Can I read What Can We Learn about Motion Videos from Still Images? on EtoBox?

What Can We Learn about Motion Videos from Still Images? by Jianguang Zhang; Yahong Han; Jinhui Tang; Qinghua Hu; Jianmin Jiang is a scholarly article available to read on EtoBox.

What is What Can We Learn about Motion Videos from Still Images? about?

Human action recognition from motion videos plays an important role in multimedia analysis. Different from the temporal cues of action series in motion videos, the motion tendency can also be revealed from the still images or key frames. Thus, if the action knowledge in related still images can be well adapted to the target motion videos, we would have a great chance to improve the performance of video action recognition. In this paper, we propose a framework of Still-to-Motion Adaptation (SMA) for human action recognition. Common visual features are extracted both from the related images and target videos' key frames, by which the gap between still images and videos are bridged. Meanwhile, to utilize the un-labeled training videos in target domain, we incorporate a semi-supervised process into our framework. By minimizing the difference of action prediction from still features and motion features, we formulate the still-tomotion adaptation into a joint optimization process. Experiments successfully demonstrate the effectiveness of the proposed framework and show the better performance of action recognition compared with the state-of-the-art methods. We also analyze the impact on t

Author

Jianguang Zhang; Yahong Han; Jinhui Tang; Qinghua Hu; Jianmin Jiang

Publisher

ACM

Published

2014

Language

EN