Multimodal Language Models for Domain-Specific Procedural Video Summarization.
Nafisa HussainPublished in: CoRR (2024)
Keyphrases
- language model
- video summarization
- domain specific
- audio visual
- multi modal
- language modeling
- event detection
- probabilistic model
- video content
- n gram
- information retrieval
- visual information
- query expansion
- video data
- retrieval model
- smoothing methods
- key frames
- video sequences
- visual data
- test collection
- video retrieval
- mixture model
- surveillance videos
- language models for information retrieval
- multimedia
- relevance model
- video surveillance
- low level features
- computer vision