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. 紫东太初大模型研究中心
  5. 图像与视频分析团队
Question-Guided Erasing-Based Spatiotemporal Attention Learning for Video Question Answering

文献类型：期刊论文

作者Liu, Fei2,3; Liu, Jing2,3; Hong, Richang1; Lu, Hanqing2,3
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2021-08-30
页码13
ISSN号2162-237X
关键词Spatiotemporal phenomena Measurement Visualization Knowledge discovery Task analysis Cognition Semantics Erasing mechanism metric learning spatiotemporal attention video question answering (VideoQA)
DOI10.1109/TNNLS.2021.3105280
通讯作者Liu, Jing(jliu@nlpr.ia.ac.cn)
英文摘要Spatiotemporal attention learning for video question answering (VideoQA) has always been a challenging task, where existing approaches treat the attention parts and the nonattention parts in isolation. In this work, we propose to enforce the correlation between the attention parts and the nonattention parts as a distance constraint for discriminative spatiotemporal attention learning. Specifically, we first introduce a novel attention-guided erasing mechanism in the traditional spatiotemporal attention to obtain multiple aggregated attention features and nonattention features and then learn to separate the attention and the nonattention features with an appropriate distance. The distance constraint is enforced by a metric learning loss, without increasing the inference complexity. In this way, the model can learn to produce more discriminative spatiotemporal attention distribution on videos, thus enabling more accurate question answering. In order to incorporate the multiscale spatiotemporal information that is beneficial for video understanding, we additionally develop a pyramid variant on basis of the proposed approach. Comprehensive ablation experiments are conducted to validate the effectiveness of our approach, and state-of-the-art performance is achieved on several widely used datasets for VideoQA.
WOS关键词IMAGE SIMILARITY
资助项目National Key Research and Development Program of China[2020AAA0106400] ; National Natural Science Foundation of China[61922086] ; National Natural Science Foundation of China[61872366]
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000733489300001
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/47028]  
专题自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者Liu, Jing
作者单位1.Hefei Univ Technol, Sch Comp & Informat, Hefei 230000, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Fei,Liu, Jing,Hong, Richang,et al. Question-Guided Erasing-Based Spatiotemporal Attention Learning for Video Question Answering[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021:13.
APA Liu, Fei,Liu, Jing,Hong, Richang,&Lu, Hanqing.(2021).Question-Guided Erasing-Based Spatiotemporal Attention Learning for Video Question Answering.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,13.
MLA Liu, Fei,et al."Question-Guided Erasing-Based Spatiotemporal Attention Learning for Video Question Answering".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021):13.

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。