Viewpoint invariant collective activity recognition with relative action context

Authors:
Takuhiro Kaneko;Masamichi Shimosaka;Shigeyuki Odashima;Rui Fukui;Tomomasa Sato
Affiliations:
The University of Tokyo, Japan;The University of Tokyo, Japan;The University of Tokyo, Japan;The University of Tokyo, Japan;The University of Tokyo, Japan
Venue:
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Year:
2012

Citing 6
Cited 0

On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
LIBLINEAR: A Library for Large Linear Classification

The Journal of Machine Learning Research
Efficient inference for fully-connected CRFs with stationarity

CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
A chains model for localizing participants of group activities in videos

ICCV '11 Proceedings of the 2011 International Conference on Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an approach for collective activity recognition. Collective activities are activities performed by multiple persons, such as queueing in a line and talking together. To recognize them, the action context (AC) descriptor [1] encodes the "apparent" relation (e.g. a group crossing and facing "right"), however this representation is sensitive to viewpoint change. We instead propose a novel feature representation called the relative action context (RAC) descriptor that encodes the "relative" relation (e.g. a group crossing and facing the "same" direction). This representation is viewpoint invariant and complementary to AC; hence we employ a simplified combinational classifier. This paper also introduces two methods to accelerate performance. First, to make the contexts robust to various situations, we apply post processes. Second, to reduce local classification failures, we regularize the classification using fully connected CRFs. Experimental results show that our method is applicable to various scenes and outperforms state-of-the art methods.