The Community for Technology Leaders
2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) (2014)
Chengdu, China
July 14, 2014 to July 18, 2014
ISSN: 1945-7871
ISBN: 978-1-4799-4717-1
pp: 1-6
Lei Wang , Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, China
Jun Wu , Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, China
Zhimin Zhou , Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, China
Yuncai Liu , Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, China
Xu Zhao , Shanghai Jiao Tong University, Institute of Image Processing and Pattern Recognition, China
ABSTRACT
Visually perceiving human motion at semantic level is an important however challenging problem in multimedia area. In this work, we propose a novel approach to map the low-level responses from visual detection to semantically sensitive description to human actions. The feature map is triggered by the output of deformable part model detection, in which the critical information about body parts configuration is contained implicitly under the specific human actions. We map the filter responses of the detectors to an effective feature description, which encodes the position and appearance information of the root and every body parts simultaneously. Statistically, the obtained feature map captures the significance of relative configuration of body parts, therefore is robust to the false detections occurred in the individual part detectors. We conduct comprehensive experiments and the results show that the method generates discriminative action features and achieves remarkable performance in most of the cases.
INDEX TERMS
Accuracy, Feature extraction, YouTube, Vectors, Detectors, Visualization, Deformable models
CITATION

Lei Wang, Jun Wu, Zhimin Zhou, Y. Liu and X. Zhao, "Recognition by detection: Perceiving human motion through part-configured feature maps," 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), Chengdu, China, 2014, pp. 1-6.
doi:10.1109/ICMEW.2014.6890599
97 ms
(Ver 3.3 (11022016))