HAIR: Hierarchical Visual-Semantic Relational Reasoning for Video Question Answering | |
Liu, Fei1,2; Liu, Jing1,2; Wang, Weining2; Lu, Hanqing1,2 | |
2021 | |
会议日期 | 2021-10 |
会议地点 | 线上 |
英文摘要 | Relational reasoning is at the heart of video question answering. However, existing approaches suffer from several common limitations: (1) they only focus on either object-level or frame-level relational reasoning, and fail to integrate the both; and (2) they neglect to leverage semantic knowledge for relational reasoning. In this work, we propose a Hierarchical VisuAl-Semantic RelatIonal Reasoning (HAIR) framework to address these limitations. Specifically, we present a novel graph memory mechanism to perform relational reasoning, and further develop two types of graph memory: a) visual graph memory that leverages visual information of video for relational reasoning; b) semantic graph memory that is specifically designed to explicitly leverage semantic knowledge contained in the classes and attributes of video objects, and perform relational reasoning in the semantic space. Taking advantage of both graph memory mechanisms, we build a hierarchical framework to enable visual-semantic relational reasoning from object level to frame level. Experiments on four challenging benchmark datasets show that the proposed framework leads to state-of-the-art performance, with fewer parameters and faster inference speed. Besides, our approach also shows superior performance on other video+language task. |
会议录出版者 | IEEE |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48674] |
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.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Liu, Fei,Liu, Jing,Wang, Weining,et al. HAIR: Hierarchical Visual-Semantic Relational Reasoning for Video Question Answering[C]. 见:. 线上. 2021-10. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论