sub-sampled dictionaries for coarse-to-fine sparse representation-based human action recognition
DESCRIPTION
Sub-Sampled Dictionaries for Coarse-to-Fine Sparse Representation-based Human Action Recognition. Spotlight presentation for the main track of ICME 2014.TRANSCRIPT
Poster Spotlights
SUB-SAMPLED DICTIONARIES FOR COARSE-TO-FINE SPARSE REPRESENTATION-BASED HUMAN ACTION RECOGNITION
Poster Session 5, July 17h
JongHo Lee, Hyun-seok Min, Jeong-jik Seo, Wesley De Neve, and Yong Man Ro
506
SUB-SAMPLED DICTIONARIES FOR COARSE-TO-FINE SPARSE REPRESENTATION-BASED HUMAN ACTION RECOGNITION
1. IntroductionSparse representation-based classification
(SRC) has recently attracted much attentionHowever, the computational complexity of SRC
makes its usage challenging in practice We propose a novel method for human action
recognition, leveraging coarse-to-fine sparse representations
2. Proposed MethodThe time complexity of SRC depends on the
dictionary size
4. ConclusionsWe proposed a novel method for human
action recognition using coarse-to-fine sparse representations
This proposed method is able to achieve efficient human action recognition with no substantial loss in accuracy
3. Experimental Results
A: Conventional SRC (using only the Fine-Grained Dictionary) B: Proposed Method (using Coarse-to-Fine Representations)
1 2 3 4 K…
1 2 3 4 K…
1 4 H…Coarse-Grained Dictionary
Fine-Grained Dictionary
Pruned Fine-Grained Dictionary
Candidate Classes
A B0.0
10.020.030.040.050.060.070.080.0
67.5
32.8
Time Complexity (s)
Tim
e co
mpl
exity
A B0.835
0.84
0.845
0.85
0.855
0.86
0.8438
0.8567
Accuracy
Reco
gniti
on A
ccur
acy