Multi-modal Transformer for Video Retrieval.
Valentin GabeurChen SunKarteek AlahariCordelia SchmidPublished in: CoRR (2020)
Keyphrases
- multi modal
- video retrieval
- video search
- visual content
- semantic gap
- content based retrieval
- video database
- video data
- concept detection
- multi modality
- retrieval systems
- video shots
- video content
- key frames
- video clips
- audio visual
- multiple modalities
- feature extraction
- concept based video retrieval
- semantic concepts
- image retrieval
- high dimensional
- video sequences