Differentiate Visual Features with Guidance Signals for Video Captioning.
Yifan YangXiaoqiang LuPublished in: CCRIS (2022)
Keyphrases
- visual features
- key frames
- semantic concepts
- video shots
- visual data
- human actions
- visual information
- content based video retrieval
- visual content
- motion features
- image retrieval
- image classification
- low level features
- video database
- video sequences
- video data
- keywords
- low level
- image search
- image annotation
- semantic gap
- visual appearance
- image collections
- video streams
- video content
- multimedia
- video retrieval
- audio features
- bridge the semantic gap
- video clips
- web images
- saliency map
- search engine
- bag of features
- visual patterns
- video frames
- computer vision
- video analysis
- visual concepts
- multimedia documents
- visual similarity
- relevance feedback
- high level
- visual properties
- image processing