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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 中科院工业视觉智能装备工程实验室
  5. 精密感知与控制
Class-wise boundary regression by uncertainty in temporal action detection

文献类型：期刊论文

作者Chen, Yunze1,2; Chen, Mengjuan2; Gu, Qingyi2
刊名IET IMAGE PROCESSING
出版日期2022-08-04
页码9
ISSN号1751-9659
DOI10.1049/ipr2.12599
通讯作者Gu, Qingyi(qingyi.gu@ia.ac.cn)
英文摘要Temporal action detection is a crucial aspect of video understanding. It aims to classify the action as well as locate the start and end boundaries of the action in the untrimmed videos. As deep learning is frequently utilized, the accuracy of annotation is crucial to boundary localization. However, it is observed that some annotation instances are ambiguous and the ambiguity varies between categories. To solve the problem above, a Gaussian model is built to estimate the boundary uncertainty for each instance. Based on instance uncertainty, category uncertainty is applied to describe the uncertainty of each category. By combining instance and category uncertainty, the boundaries of the selected proposals are refined and the ranking of candidate proposals is adjusted. Furthermore, overcorrection is avoided for categories with a high level of uncertainty. With the uncertainty approach, state-of-the-art performance is achieved: 57.5% on THUMOS14 (mAP@0.5) and 35.4% on ActivityNet (mAP@Avg).
资助项目Scientific Instrument Developing Project of the Chinese Academy of Sciences[YJKYYQ20200045]
WOS研究方向Computer Science ; Engineering ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:000836034700001
出版者WILEY
资助机构Scientific Instrument Developing Project of the Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/49827]  
专题精密感知与控制研究中心_精密感知与控制
通讯作者Gu, Qingyi
作者单位1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
2.Chinese Acad Sci, Ctr Precis Sensing & Control, Inst Automat, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Yunze,Chen, Mengjuan,Gu, Qingyi. Class-wise boundary regression by uncertainty in temporal action detection[J]. IET IMAGE PROCESSING,2022:9.
APA Chen, Yunze,Chen, Mengjuan,&Gu, Qingyi.(2022).Class-wise boundary regression by uncertainty in temporal action detection.IET IMAGE PROCESSING,9.
MLA Chen, Yunze,et al."Class-wise boundary regression by uncertainty in temporal action detection".IET IMAGE PROCESSING (2022):9.

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。