Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks.
Avinash MadasuAnahita BhiwandiwallaVasudev LalPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- query expansion
- probabilistic model
- document retrieval
- statistical language models
- speech recognition
- retrieval model
- language modelling
- computer vision
- video content
- language models for information retrieval
- information retrieval
- test collection
- smoothing methods
- video data
- language model for information retrieval
- vector space model
- relevance model
- query terms
- context sensitive
- multimedia
- video frames
- translation model
- document ranking
- document length
- video sequences
- cross lingual
- ad hoc information retrieval