Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding.
Erica Kido ShimomotoEdison Marrese-TaylorHiroya TakamuraIchiro KobayashiHideki NakayamaYusuke MiyaoPublished in: ACL (Findings) (2023)
Keyphrases
- language model
- pre trained
- language modeling
- n gram
- speech recognition
- document retrieval
- language modelling
- spatial and temporal
- probabilistic model
- statistical language models
- retrieval model
- information retrieval
- query expansion
- bayesian networks
- training data
- relevance model
- video data
- training examples
- test collection
- document ranking
- multimedia
- control signals
- data points
- learning process
- computer vision