VIDEO ACTION RECOGNITION WITH SPATIO-TEMPORAL GRAPH EMBEDDING AND SPLINE MODELING

被引：7
|
作者：
Yuan, Yin [1 ]
Zheng, Haomian [1 ]
Li, Zhu [1 ]
Zhang, David [1 ]
机构：
[1] Hong Kong Polytech Univ, Dept Comp, Kowloon, Hong Kong, Peoples R China
来源：
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2010年
关键词：
Appearance modeling; Graph Embedding; Spline Modeling; Video Event Analysis;
D O I：
10.1109/ICASSP.2010.5496275
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
In recent years, video analysis and event recognition are becoming a popular research topic with wide applications in surveillance and security. In this paper, we proposed a video action appearance modeling based on spatio-temporal graph embedding and video action recognition based on video luminance field trajectory spline modeling and aligned matching. Graphs are computed from spline re-sampling of training video data set. Matching is achieved from minimizing the average projection distance between query clips and training groups. Simulation with the Cambridge hand gesture data set demonstrates the effectiveness of the proposed solution.
引用
收藏
页码：2422 / 2425
页数：4
相关论文
共 50 条
  • [21] Video action detection by learning graph-based spatio-temporal interactions
    Tomei, Matteo
    Baraldi, Lorenzo
    Calderara, Simone
    Bronzin, Simone
    Cucchiara, Rita
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2021, 206
  • [22] Action recognition for sports video analysis using part-attention spatio-temporal graph convolutional network
    Liu, Jiatong
    Che, Yanli
    JOURNAL OF ELECTRONIC IMAGING, 2021, 30 (03)
  • [23] Human action recognition based on graph-embedded spatio-temporal subspace
    Tseng, Chien-Chung
    Chen, Ju-Chin
    Fang, Ching-Hsien
    Lien, Jenn-Jier James
    PATTERN RECOGNITION, 2012, 45 (10) : 3611 - 3624
  • [24] Action Recognition Based on Person-Object Relationship Spatio-Temporal Graph
    Wang, Tianxiao
    Liu, Jun
    PROCEEDINGS OF 2022 THE 6TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND SOFT COMPUTING, ICMLSC 20222, 2022, : 105 - 110
  • [25] Spatio-Temporal Fusion for Human Action Recognition via Joint Trajectory Graph
    Zheng, Yaolin
    Huang, Hongbo
    Wang, Xiuying
    Yan, Xiaoxu
    Xu, Longfei
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 7, 2024, : 7579 - 7587
  • [26] Spatio-Temporal Pyramid Graph Convolutions for Human Action Recognition and Postural Assessment
    Parsa, Behnoosh
    Narayanan, Athma
    Dariush, Behzad
    2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2020, : 1069 - 1079
  • [27] Modeling spatio-temporal layout with Lie Algebrized Gaussians for action recognition
    Chen, Meng
    Gong, Liyu
    Wang, Tianjiang
    Liu, Fang
    Feng, Qi
    MULTIMEDIA TOOLS AND APPLICATIONS, 2016, 75 (17) : 10335 - 10355
  • [28] Modeling spatio-temporal layout with Lie Algebrized Gaussians for action recognition
    Meng Chen
    Liyu Gong
    Tianjiang Wang
    Fang Liu
    Qi Feng
    Multimedia Tools and Applications, 2016, 75 : 10335 - 10355
  • [29] Spatio-temporal Relation Modeling for Few-shot Action Recognition
    Thatipelli, Anirudh
    Narayan, Sanath
    Khan, Salman
    Anwer, Rao Muhammad
    Khan, Fahad Shahbaz
    Ghanem, Bernard
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 19926 - 19935
  • [30] Silhouette analysis for human action recognition based on maximum spatio-temporal dissimilarity embedding
    Jian Cheng
    Haijun Liu
    Hongsheng Li
    Machine Vision and Applications, 2014, 25 : 1007 - 1018
12345