TOPA: Extend Large Language Models for Video Understanding via Text-Only Pre-Alignment.
Wei LiHehe FanYongkang WongMohan S. KankanhalliYi YangPublished in: CoRR (2024)
Keyphrases
- language model
- information retrieval
- language modeling
- probabilistic model
- document level
- document retrieval
- query expansion
- text retrieval
- n gram
- video sequences
- video data
- speech recognition
- test collection
- multimedia
- statistical language models
- retrieval model
- smoothing methods
- video frames
- language modelling
- multiword
- video search
- ad hoc information retrieval
- context sensitive
- language models for information retrieval
- query terms
- text mining
- video content
- word level
- video retrieval
- text documents
- vector space model
- relevance model
- document ranking
- translation model
- web documents
- query specific
- key frames
- text categorization
- news video
- sentence level
- question answering
- co occurrence
- web search
- pseudo relevance feedback
- okapi bm
- information extraction
- statistical language modeling
- search engine