期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 34, 期 3, 页码 601-614出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2011.158
关键词
Action recognition; weakly supervised learning; object detection
资金
- QUAERO
- OSEO
- French State Agency for innovation
- Microsoft/INRIA
- Swiss National Science Foundation
We introduce a weakly supervised approach for learning human actions modeled as interactions between humans and objects. Our approach is human-centric: We first localize a human in the image and then determine the object relevant for the action and its spatial relation with the human. The model is learned automatically from a set of still images annotated only with the action label. Our approach relies on a human detector to initialize the model learning. For robustness to various degrees of visibility, we build a detector that learns to combine a set of existing part detectors. Starting from humans detected in a set of images depicting the action, our approach determines the action object and its spatial relation to the human. Its final output is a probabilistic model of the human-object interaction, i.e., the spatial relation between the human and the object. We present an extensive experimental evaluation on the sports action data set from [1], the PASCAL Action 2010 data set [2], and a new human-object interaction data set.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据