Leveraging Weighted Cross-Graph Attention for Visual and Semantic Enhanced Video Captioning Network.
Deepali VermaArya HaldarTanima DuttaPublished in: AAAI (2023)
Keyphrases
- weighted graph
- content based video retrieval
- semantic concepts
- visual features
- graph model
- visual analysis
- graphical representation
- selective attention
- video data
- edge weights
- visual cues
- visual data
- video sequences
- semantic content
- video frames
- visual saliency
- multimedia
- video streams
- multimedia data
- high level
- graph matching
- small world
- visual information
- visual concepts
- network structure
- video database
- video analysis
- graph structure
- clustering coefficient
- video content
- video clips
- natural language
- low level
- video search
- path length
- wireless sensor networks
- semantic labels
- real time
- semantic information
- complex networks
- graph mining
- graph theory
- video retrieval