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 |
DOI | 10.1016/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。