Title
Detecting conversational groups in images and sequences: A robust game-theoretic approach.
Abstract
•A game-theoretic approach for group detection in still images and video.•Extended (game) theory to integrate temporal information and data continuity.•A new model of frustum of visual attention which achieves better performance.•A new annotated dataset for group detection including 10685 labeled frames.•Performance evaluation on all public datasets outperforming the state of the art.
Year
DOI
Venue
2016
10.1016/j.cviu.2015.09.012
Computer Vision and Image Understanding
Keywords
Field
DocType
Group detection,F-formation detection,Conversational groups,Game-theory,Scene understanding
Social relation,Social robot,Signal processing,Computer vision,Computer science,Robustness (computer science),Game theoretic,Game theory,Artificial intelligence,Evolutionary game theory,Spatial structure,Machine learning
Journal
Volume
Issue
ISSN
143
1
1077-3142
Citations 
PageRank 
References 
17
0.57
36
Authors
6
Name
Order
Citations
PageRank
Sebastiano Vascon1356.04
Eyasu Zemene Mequanint2191.28
M. Cristani31928109.03
Hayley Hung456551.21
Marcello Pelillo51888150.33
Vittorio Murino63277207.20