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
Hierarchical compositional representations for few-shot action recognition

文献类型：期刊论文

作者Li, Changzhen2,3,4; Zhang, Jie3,4; Wu, Shuzhe1; Jin, Xin1; Shan, Shiguang2,3,4
刊名COMPUTER VISION AND IMAGE UNDERSTANDING
出版日期2024-03-01
卷号240页码:11
关键词Action recognition Few-shot learning Hierarchical compositional representations Body parts EMD distance
ISSN号1077-3142
DOI10.1016/j.cviu.2023.103911
英文摘要Recently action recognition has received more and more attention for its comprehensive and practical applications in intelligent surveillance and human-computer interaction. However, few-shot action recognition has not been well explored and remains challenging because of data scarcity. In this paper, we propose a novel hierarchical compositional representations (HCR) learning approach for few-shot action recognition. Specifically, we divide a complicated action into several sub-actions by carefully designed hierarchical clustering and further decompose the sub-actions into more fine-grained spatially attentional sub-actions (SASactions). Although there exist large differences between base classes and novel classes, they can share similar patterns in sub-actions or SAS-actions. Furthermore, we adopt the Earth Mover's Distance in the transportation problem to measure the similarity between video samples in terms of sub-action representations. It computes the optimal matching flows between sub-actions as distance metric, which is favorable for comparing finegrained patterns. Extensive experiments show our method achieves the state-of-the-art results on HMDB51, UCF101 and Kinetics datasets.
资助项目National Key R&D Program of China[2021YFC3310100] ; National Natural Science Foundation of China[62176251] ; Youth Innovation Promotion Association CAS
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001166488900001
出版者ACADEMIC PRESS INC ELSEVIER SCIENCE
源URL[http://119.78.100.204/handle/2XEOYT63/38842]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhang, Jie
作者单位1.Beijing Huawei Cloud Comp Technol Co Ltd, 3 Xinxi Rd, Beijing 100095, Peoples R China
2.UCAS, Hangzhou Inst Adv Study, Sch Intelligent Sci & Technol, Hangzhou, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Li, Changzhen,Zhang, Jie,Wu, Shuzhe,et al. Hierarchical compositional representations for few-shot action recognition[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2024,240:11.
APA Li, Changzhen,Zhang, Jie,Wu, Shuzhe,Jin, Xin,&Shan, Shiguang.(2024).Hierarchical compositional representations for few-shot action recognition.COMPUTER VISION AND IMAGE UNDERSTANDING,240,11.
MLA Li, Changzhen,et al."Hierarchical compositional representations for few-shot action recognition".COMPUTER VISION AND IMAGE UNDERSTANDING 240(2024):11.

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。