中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
MIFNet: Multiple instances focused temporal action proposal generation

文献类型：期刊论文

作者Wang, Lining2; Yao, Hongxun2; Yang, Haosen1; Wang, Sibo3; Jin, Sheng2
刊名NEUROCOMPUTING
出版日期2023-06-14
卷号538页码:13
关键词Video understanding Temporal action proposal Temporal action detection Contrastive learning Multiple instances
ISSN号0925-2312
DOI10.1016/j.neucom.2023.01.045
英文摘要Temporal action proposal generation (TAPG) serves as a promising solution for video analysis. However, the performance of existing methods is still far from satisfactory for real-world applications. We attribute it to a crucial issue, i.e., hard multiple instances. In this paper, we investigate why this is the case. We discover that when processing multiple instances videos, mainstream approaches always recognize mul-tiple instances as one instance due to boundary ambiguity or ignoring insignificant backgrounds between these instances. To address this problem, we propose a Multiple Instances Focused Network(MIFNet) that improves the quality of action proposals by considering boundary correlations and fusing multi-scale proposals. In particular, we first propose a pure boundary embedding module named Boundary Constraint Module (BCM) for suppressing the generation of hard negatives proposal by evaluating bound-ary correlation. The BCM introduces a boundary contrastive learning strategy that can pull the positive boundary pairs' representation closer and push the negative pairs' representation away. Then, a Proposal Blending Module (PBM) is proposed, which augments the proposal-level representation by mod-eling information among multi-scale proposals so that proposals can be complemented with local details as well as global information. The experimental results on the ActivityNet-v1.3 and THUMOS14 bench-marks demonstrate that MIFNet outperforms the state-of-the-arts.(c) 2023 Published by Elsevier B.V.
资助项目Heilongjiang Province Science Foundation[2020ZX14A02] ; National Key R&D Program of China[2021ZD0110901]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000980065500001
出版者ELSEVIER
源URL[http://119.78.100.204/handle/2XEOYT63/21401]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Yao, Hongxun
作者单位1.Univ Surrey, Guildford, England
2.Harbin Inst Technol, Fac Comp, Harbin, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Lining,Yao, Hongxun,Yang, Haosen,et al. MIFNet: Multiple instances focused temporal action proposal generation[J]. NEUROCOMPUTING,2023,538:13.
APA Wang, Lining,Yao, Hongxun,Yang, Haosen,Wang, Sibo,&Jin, Sheng.(2023).MIFNet: Multiple instances focused temporal action proposal generation.NEUROCOMPUTING,538,13.
MLA Wang, Lining,et al."MIFNet: Multiple instances focused temporal action proposal generation".NEUROCOMPUTING 538(2023):13.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

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。