Adaptive Spatio-Temporal Graph Enhanced Vision-Language Representation for Video QA.
Weike JinZhou ZhaoXiaochun CaoJieming ZhuXiuqiang HeYueting ZhuangPublished in: IEEE Trans. Image Process. (2021)
Keyphrases
- spatio temporal
- video representation
- graph representation
- temporal domain
- spatial and temporal
- spatial temporal
- space time
- temporal structure
- question answering
- computer vision
- real time
- representation language
- conceptual graphs
- human actions
- spatio temporally
- graphical representation
- video streams
- natural language
- open domain
- temporal segmentation
- video sequences
- video analysis
- programming language
- video frames
- video content
- image sequences
- graph structures
- vision system
- video database
- graph structure
- moving objects
- spatio temporal data
- relational structures
- graph mining
- graph theory
- language learning
- random walk
- dynamic textures
- graph model
- temporal consistency
- video surveillance
- graph matching
- multimedia