Jointly social grouping and identification in visual dynamics with causality-induced hierarchical Bayesian model
Journal of Visual Communication and Image Representation(2019)
摘要
•Causality-Induced Hierarchical Bayesian tackles where/when/what interaction happens.•The spatio-temporal learned latent topics aggregate for power of discrimination.•Relative Entropy metric estimates motion dependence formulating interactive group.•The effectiveness and scalability of proposed method are shown in realistic scenario.
更多查看译文
关键词
Group activity detection and recognition,Casual context,Granger casual topic model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要