multi-feature Fusion with Diffusion for
Image Retrieval, Fan Yang, Bogdan Matei, Larry S. Davis
1640–1800 Poster Session 3 (Naupaka Salon 5-7)
Posters for Oral Session 3
1640–1800 PhD Forum (Naupaka Salon 5-7)
Fast and Robust Estimation for Autonomous Navigation, German Ros (Universitat Autònoma de Barcelona)
Unsupervised Semantic Perception, Summarization, and Autonomous Exploration for Robots in Unstructured Environments, Yogesh Girdhar (Woods Hole Oceanographic Institution)
Photogrammetric Method of Distant Reconstruction of Displacement Fields in Deformable Solids, Ghulam Mubashar Hassan (Univ. of Western Australia)
Image Analysis Using Visual Saliency with Applications in Hazmat Sign Detection and Recognition, Bin Zhao (Purdue Univ.)
Model-free Point Cloud Segmentation and Tracking, Jeremie Papon (Georg-August-Universität Göttingen)
Topology-Constrained Non-rigid Articulated Point Set Registration, Song Ge (Oklahoma State Univ.)
Manifold Learning for Human Motion Modeling and Vision-based Pose Tracking, Meng Ding (Oklahoma State Univ.)
Pedestrian Detection in Low Resolution Videos Using Multi-Frame HOG Detector, Hisham Sager (Colorado School of Mines)
1640–1800 Demo (Naupaka Salon 5-7)
Facial Attribute Recognition for Real Time Video, Ethan Rudd, Terrance E. Boult, (Univ. of Colorado at Colorado Springs)
1800–1900 Dinner (Naupaka Lawn)
1900–2105 Oral Session 4: Applications of Computer Vision (Naupaka Salon 1-4)
Format (5 min. short presentation)
1. Leveraging Context to Support Automated Food
Recognition in Restaurants, Vinay Bettadapura, Edison
Thomaz, Aman Parnami, Gregory D. Abowd, Irfan Essa
2. Genre and Style based Painting Classification, Siddharth
Agarwal, Harish Karnick, Nirmal Pant, Urvesh Patel
3. Choosing Basic-Level Concept Names using Visual and
Language Context, Alexander Mathews, Lexing Xie, Xuming
He
4. The Mountain Habitats Segmentation and Change
Detection Dataset, Frédéric Jean, Alexandra Branzan Albu,
David Capson, Eric Higgs, Jason T. Fisher, Brian M.
Starzomski
5. Detection of Arrows in On-line Sketched Diagrams using
Relative Stroke Positioning, Martin Bresler, Daniel Průša,
Václav Hlaváč
6. AR-Weapon: Live Augmented Reality based First-Person
Shooting System , Zhiwei Zhu, Vlad Branzoi, Mikhail
Sizintsev, Nicholas Vitovitch, Taragay Oskiper, Ryan
Villamil, Ali Chaudhry, Supun Samarasekera, Rakesh Kumar
7. Egocentric Field-of-View Localization Using First-Person
Point-of-View Devices, Vinay Bettadapura, Irfan Essa,
Caroline Pantofaru
Wednesday, January 7 Program
8
8. Multiple Insect Tracking with Occlusion Sub-Tunnels,
Thomas Fasciano, Anna Dornhaus, Min C. Shin
9. Towards Convenient Calibration for Cross-Ratio based
Gaze Estimation, Nuri Murat Arar, Hua Gao, Jean-Philippe
Thiran
10. Composition Context Photography, Daniel Vaquero,
Matthew Turk
11. A Multi-modal 2D + 3D Face Recognition Method with a
Novel Local Feature Descriptor, Xu Dai, Shouyi Yin, Peng
Ouyang, Leibo Liu, Shaojun Wei
12. Fingerprint Orientation Modeling using Symmetric Filters,
Puneet Gupta, Phalguni Gupta
13. Gait-based Person Identification Method Using Shadow
Biometrics for Robustness to Changes in the Walking
Direction, Makoto Shinzaki, Yumi Iwashita, Ryo Kurazume,
Koichi Ogawara
14. Quality-Aware Estimation of Facial Landmarks in Video
Sequences, Mohammad A. Haque, Kamal Nasrollahi,
Thomas B. Moeslund
15. Circular Hough Transform and Local Circularity Measure
for Weight Estimation of a Graph-Cut based Wood Stack
Measurement, Bo Galsgaard, Dennis H. Lundtoft, Ivan
Nikolov, Kamal Nasrollahi, Thomas B. Moeslund
16. Robust Fastener Detection for Autonomous Visual Railway
Track Inspection, Xavier Gibert, Vishal M. Patel, Rama
Chellappa
17. Adaptive Keyframe Selection for Video Summarization,
Shayok Chakraborty, Omesh Tickoo, Ravishankar Iyer
18. Extending Digital Image Correlation to Reconstruct
Displacement and Strain Fields around Discontinuities in
Geomechanical Structures under Deformation, Ghulam
Mubashar Hassan, Cara MacNish, Arcady Dyskin
19. Entropy-based Similarity Evaluation and Visualization of
Cartographic Symbol Sets, Florence Ying Wang, Masahiro
Takatsuka
20. City Scale Image Geolocalization via Dense Scene
Alignment, Semih Yagcioglu, Erkut Erdem, Aykut Erdem
21. Change Detection in Laser-Scanned Data of Industrial
Sites, Jing Huang, Suya You
22. Document Retrieval with Unlimited Vocabulary, Viresh
Ranjan, Gaurav Harit, C. V. Jawahar
23. Material Classification on Symmetric Positive Definite
Manifolds, Masoud Faraki, Mehrtash T. Harandi, Fatih
Porikli
24. Distance Transform Based Active Contour Approach for
Document Image Rectification, Dhaval Salvi, Kang Zheng,
Youjie Zhou, Song Wang
25. Extending the Performance of Human Classifiers using a
Viewpoint Specific Approach, Endri Dibra, Jerome Maye,
Olga Diamanti, Roland Siegwart, Paul Beardsley
2105–2230 Poster Session 4 (Naupaka Salon 5-7)
Posters for Oral Session 4
2105–2230 Demo (Naupaka Salon 5-7)
Facial Attribute Recognition for Real Time Video, Ethan Rudd, Terrance E. Boult, (Univ. of Colorado at Colorado Springs)
Thursday, January 8 Program
9
Thursday, January 8
1230–1700 Registration (Paniolo Ocean Terrace)
1300–1400 Invited Talk (Naupaka Salon 1-4)
DARPA’s Visual Media Reasoning Program and Tools for CV Researchers, Mike Geertsen (Program Manager DARPA)
Abstract: Our country's adversaries often take photos and videos to claim responsibility for events or to illustrate capabilities. This media is sometimes confiscated by the Department of Defense from a variety of devices, including laptops, cellphone cameras and memory cards. The volume of this visual media is quickly outpacing our ability to review, let alone analyze the contents of every image. DARPA’s Visual Media Reasoning (VMR) program seeks to provide “visual intelligence” to our warfighters and analysts by providing a software system that lets users ask queries of ad hoc photo content, such as “What make and model of vehicle is that?” or “Is this person on our terrorist watch list?” or “Where is this building located?” The result of VMR may be an enhanced capability to generate intelligence required for successful counterinsurgency and counterterrorist operations.
Under the Visual Media Reasoning Program, DARPA has facilitated the development of a range of innovative computer vision technologies. This includes two general-purpose tools which DARPA and its contractors will make generally available. One of these tools enables the automated evaluation of vision algorithms over their parameter spaces. The other enables the automatic generation of large amounts of synthetic images for use in developing and testing vision algorithms. These tools are planned to be released to the research community in early 2015. Mike Geertsen, Program Manager for the DARPA Visual Media Reasoning Program, will present an overview of the Visual Media Reasoning (VMR) Program, its systems approach to large-volume visual search and the research tools.
1400–1415 Coffee Break (Naupaka Pre-function)
1415–1640 Oral Session 5: Object Recognition (Naupaka Salon 1-4)
Format (5 min. short presentation)
1. Heterogeneous Multi-column ConvNets with a Fusion
Framework for Object Recognition, Yandong Li, Ferdous
Sohel, Mohammed Bennamoun, Hang Lei
2. Error Factor Analysis for Wild Scene Image-Labelling, Peng
Wang, Alan Yuille
3. Efficient Model Evaluation with Bilinear Separation Model,
Fanyi Xiao, Martial Hebert
4. Evaluation of Features for Leaf Classification in
Challenging Conditions, David Hall, Chris McCool, Feras
Dayoub, Niko Sünderhauf, Ben Upcroft
5. Unsupervised Generation of Context-Relevant Training-
Sets for Visual Object Recognition Employing
Multilinguality, Markus Schoeler, Florentin Wörgötter,
Jeremie Papon, Tomas Kulvicius
6. Local Novelty Detection in Multi-class Recognition
Problems, Paul Bodesheim, Alexander Freytag, Erik Rodner,
Joachim Denzler
7. Pose Estimation of Object Categories in Videos Using
Linear Programming, Michele Fenzi, Laura Leal-Taixé,
Konrad Schindler, Jörn Ostermann
8. Category Attentional Search for Fast Object Detection by
Mimicking Human Visual Perception, Hawook Jeong,
Sangdoo Yun, Kwang Moo Yi, Jin Young Choi
9. How to Transfer? Zero-Shot Object Recognition via
Hierarchical Transfer of Semantic Attributes, Ziad Al-
Halah, Rainer Stiefelhagen
10. Menu-Match: Restaurant-Specific Food Logging from
Images, Oscar Beijbom, Neel Joshi, Dan Morris, Scott
Saponas, Siddharth Khullar
11. Non-Negative Sparse Coding with Regularizer for Image
Classification, Lopamudra Mukherjee, Alex Hall
12. Selective Pooling Vector for Fine-grained Recognition,
Guang Chen, Jianchao Yang, Hailin Jin, Eli Shechtman,
Jonathan Brandt, Tony X. Han
13. An Ensemble Color Model for Human Re-identification,
Xiaokai Liu, Hongyu Wang, Yi Wu, Jimei Yang, Ming-Hsuan
Yang
Thursday, January 8 Program
10
14. Bikers are Like Tobacco Shops, Formal Dressers are Like
Suits: Recognizing Urban Tribes with Caffe, Yufei Wang,
Garrison W. Cottrell
15. A General Framework for Fast 3D Object Detection and
Localization Using an Uncalibrated Camera, Andrés Solís
Montero, Jochen Lang, Robert Laganière
16. Characterizing Feature Matching Performance Over Long
Time Periods, Abby Stylianou, Austin Abrams, Robert Pless
17. Action Recognition using Discriminative Structured
Trajectory Groups, Indriyati Atmosukarto, Narendra Ahuja,
Bernard Ghanem
18. Multimodal Registration of Multiple Retinal Images Based
on Line Structures, Matthias Hernandez, Gérard Medioni,
Zhihong Hu, SriniVas Sadda
19. Automated Axon Segmentation from Highly Noisy
Microscopic Videos, John Bowler, Rogerio Feris, Liangliang
Cao, Jun Wang, Mo Zhou
20. A Robust Adaptive Classifier for Detector Adaptation in a
Video, Pramod Sharma, Ram Nevatia
21. Person Re-Identification Using the Silhouette Shape
Described by a Point Distribution Model, Olivier Huynh,
Bogdan Stanciulescu
22. Ensembles of Correlation Filters for Object Detection,
Ryan Tokola, David Bolme
23. Near Duplicate Image Discovery on One Billion Images,
Saehoon Kim, Xin-Jing Wang, Lei Zhang, Seungjin Choi
24. Runway to Realway: Visual Analysis of Fashion, Sirion
Vittayakorn, Kota Yamaguchi, Alexander C. Berg, Tamara L.
Berg
25. Feature Fusion by Similarity Regression for Logo Retrieval,
Fan Yang, Mayank Bansal
26. Retrieval of Images with Objects of Specific Size, Location
and Spatial Configuration, Niloufar Pourian, B.S.
Manjunath
27. Norm-Induced Entropies for Decision Forests, Christoph
Lassner, Rainer Lienhart
28. Visual Saliency Models Based on Spectrum Processing, Bin
Zhao, Edward J. Delp
29. Family Member Identification from Photo Collections,
Qieyun Dai, Peter Carr, Leon Sigal, Derek Hoiem
1640–1800 Poster Session 5 (Naupaka Salon 5-7)
Posters for Oral Session 5
1640–1800 Demo (Naupaka Salon 5-7)
Real-World Impacts in Computer Vision and Photogrammetry: How Trimble Navigation is Using Google’s Project Tango to Transform the Way our Customers Work, Jordan Lawver (Trimble)
1800–1900 Dinner (Naupaka Lawn)
1900–2110 Oral Session 6: Segmentation and Recognition (Naupaka Salon 1-4)
Format (5 min. short presentation)
1. A Self-Adjusting Approach to Change Detection Based on
Background Word Consensus, Pierre-Luc St-Charles,
Guillaume-Alexandre Bilodeau, Robert Bergevin
2. Real-time Multi-scale Action Detection From 3D Skeleton
Data, Amr Sharaf, Marwan Torki, Mohamed E. Hussein,
Motaz El-Saban
3. A Multi-modal Graphical Model for Scene Analysis, Sarah
Taghavi Namin, Mohammad Najafi, Mathieu Salzmann,
Lars Petersson
4. Multi-class Semantic Video Segmentation with Exemplar-
based Object Reasoning, Buyu Liu, Xuming He, Stephen
Gould
5. Finding Temporally Consistent Occlusion Boundaries in
Videos using Geometric Context, Syed Hussain Raza,
Ahmad Humayun, Irfan Essa, Matthias Grundmann, David
Anderson
6. Visual Object Clustering via Mixed-Norm Regularization,
Xin Zhang, Duc-Son Pham, Dinh Phung, Wanquan Liu,
Budhaditya Saha, Svetha Venkatesh
7. Efficient Facade Segmentation using Auto-Context, Varun
Jampani, Raghudeep Gadde, Peter V. Gehler
8. Motion Segmentation of Truncated Signed Distance
Function based Volumetric Surfaces, Samunda Perera,
Nick Barnes, Xuming He, Shahram Izadi, Pushmeet Kohli,
Ben Glocker
9. Real-time Facial Expression Recognition on Smartphones,
Myunghoon Suk, Balakrishnan Prabhakaran
Thursday, January 8 Program
11
10. Extracting Image Regions by Structured Edge Prediction,
Yi-Ting Chen, Jimei Yang, Ming-Hsuan Yang
11. Semantic Instance Labeling Leveraging Hierarchical
Segmentation, Steven Hickson, Irfan Essa, Henrik
Christensen
12. Multiscale Superpixels and Supervoxels Based on
Hierarchical Edge-Weighted Centroidal Voronoi
Tessellation, Youjie Zhou, Lili Ju, Song Wang
13. Topology-Preserving Multi-Label Image Segmentation,
Jarrell Waggoner, Youjie Zhou, Jeff Simmons, Marc De
Graef, Song Wang
14. Action Recognition from Depth Sequences Using Depth
Motion Maps-based Local Binary Patterns, Chen Chen,
Roozbeh Jafari, Nasser Kehtarnavaz
15. SparseFlow: Sparse Matching for Small to Large
Displacement Optical Flow, Radu Timofte, Luc Van Gool
16. Gradient Boundary Histograms for Action Recognition,
Feng Shi, Robert Laganière, Emil Petriu
17. Dense and Deformable Motion Extraction in Dynamic
Scenes Based on Hierarchical MRF Optimization in RGB-D
Images, Wei Wang, Darius Burschka
18. An Improved Model for Segmentation and Recognition of
Fine Grained Activities with Application to Surgical
Training Tasks, Colin Lea, Gregory D. Hager, René Vidal
19. Optimization of Plane Fits to Image Segments in Multi-
View Stereo, Nelson Max, Hyojin Kim
20. Robust Nonrigid Point Set Registration using Graph-
Laplacian Regularization, Varun Panaganti, R. Aravind
21. Semantic Multi-body Motion Segmentation, Cosimo
Rubino, Marco Crocco, Vittorio Murino, Alessio Del Bue
22. Stereovision Bias Removal by Autocorrelation, Yang
Cheng, Larry H. Matthies
23. Clauselets: Leveraging Temporally Related Actions for
Video Event Analysis, Hyungtae Lee, Vlad I. Morariu, Larry
S. Davis
24. How to Collect Segmentations for Biomedical Images? A
Benchmark Evaluating the Performance of Experts,
Crowdsourced Non-Experts, and Algorithms, Danna
Gurari, Diane Theriault, Mehrnoosh Sameki, Brett Isenberg,
Tuan A. Pham, Alberto Purwada, Patricia Solski, Matthew
Walker, Chentian Zhang, Joyce Y. Wong, Margrit Betke
25. Shot Boundary Detection with Graph Theory using
Keypoint Features and Color Histograms, Kyoungmin Lee,
Mathias Kölsch
26. Fixing WTFs: Detecting Image Matches caused by
Watermarks, Timestamps, and Frames in Internet Photos,
Tobias Weyand, Chih-Yun Tsai, Bastian Leibe
2110–2230 Poster Session 6 (Naupaka Salon 5-7)
Posters for Oral Session 6
2110–2230 Demo (Naupaka Salon 5-7)
Real-World Impacts in Computer Vision and Photogrammetry: How Trimble Navigation is Using Google’s Project Tango to Transform the Way our Customers Work, Jordan Lawver (Trimble)
Friday, January 9 Workshops
12
Friday, January 9
0830–1700 Registration (Paniolo Ocean Terrace)
1030–1130 Coffee Break (Naupaka Pre-function)
1200–1300 Lunch (Naupaka Pre-function)
1500–1600 Coffee Break (Naupaka Pre-function)
Workshop on Applications for Aerial Video Exploitation
Organizers: Matt Turek Mikel Rodriguez Larry Davis Anthony Hoogs
Location: Alii I
Schedule: Full Day
0900 Invited Talk: Wide Area Aerial Surveillance,
Opportunities and Challenges, Gérard Medioni (Univ. of
Southern California)
0945 Invited Talk: Challenges in Video Exploitation, Juan
Vasquez (Air Force Research Lab)
1030 Object Detection in Low Resolution Overhead Imagery,
Paul Kidwell, Kofi Boakye
1100 Morning Break
1115 Invited Talk: Modeling Video via Structured Sparsity,
Alexey Castrodad (United States Department of
Defense)
1200 Demo: Activity Recognition Applications from
Contextual Video-Text Fusion, Georgiy Levchuk,
Charlotte Shabarekh
1230 Lunch (Naupaka Pre-function)
1330 Invited Talk: Skybox Satellite FMV and Image Data
Applications, Andrew Hock (Skybox Imaging)
1415 Multi-Objective Detector and Tracker Parameter
Optimization via NSGA-II, Ryan Fogle, Karl Salva, Juan
Vasquez, Ashley Kessler
1445 3D Urban Reconstruction from Wide Area Aerial
Surveillance Video, Zhuoliang Kang, Gérard Medioni
1515 Context Exploitation in Intelligence, Surveillance, and
Reconnaissance for Detection Algorithms, Jonathan
Tucker, Robert Stanfill
1545 Afternoon Break
1600 Demo: Depth Map Generation for Aerial Video in
Natural Scenery, Jung-Jae Yu, Seung-Wan Han
1630 Panel Discussion: Future trends in aerial and overhead
video exploitation
1700 Invited Talk: Vision-based Target Tracking, Brandon
Basso (3D Robotics)
1730 Invited Talk: UAV Sense and Avoid Using Computer
Vision, James Revell (BAE Systems)
1800 Closing Remarks
Friday, January 9 Workshops
13
Automated Analysis of Video Data for Wildlife Surveillance
Organizers: Benjamin Richards Anthony Hoogs David Kriegman
Location: Alii II
Schedule: Full Day
0900 Overview of NOAA Fisheries Optical Data Streams and
Automated Analysis Needs, Benjamin Richards (NOAA
Fisheries)
1000 Counting and Sizing Fish, Elizabeth Clarke (NOAA
Fisheries)
1030 Morning Break
1045 Invited Talk: Video: Big Data, Big Challenges, John
Garofolo (National Institute of Standards and
Technology)
1145 Monitoring Giraffe Behavior in Thermal Video, Victor
Gan, Peter Carr, Joseph Soltis
1215 Lunch (Naupaka Pre-function)
1315 Invited Talk: Animal Detection and Classification in
Video/Images in the Mojave Desert, Terry Boult (Univ.
of Colorado at Colorado Springs)
1415 Dolphin Detection and Tracking, Jeremy Karnowski,
Edwin Hutchins, Christine Johnson
1445 Automated Detection of Rockfish in Unconstrained
Underwater Videos using Haar Cascades and a New
Image Dataset: Labeled Fishes in the Wild, George
Cutter, Kevin Stierhoff, Jiaming Zeng
1515 Afternoon Break
1530 Invited Talk: Hiding in Plain Sight: Experiments in
Nonspectral Camouflage Detection for Robust Benthic
Census, Lakshman Prasad (Los Alamos National
Laboratories)
1600 Evolutionary Computational Methods for Optimizing
the Classification of Sea Stars in Underwater Images,
André Mendes, Maia Hoeberechts, Alexandra Branzen
Albu
1630 Invited Talk: Penoptes: A Development Framework for
Citizen Science, Alexandra Swanson (Zooniverse)
1715 Closing Remarks
Benchmarking Multi-Target Tracking
Organizers: Laura Leal-Taixé Anton Milan Ian Reid Stefan Roth Konrad Schindler
Location: Alii III
Schedule: Full Day
1000 Welcome
1030 Keynote Speaker: Alexandre Alahi (Stanford Univ.)
1130 Discovery of Sets of Mutually Orthogonal Vanishing
Points in Videos, Till Kroeger, Dengxin Dai, Radu
Timofte, Luc Van Gool
1200 Lunch (Naupaka Pre-function)
1300 Multiple Object Tracking Benchmark, Laura Leal-Taixe,
Anton Milan
1400 Solving Multiple People Tracking In A Minimum Cost
Arborescence, Roberto Henschel, Laura Leal-Taixé,
Bodo Rosenhahn
1430 TBA
1500 TBA
1530 Discussion: Challenges in Multiple Object Tracking
Evaluation
1630 Keynote Speaker: TBA
1730 Further Discussion and Closing Remarks
WACV 2015 Notes
14
Poster