Hierarchical multimodal transformer to summarize videos.
Bin ZhaoMaoguo GongXuelong LiPublished in: Neurocomputing (2022)
Keyphrases
- video sequences
- video frames
- multi modal
- hierarchical clustering
- multimodal interaction
- fuzzy logic
- space time
- video database
- real time
- video content
- video analysis
- key frames
- partial discharge
- video indexing
- hierarchical model
- dynamic scenes
- coarse to fine
- hierarchical structure
- power system
- video data
- expert systems
- data sets