Video Captioning Based on Channel Soft Attention and Semantic Reconstructor.
Zhou LeiYiyong HuangPublished in: Future Internet (2021)
Keyphrases
- video sequences
- video event
- semantic concepts
- multimedia
- video streams
- video data
- natural language
- video content
- video clips
- multi channel
- semantic web
- semantic video
- sports video
- video database
- video analysis
- space time
- video frames
- real time
- semantic labels
- semantic search
- semantic similarity
- content based video retrieval
- visual attention
- audio visual content
- channel conditions
- channel bandwidth
- video annotation
- low level features
- event detection
- human activities
- motion estimation
- low level
- high level