Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank.
Jiaxin WuChong-Wah NgoWing-Kwong ChanPublished in: ICMR (2024)
Keyphrases
- video search
- multiword
- image search
- visual content
- video content
- video retrieval
- multi modal
- semantic content
- visual features
- context sensitive
- semantic concepts
- information retrieval
- image collections
- image retrieval
- image classification
- video shots
- visual concepts
- spatial relationships
- image annotation
- visual information
- semantic information
- video sequences
- multimedia
- feature selection