Event Graph Guided Compositional Spatial--Temporal Reasoning for Video Question Answering

doi:10.1109/TIP.2024.3358726

	Event Graph Guided Compositional Spatial--Temporal Reasoning for Video Question Answering
	Bai, Ziyi 1,2; Wang, Ruiping 1,2; Gao, Difei 1,2; Chen, Xilin 1,2
	2024
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	33 页码:1109-1121
摘要	Video question answering (VideoQA) is challenging since it requires the model to extract and combine multi-level visual concepts from local objects to global actions from complex events for compositional reasoning. Existing works represent the video with fixed-duration clip features that make the model struggle in capturing the crucial concepts in multiple granularities. To overcome this shortcoming, we propose to represent the video with an Event Graph in a hierarchical structure whose nodes correspond to visual concepts of different levels (object, relation, scene and action) and edges indicate their spatial-temporal relationships. We further propose a Hierarchical S patial- Temporal Transformer (HSTT) which takes nodes from the graph as visual input to realize compositional reasoning guided by the event graph. To fully exploit the spatial-temporal context delivered from the graph structure, on the one hand, we encode the nodes in the order of their semantic hierarchy (depth) and occurrence time (breadth) with our improved graph search algorithm; On the other hand, we introduce edge-guided attention to combine the spatial-temporal context among nodes according to their edge connections. HSTT then performs QA by cross-modal interactions guaranteed by the hierarchical correspondence between the multi-level event graph and the cross-level question. Experiments on the recent challenging AGQA and STAR datasets show that the proposed method clearly outperforms the existing VideoQA models by a large margin, including those pre-trained with large-scale external data.
关键词	Visualization Cognition Transformers Semantics Feature extraction Context modeling Task analysis VideoQA video representation transformer spatial-temporal reasoning compositional reasoning
DOI	10.1109/TIP.2024.3358726
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001174109400006
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38787
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Ruiping
作者单位	1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Bai, Ziyi,Wang, Ruiping,Gao, Difei,et al. Event Graph Guided Compositional Spatial--Temporal Reasoning for Video Question Answering[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2024,33:1109-1121.
APA	Bai, Ziyi,Wang, Ruiping,Gao, Difei,&Chen, Xilin.(2024).Event Graph Guided Compositional Spatial--Temporal Reasoning for Video Question Answering.IEEE TRANSACTIONS ON IMAGE PROCESSING,33,1109-1121.
MLA	Bai, Ziyi,et al."Event Graph Guided Compositional Spatial--Temporal Reasoning for Video Question Answering".IEEE TRANSACTIONS ON IMAGE PROCESSING 33(2024):1109-1121.