Distilling Vision-Language Models on Millions of Videos.
Yue ZhaoLong ZhaoXingyi ZhouJialin WuChun-Te ChuHui MiaoFlorian SchroffHartwig AdamTing LiuBoqing GongPhilipp KrähenbühlLiangzhe YuanPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- document retrieval
- computer vision
- information retrieval
- language modelling
- query expansion
- video sequences
- test collection
- retrieval model
- video frames
- query terms
- speech recognition
- video content
- context sensitive
- smoothing methods
- ad hoc information retrieval
- language models for information retrieval
- vector space model
- document ranking
- video data
- retrieval effectiveness
- recommender systems
- pseudo relevance feedback
- relevance model
- feature selection
- document length
- okapi bm