M2HF: Multi-level Multi-modal Hybrid Fusion for Text-Video Retrieval.
Shuo LiuWeize QuanMing ZhouSihong ChenJian KangZhe ZhaoChen ChenDong-Ming YanPublished in: CoRR (2022)
Keyphrases
- multi modal
- video retrieval
- video search
- multi modality
- concept based video retrieval
- video collections
- video database
- fusing multiple
- visual content
- content based retrieval
- multiple modalities
- semantic gap
- video content
- single modality
- key frames
- video data
- video shots
- image annotation
- retrieval systems
- audio visual
- concept detection
- high dimensional
- broadcast news
- video clips
- semantic concepts
- computer vision
- image database
- text retrieval
- three dimensional
- uni modal
- multimedia