Collaborative Local-Global Learning for Temporal Action Proposal

doi:10.1145/3466181

	Collaborative Local-Global Learning for Temporal Action Proposal
	Zhu, Yisheng 1; Han, Hu 2; Liu, Guangcan 1; Liu, Qingshan 1
	2021-12-01
发表期刊	ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
ISSN	2157-6904
卷号	12 期号:5 页码:14
摘要	Temporal action proposal generation is an essential and challenging task in video understanding, which aims to locate the temporal intervals that likely contain the actions of interest. Although great progress has been made, the problem is still far from being well solved. In particular, prevalent methods can handle well only the local dependencies (i.e., short-term dependencies) among adjacent frames but are generally powerless in dealing with the global dependencies (i.e., long-term dependencies) between distant frames. To tackle this issue, we propose CLGNet, a novel Collaborative Local-Global Learning Network for temporal action proposal. The majority of CLGNet is an integration of Temporal Convolution Network and Bidirectional Long Short-Term Memory, in which Temporal Convolution Network is responsible for local dependencies while Bidirectional Long Short-Term Memory takes charge of handling the global dependencies. Furthermore, an attention mechanism called the background suppression module is designed to guide our model to focus more on the actions. Extensive experiments on two benchmark datasets, THUMOS'14 and ActivityNet-1.3, show that the proposed method can outperform state-of-the-art methods, demonstrating the strong capability of modeling the actions with varying temporal durations.
关键词	Temporal action proposal generation untrimmed videos long short-term memory attention mechanism
DOI	10.1145/3466181
收录类别	SCI
语种	英语
资助项目	New Generation AI Major Project of Ministry of Science and Technology of China[2018AAA0102501]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems
WOS记录号	WOS:000732997200004
出版者	ASSOC COMPUTING MACHINERY
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/18006
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Guangcan
作者单位	1.Nanjing Univ Infor Mat Sci & Technol, Sch Automat, 219 NingLiu Rd, Nanjing 210000, Jiangsu, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, 6 Kexueyuan South Rd, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Yisheng,Han, Hu,Liu, Guangcan,et al. Collaborative Local-Global Learning for Temporal Action Proposal[J]. ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY,2021,12(5):14.
APA	Zhu, Yisheng,Han, Hu,Liu, Guangcan,&Liu, Qingshan.(2021).Collaborative Local-Global Learning for Temporal Action Proposal.ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY,12(5),14.
MLA	Zhu, Yisheng,et al."Collaborative Local-Global Learning for Temporal Action Proposal".ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY 12.5(2021):14.