Linguistically-aware attention for reducing the semantic gap in vision-language tasks.
Gouthaman KVAthira M. NambiarKancheti Sai SrinivasAnurag MittalPublished in: Pattern Recognit. (2021)
Keyphrases
- semantic gap
- video retrieval
- low level
- low level features
- image content
- semantic information
- visual content
- visual features
- high level semantics
- multimedia databases
- computer vision
- natural language
- semantic concepts
- image annotation
- image classification
- data processing
- key frames
- image understanding
- information extraction
- multiscale
- machine learning