QQ客服 官方微博 反馈留言

	Fast Action Localization Based on Spatio-Temporal Path Search
	Qingtian Wu; Huiwen Guo; Xinyu Wu; Yiming Zhou; Nannan Li
	2017
会议地点	中国北京
英文摘要	In this paper, a method is proposed to search for spatiotemporal path for action localization in unconstrained videos. We mainly focus on two requirements, i.e., accurate human extraction and speeding generation of action proposal. The approach first generates human proposals at the frame level, then scores them based on two complementary parts, i.e., posteriori probability evaluated via a fine-tuned FasterRCNN and template-matching similarity based on the spatiotemporal continuity. Finally, the generation of action proposal is formulated as a Max-Path discovery problem, coupled with dynamic programming to find an optimal path with maximum score. Experiments on UCF-Sports are performed to verify that the proposed method can achieve fast high-quality action proposal and link the missed-detection proposals in successive frames together to form a complete action.
语种	英语
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/11883]
专题	深圳先进技术研究院_集成所
作者单位	2017
推荐引用方式 GB/T 7714	Qingtian Wu,Huiwen Guo,Xinyu Wu,et al. Fast Action Localization Based on Spatio-Temporal Path Search[C]. 见:. 中国北京.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。