Scaling Up Video Summarization Pretraining with Large Language Models.
Dawit Mureja ArgawSeunghyun YoonFabian Caba HeilbronHanieh DeilamsalehyTrung BuiZhaowen WangFranck DernoncourtJoon Son ChungPublished in: CoRR (2024)
Keyphrases
- language model
- video summarization
- language modeling
- audio visual
- video content
- event detection
- retrieval model
- probabilistic model
- information retrieval
- query expansion
- n gram
- video summaries
- video data
- mixture model
- surveillance videos
- key frames
- test collection
- video retrieval
- video sequences
- video frames
- multi modal
- low level features
- real time
- co occurrence
- image classification
- smoothing methods
- relevance model
- natural language processing
- generative model
- higher level
- visual features