DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models.
Zongxin YangGuikun ChenXiaodi LiWenguan WangYi YangPublished in: CoRR (2024)
Keyphrases
- language model
- dynamic scenes
- language modeling
- multi view
- n gram
- document retrieval
- space time
- static scenes
- information retrieval
- probabilistic model
- language modelling
- speech recognition
- video sequences
- query expansion
- moving objects
- statistical language models
- retrieval model
- multiple views
- test collection
- frame rate
- motion segmentation
- smoothing methods
- mixture model
- pseudo relevance feedback
- background subtraction
- language models for information retrieval
- relevance model
- generative model
- information retrieval systems
- viewpoint
- three dimensional
- decision trees