Bridging the Emotional Semantic Gap via Multimodal Relevance Estimation.
Chuan ZhangDaoxin ZhangRuixiu ZhangJiawei LiJianke ZhuPublished in: CoRR (2023)
Keyphrases
- semantic gap
- low level features
- video retrieval
- low level
- image content
- semantic concepts
- visual features
- semantic information
- visual content
- relevance feedback
- image annotation
- multimedia databases
- multi modal
- high level semantics
- higher level
- visual information
- high level
- image collections
- key frames
- information retrieval
- relational databases