Computer Vision -- ACCV 2014 - 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised Selected Papers, Part IV
Computer Vision -- ACCV 2014 - 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised Selected Papers, Part IV
复制标题
计算机视觉 - ACCV 2014 - 第 12 届亚洲计算机视觉会议，新加坡，新加坡，2014 年 11 月 1-5 日，修订论文选集，第四部分
DOI：
10.1007/978-3-319-16817-3_15
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Hoai M
中科院分区：
文献类型：
--
作者：
Hoai M
我们研究了在视频中识别人类行为的任务，同时注意镜头和线程编辑结构。目前大多数的动作识别算法都忽略了这种结构，但是这种结构普遍存在于编辑过的电视和电影素材中，为此，我们做了以下贡献：首先，我们引入了一个新的人类动作数据集来研究编辑过的电视素材中人类动作模式的发生/重现;其次，我们提出了将视频合成为相关镜头的线程，去除一些由于镜头边界而导致的不连续性;第三，我们展示了利用视频线程识别人类行为的好处。实验结果表明，使用线程可以提高人体动作检索的准确率。
We study the task of recognizing human actions in video whilst paying attention to the shot and thread editing structure. Most existing action recognition algorithms ignore this structure, but it is generally present in edited TV and film material.To this end, we make the following contributions: first, we introduce a new dataset of human actions to study the occurrence/reoccurrence of patterns of human actions in edited TV material; second, we propose composing a video into threads of related shots, removing some of the discontinuities due to shot boundaries; and third, we show the benefits of utilizing video threads in recognizing human actions. The experiments demonstrate that human action retrieval accuracy can be improved using threads.