Paper Info
Title
Recognition of Group Activities in Videos Based on Single-and Two-Person Descriptors
Abstract
Group activity recognition from videos is a very challenging problem that has barely been addressed. We propose an activity recognition method using group context. In order to encode both single-person description and two-person interactions, we learn mappings from highdimensional feature spaces to low-dimensional dictionaries. In particular the proposed two-person descriptor takes into account geometric characteristics of the relative pose and motion between the two persons. Both single-person and two-person representations are then used to define unary and pairwise potentials of an energy function, whose optimization leads to the structured labeling of persons involved in the same activity. An interesting feature of the proposed method is that, unlike the vast majority of existing methods, it is able to recognize multiple distinct group activities occurring simultaneously in a video. The proposed method is evaluated with datasets widely used for group activity recognition, and is compared with several baseline methods.
Year
DOI
Venue
2017
10.1109/WACV.2017.31
2017 IEEE Winter Conference on Applications of Computer Vision (WACV)
Keywords
Field
DocType
video signal processing,two-person descriptor,group activity recognition,single-person descriptor,high-dimensional feature spaces,low-dimensional dictionaries,geometric characteristics,single-person representations,two-person representations,unary potentials,pairwise potentials,energy function,structured labeling
Computer vision,ENCODE,Pairwise comparison,Activity recognition,Pattern recognition,Unary operation,Computer science,Support vector machine,Group activity recognition,Feature extraction,Artificial intelligence
Conference
ISSN
ISBN
Citations 
2472-6737
978-1-5090-4823-6
0
PageRank 
References 
Authors
0.34
35
3
Name
Order
Citations
PageRank
Stéphane Lathuilière1335.98
Georgios D. Evangelidis219912.91
Radu Horaud32776261.99