Fused GRU with semantic-temporal attention for video captioning.
Lianli GaoXuanhan WangJingkuan SongYang LiuPublished in: Neurocomputing (2020)
Keyphrases
- spatial and temporal
- temporal information
- temporal consistency
- space time
- spatial temporal
- video data
- temporal correlation
- video sequences
- temporal coherence
- spatio temporal
- video frames
- temporal structure
- semantic concepts
- temporal domain
- video event
- temporal analysis
- video content
- multimedia
- temporal relationships
- data fusion
- temporal data
- temporal resolution
- spatial and temporal relationships
- video streams
- natural language
- video analysis
- semantic similarity
- semantic content
- sports video
- semantic video retrieval
- temporal segmentation
- semantic information
- visual attention
- semantic video
- temporal continuity
- semantic search
- semantic annotation
- dynamic scenes
- video database
- domain ontology
- high level
- semantic web
- temporal order
- spatio temporally
- content based video retrieval
- key frames
- multimedia data
- video annotation
- event recognition
- dynamic textures
- semantic network
- real time
- temporal constraints