Discriminative Action Recognition using Supervised Latent Topic Model

摘要：

　　We present a discriminative learning method for human action recognition from video sequences.Our model combines a bag-of-words component with supervised latent topic models.The supervised latent Dirichlet allocation (sLDA) topic model, which employs discriminative learning using labeled data under a generative framework, is introduced to discover the latent topic structure which is most relevant to action categorization.We test our algorithm on two challenging datasets.Experimental results demonstrate the effectiveness of our algorithm.

关键词： action recognition topic model discriminative learning

作者: Zou Huan-xin Sun Hao Ji Ke-feng

作者单位: School of Electronic Science and Engineering,National University of Defense Technology,Changsha 410073,China

会议类型: 国际会议

会议名称: the 3nd International Conference on Digital Manufacturing & Automation (第三届数字制造与自动化国际会议(ICDMA 2012))

会议地点: 桂林

会议语种:英文

页码: 1125-1128

在线出版日期: 2012-08-01（万方平台首次上网日期，不代表论文的发表时间）