Attentive Visual Semantic Specialized Network for Video Captioning.
Jesus Perez-MartinBenjamin BustosJorge PérezPublished in: ICPR (2020)
Keyphrases
- content based video retrieval
- video sequences
- visual cues
- video data
- semantic concepts
- key frames
- visual features
- video streams
- semantic web
- semantic labels
- peer to peer
- general purpose
- video frames
- network structure
- multimedia
- video delivery
- video content
- network conditions
- concept detectors
- video search
- semantic search
- video event
- high level
- real time
- natural language
- wireless sensor networks
- complex networks
- video retrieval
- semantic information
- low level
- news video
- neural network
- eye contact
- semantic context
- visual motion
- semantic content
- multimedia data
- visual perception
- video surveillance
- visual data
- video clips