Text-Video Retrieval via Variational Multi-Modal Hypergraph Networks.
Qian LiLixin SuJiashu ZhaoLong XiaHengyi CaiSuqi ChengHengzhu TangJunfeng WangDawei YinPublished in: CoRR (2024)
Keyphrases
- multi modal
- video retrieval
- video search
- concept based video retrieval
- video collections
- semantic gap
- multi modality
- visual content
- video data
- retrieval systems
- video database
- audio visual
- content based retrieval
- high dimensional
- information retrieval
- video clips
- image segmentation
- video content
- text retrieval
- multiple modalities
- key frames
- single modality
- uni modal
- computer vision
- image annotation
- video shots
- text mining
- active learning
- video sequences
- broadcast news