Long Short-Term Relation Transformer With Global Gating for Video Captioning

doi:10.1109/TIP.2022.3158546

	Long Short-Term Relation Transformer With Global Gating for Video Captioning
	Li, Liang 1; Gao, Xingyu 2; Deng, Jincan 3; Tu, Yunbin 4; Zha, Zheng-Jun 5; Huang, Qingming 1,6
	2022
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	31 页码:2726-2738
摘要	Video captioning aims to generate a natural language sentence to describe the main content of a video. Since there are multiple objects in videos, taking full exploration of the spatial and temporal relationships among them is crucial for this task. The previous methods wrap the detected objects as input sequences, and leverage vanilla self-attention or graph neural network to reason about visual relations. This cannot make full use of the spatial and temporal nature of a video, and suffers from the problems of redundant connections, over-smoothing, and relation ambiguity. In order to address the above problems, in this paper we construct a long short-term graph (LSTG) that simultaneously captures short-term spatial semantic relations and long-term transformation dependencies. Further, to perform relational reasoning over the LSTG, we design a global gated graph reasoning module (G3RM), which introduces a global gating based on global context to control information propagation between objects and alleviate relation ambiguity. Finally, by introducing G3RM into Transformer instead of self-attention, we propose the long short-term relation transformer (LSRT) to fully mine objects' relations for caption generation. Experiments on MSVD and MSR-VTT datasets show that the LSRT achieves superior performance compared with state-of-the-art methods. The visualization results indicate that our method alleviates problem of over-smoothing and strengthens the ability of relational reasoning.
关键词	Transformers Cognition Visualization Feature extraction Decoding Task analysis Semantics Video captioning relational reasoning long short-term graph transformer
DOI	10.1109/TIP.2022.3158546
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018AAA0102003] ; National Natural Science Foundation of China[61771457] ; National Natural Science Foundation of China[61702491] ; Youth Innovation Promotion Association of Chinese Academy of Sciences[2020108] ; China Computer Federation (CCF)-Baidu Open Fund[2021PP15002000]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000776079300006
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：43[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/2XEOYT63/18917
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Gao, Xingyu
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Microelect, Beijing 100029, Peoples R China 3.Kuaishou Technol, Beijing 100084, Peoples R China 4.Kunming Univ Sci & Technol, Kunming 650506, Yunnan, Peoples R China 5.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230052, Peoples R China 6.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China
推荐引用方式 GB/T 7714	Li, Liang,Gao, Xingyu,Deng, Jincan,et al. Long Short-Term Relation Transformer With Global Gating for Video Captioning[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2022,31:2726-2738.
APA	Li, Liang,Gao, Xingyu,Deng, Jincan,Tu, Yunbin,Zha, Zheng-Jun,&Huang, Qingming.(2022).Long Short-Term Relation Transformer With Global Gating for Video Captioning.IEEE TRANSACTIONS ON IMAGE PROCESSING,31,2726-2738.
MLA	Li, Liang,et al."Long Short-Term Relation Transformer With Global Gating for Video Captioning".IEEE TRANSACTIONS ON IMAGE PROCESSING 31(2022):2726-2738.