Semantic and Temporal Contextual Correlation Learning for Weakly-Supervised Temporal Action Localization
文献类型：期刊论文
| 作者 | Fu, Jie1,2; Gao, Junyu1,3 ; Xu, Changsheng1,3,4
|
| 刊名 | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
 |
| 出版日期 | 2023-10-01 |
| 卷号 | 45期号:10页码:12427-12443 |
| ISSN号 | 0162-8828 |
| 关键词 | Weakly-supervised video action localization semantic temporal context correlation learning |
| DOI | 10.1109/TPAMI.2023.3287208 |
| 通讯作者 | Xu, Changsheng(csxu@nlpr.ia.ac.cn) |
| 英文摘要 | Weakly-supervised temporal action localization (WSTAL) aims to automatically identify and localize action instances in untrimmed videos with only video-level labels as supervision. In this task, there exist two challenges: (1) how to accurately discover the action categories in an untrimmed video (what to discover); (2) how to elaborately focus on the integral temporal interval of each action instance (where to focus). Empirically, to discover the action categories, discriminative semantic information should be extracted, while robust temporal contextual information is beneficial for complete action localization. However, most existing WSTAL methods ignore to explicitly and jointly model the semantic and temporal contextual correlation information for the above two challenges. In this article, a Semantic and Temporal Contextual Correlation Learning Network (STCL-Net) with the semantic (SCL) and temporal contextual correlation learning (TCL) modules is proposed, which achieves both accurate action discovery and complete action localization by modeling the semantic and temporal contextual correlation information for each snippet in the inter- and intra-video manners respectively. It is noteworthy that the two proposed modules are both designed in a unified dynamic correlation-embedding paradigm. Extensive experiments are performed on different benchmarks. On all the benchmarks, our proposed method exhibits superior or comparable performance in comparison to the existing state-of-the-art models, especially achieving gains as high as 7.2% in terms of the average mAP on THUMOS-14. In addition, comprehensive ablation studies also verify the effectiveness and robustness of each component in our model. |
| 资助项目 | National Key Research and Development Plan of China ; National Natural Science Foundation of China[2020AAA0106200] ; National Natural Science Foundation of China[62036012] ; National Natural Science Foundation of China[U21B2044] ; National Natural Science Foundation of China[62236008] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[62102415] ; National Natural Science Foundation of China[62072286] ; National Natural Science Foundation of China[62106262] ; Beijing Natural Science Foundation[62002355] ; Open Research Projects of Zhejiang Lab[L201001] ; [2022RC0AB02] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| 出版者 | IEEE COMPUTER SOC |
| WOS记录号 | WOS:001068816800057 |
| 资助机构 | National Key Research and Development Plan of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Open Research Projects of Zhejiang Lab |
| 源URL | [http://ir.ia.ac.cn/handle/173211/53044]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Xu, Changsheng |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Zhengzhou Univ, Zhengzhou 450001, Henan, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 4.Peng Cheng Lab, Shenzhen 518055, Guangdong, Peoples R China |
| 推荐引用方式 GB/T 7714 | Fu, Jie,Gao, Junyu,Xu, Changsheng. Semantic and Temporal Contextual Correlation Learning for Weakly-Supervised Temporal Action Localization[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(10):12427-12443. |
| APA | Fu, Jie,Gao, Junyu,&Xu, Changsheng.(2023).Semantic and Temporal Contextual Correlation Learning for Weakly-Supervised Temporal Action Localization.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(10),12427-12443. |
| MLA | Fu, Jie,et al."Semantic and Temporal Contextual Correlation Learning for Weakly-Supervised Temporal Action Localization".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.10(2023):12427-12443. |
入库方式： OAI收割
来源：自动化研究所
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。