Insert title here
    登录 | 注册 | 期刊登录 | 收藏
International Journal of Computer Vision 2013, Vol. 103 (1) :60 -79 doi:10.1007/s11263-012-0594-8 <<-上一篇 下一篇 ->>
Dense Trajectories and Motion Boundary Descriptors for Action;Recognition
Wang, Heng1;Liu, Cheng-Lin1;Klaeser, Alexander2;Schmid, Cordelia2;
Wang, Heng1;Liu, Cheng-Lin1;Klaeser, Alexander2;Schmid, Cordelia2;
全文:     原文
Abstract: This paper introduces a video representation based on dense trajectories and motion boundary descriptors. Trajectories capture the local motion information of the video. A dense representation guarantees a good coverage of foreground motion as well as of the surrounding context. A state-of-the-art optical flow algorithm enables a robust and efficient extraction of dense trajectories. As descriptors we extract features aligned with the trajectories to characterize shape (point coordinates), appearance (histograms of oriented gradients) and motion (histograms of optical flow). Additionally, we introduce a descriptor based on motion boundary histograms (MBH) which rely on differential optical flow. The MBH descriptor shows to consistently outperform other state-of-the-art descriptors, in particular on real-world videos that contain a significant amount of camera motion. We evaluate our video representation in the context of action classification on nine datasets, namely KTH, YouTube, Hollywood2, UCF sports, IXMAS, UIUC, Olympic Sports, UCF50 and HMDB51. On all datasets our approach outperforms current state-of-the-art results.
Insert title here
更多服务: 作者自存档 | 投稿导航 | 全球期刊检索 | 查找审稿人
关于我们 | 隐私申明 | 免责声明 | 意见反馈 | 合作服务
Magsci ©  版权所有
Copyright © 2010 - 2013 Magtech. All Rights Reserved.