An expressive deep model for human action parsing from a single image
Authors:
- 1 July 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
This paper aims at one newly raising task in vision and multimedia research: recognizing human actions from still images. Its main challenges lie in the large variations in human poses and appearances, as well as the lack of temporal motion information. Addressing these problems, we propose to develop an expressive deep model to naturally integrate human layout and surrounding contexts for higher level action understanding from still images. In particular, a Deep Belief Net is trained to fuse information from different noisy sources such as body part detection and object detection. To bridge the semantic gap, we used manually labeled data to greatly improve the effectiveness and efficiency of the pre-training and fine-tuning stages of the DBN training. The resulting framework is shown to be robust to sometimes unreliable inputs (e.g., imprecise detections of human parts and objects), and outperforms the state-of-the-art approaches.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Human Re-identification by Matching Compositional Template with Cluster Sampling2013
- Expanded Parts Model for Human Attribute and Action Recognition in Still Images2013
- Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human PosesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Recognizing human actions from still images with latent poses2010
- Recognizing human actions in still images: a study of bag-of-features and part-based representations2010
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- A stochastic graph grammar for compositional object representation and recognitionPattern Recognition, 2009
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- Pose primitive based human action recognition in videos or still images2008
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006