View-invariant representation and learning of human action

被引:6
作者
Rao, C [1 ]
Shah, M [1 ]
机构
[1] Univ Cent Florida, Sch Elect Engn & Comp Sci, Comp Vis Lab, Orlando, FL 32816 USA
来源
IEEE WORKSHOP ON DETECTION AND RECOGNITION OF EVENTS IN VIDEO, PROCEEDINGS | 2001年
关键词
video understanding; action recognition; view-invariant representation; spatiotemporal curvature; events; activities;
D O I
10.1109/EVENT.2001.938867
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Automatically understanding human actions from video sequences is a very challenging problem. This involves the extraction of relevant visual information front a video sequence, representation of that information in a suitable form, and interpretation of visual information for the purpose of recognition and learning. In this paper, we first present a view-invariant representation of action consisting of dynamic instants and intervals, which is computed using spatiotemporal curvature of a trajectory. This representation is then used by, our system to learn human actions without any, training. The system automatically segments video into individual actions, and computes view invariant representation for each action. The system is able to incrementally learn different actions starting with no model. It is able to discover different instances of the same action Performed by different people, and in different viewpoints. In order to validate our approach, we present results on video clips in which roughly, 50 actions were performed by five different people in different viewpoints. Our system performed impressively by correctly, interpreting most actions.
引用
收藏
页码:55 / 63
页数:9
相关论文
共 50 条
[41]   JOINT LEARNING ON THE HIERARCHY REPRESENTATION FOR FINE-GRAINED HUMAN ACTION RECOGNITION [J].
Leong, Mei Chee ;
Tan, Hui Li ;
Zhang, Haosong ;
Li, Liyuan ;
Lin, Feng ;
Lim, Joo Hwee .
2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, :1059-1063
[42]   Learning Attention-Enhanced Spatiotemporal Representation for Action Recognition [J].
Shi, Zhensheng ;
Cao, Liangjie ;
Guan, Cheng ;
Zheng, Haiyong ;
Gu, Zhaorui ;
Yu, Zhibin ;
Zheng, Bing .
IEEE ACCESS, 2020, 8 (08) :16785-16794
[43]   Novel Human Action Recognition in RGB-D Videos Based on Powerful View Invariant Features Technique [J].
Mambou, Sebastien ;
Krejcar, Ondrej ;
Kuca, Kamil ;
Selamat, Ali .
MODERN APPROACHES FOR INTELLIGENT INFORMATION AND DATABASE SYSTEMS, 2018, 769 :343-353
[44]   View-independent representation with frame interpolation method for skeleton-based human action recognition [J].
Jiang, Yingguo ;
Xu, Jun ;
Zhang, Tong .
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2020, 11 (12) :2625-2636
[45]   View-independent representation with frame interpolation method for skeleton-based human action recognition [J].
Yingguo Jiang ;
Jun Xu ;
Tong Zhang .
International Journal of Machine Learning and Cybernetics, 2020, 11 :2625-2636
[46]   A discriminative representation for human action recognition [J].
Yuan, Yuan ;
Zheng, Xiangtao ;
Lu, Xiaoqiang .
PATTERN RECOGNITION, 2016, 59 :88-97
[47]   X-Invariant Contrastive Augmentation and Representation Learning for Semi-Supervised Skeleton-Based Action Recognition [J].
Xu, Binqian ;
Shu, Xiangbo ;
Song, Yan .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 :3852-3867
[48]   Segment differential aggregation representation and supervised compensation learning of ConvNets for human action recognition [J].
Ren, ZiLiang ;
Zhang, QieShi ;
Cheng, Qin ;
Xu, ZhenYu ;
Yuan, Shuai ;
Luo, DeLin .
SCIENCE CHINA-TECHNOLOGICAL SCIENCES, 2024, 67 (01) :197-208
[49]   Segment differential aggregation representation and supervised compensation learning of ConvNets for human action recognition [J].
ZiLiang Ren ;
QieShi Zhang ;
Qin Cheng ;
ZhenYu Xu ;
Shuai Yuan ;
DeLin Luo .
Science China Technological Sciences, 2024, 67 :197-208
[50]   Learning Composite Latent Structures for 3D Human Action Representation and Recognition [J].
Wei, Ping ;
Sun, Hongbin ;
Zheng, Nanning .
IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 21 (09) :2195-2208