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. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICME.2014.6890158 | ICME |
Keywords | DocType | Volume |
still images,human parsing,expressive deep model,pretraining stage,dbn training,human action recognition,deep belief net,pose estimation,fine-tuning stage,body part detection,vision research,human appearance variation,action recognition,image understanding,human pose variation,multimedia research,object detection,human action parsing,computer vision,human layout integration,semantic gap,information fuse,estimation,detectors,image recognition,head,context modeling | Journal | abs/1502.00501 |
ISSN | Citations | PageRank |
1945-7871 | 9 | 0.51 |
References | Authors | |
12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhujin Liang | 1 | 39 | 2.00 |
Xiaolong Wang | 2 | 713 | 39.04 |
Rui Huang | 3 | 1179 | 83.33 |
Liang Lin | 4 | 3007 | 151.07 |