Spatio-Temporal Graph-based Semantic Compositional Network for Video Captioning.
Shun LiZefan ZhangYi JiYing LiChunping LiuPublished in: IJCNN (2022)
Keyphrases
- spatio temporal
- spatial and temporal
- spatial temporal
- space time
- semantic concepts
- network structure
- human actions
- complex networks
- network model
- video event
- real time
- multimedia
- video sequences
- semantic web
- video delivery
- video annotation
- spreading activation
- computer networks
- temporal segmentation
- network traffic
- spatial and temporal relationships
- neural network
- action recognition
- video data
- high level
- peer to peer
- natural language
- wireless sensor networks
- spatio temporally
- social networks
- computer vision
- temporal context
- image sequences
- spatio temporal data
- visual concepts
- moving objects
- domain ontology
- graph model
- video analysis
- video retrieval
- bit rate
- key frames
- event detection
- human activities
- spatial data