Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding.
Erica K. ShimomotoEdison Marrese-TaylorHiroya TakamuraIchiro KobayashiHideki NakayamaYusuke MiyaoPublished in: CoRR (2022)
Keyphrases
- language model
- pre trained
- language modeling
- probabilistic model
- speech recognition
- document retrieval
- statistical language models
- n gram
- information retrieval
- language modelling
- video sequences
- spatial and temporal
- video data
- smoothing methods
- retrieval model
- test collection
- training data
- query expansion
- multimedia
- training examples
- neural network
- image classification
- information retrieval systems
- feature vectors
- video retrieval
- document ranking
- image sequences
- decision trees
- machine learning