标题:Action Recognition based on Binary Latent Variable Models
作者:Wang, Lei; Zhao, Yanna; Zhao, Xu; Liu, Yuncai
通讯作者:Wang, L
作者机构:[Wang, Lei; Zhao, Yanna] Shangdong Univ, Sch Informat Sci & Engn, Jinan, Peoples R China.; [Zhao, Xu; Liu, Yuncai] Shangdong Univ, Inst Image Proc & 更多
会议名称:2nd IAPR Asian Conference on Pattern Recognition (ACPR)
会议日期:NOV 05-08, 2013
来源:2013 SECOND IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR 2013)
出版年:2013
页码:206-209
DOI:10.1109/ACPR.2013.108
摘要:In this paper, we present an action recognition framework based on binary stochastic latent variables model, Hidden unit Conditional Random Fields(HuCRF). It is a chain structured undirected graphs model with nonlinear dependencies at each frame/segment, contrast to standard log-linear models like CRF. So it is more powerful in sequence modeling tasks like action recognition. The observations of actions can be various and multi-cues. In this paper, we focus on (but not limited to) indoor daily life action surveillance, and the raw data are collected by RGBD sensors(Microsoft Kinect), including RGBD videos and skeleton data. The experiments results on benchmark Datasets show that our model performs well in the action recognition task.
收录类别:CPCI-S
资源类型:会议论文
TOP