Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting.
Syed Talal WasimMuzammal NaseerSalman H. KhanFahad Shahbaz KhanMubarak ShahPublished in: CVPR (2023)
Keyphrases
- video clips
- video segments
- key frames
- video database
- video data
- video streams
- video content
- video frames
- video collections
- video retrieval
- multimedia
- long video
- multimedia documents
- video sequences
- database
- multi modal
- story segmentation
- natural language descriptions
- video search
- compressed video
- news video
- high level
- closed captions
- real time
- multiple modalities
- text detection
- text retrieval
- text mining
- low level features
- temporal information
- video shots
- news stories
- space time