Discriminative Latent Models for Recognizing Contextual Group Activities

被引:209
作者
Lan, Tian [1 ]
Wang, Yang [2 ]
Yang, Weilong [1 ]
Robinovitch, Stephen N. [3 ]
Mori, Greg [1 ]
机构
[1] Simon Fraser Univ, Sch Comp Sci, Burnaby, BC V5A 1S6, Canada
[2] Univ Illinois, Dept Comp Sci, Urbana, IL 61801 USA
[3] Simon Fraser Univ, Sch Engn Sci, Burnaby, BC V5A 1S6, Canada
基金
加拿大自然科学与工程研究理事会; 加拿大健康研究院;
关键词
Group activity recognition; context; latent structured models;
D O I
10.1109/TPAMI.2011.228
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we go beyond recognizing the actions of individuals and focus on group activities. This is motivated from the observation that human actions are rarely performed in isolation; the contextual information of what other people in the scene are doing provides a useful cue for understanding high-level activities. We propose a novel framework for recognizing group activities which jointly captures the group activity, the individual person actions, and the interactions among them. Two types of contextual information, group-person interaction and person-person interaction, are explored in a latent variable framework. In particular, we propose three different approaches to model the person-person interaction. One approach is to explore the structures of person-person interaction. Differently from most of the previous latent structured models, which assume a predefined structure for the hidden layer, e.g., a tree structure, we treat the structure of the hidden layer as a latent variable and implicitly infer it during learning and inference. The second approach explores person-person interaction in the feature level. We introduce a new feature representation called the action context (AC) descriptor. The AC descriptor encodes information about not only the action of an individual person in the video, but also the behavior of other people nearby. The third approach combines the above two. Our experimental results demonstrate the benefit of using contextual information for disambiguating group activities.
引用
收藏
页码:1549 / 1562
页数:14
相关论文
共 47 条
[1]  
Andrews S., 2003, Adv. Neural Inf. Process. Syst
[2]  
[Anonymous], P INT WORKSH VIS SUR
[3]  
[Anonymous], P IEEE INT C COMP VI
[4]  
[Anonymous], 2008, P EUR C COMP VIS
[5]  
[Anonymous], 2009, P IEEE C COMP VIS PA
[6]  
[Anonymous], 2007, P IEEE INT C COMP VI
[7]  
[Anonymous], P ADV NEUR INF PROC
[8]  
[Anonymous], P IEEE C COMP VIS PA
[9]  
[Anonymous], P IEEE C COMP VIS PA
[10]  
[Anonymous], 2009, P IEEE C COMP VIS PA