HPE-CogVLM: New Head Pose Grounding Task Exploration on Vision Language Model.
Yu TianTianqi ShaoTsukasa DemizuXuyang WuHsin-Tai WuPublished in: CoRR (2024)
Keyphrases
- language model
- human pose estimation
- visual focus of attention
- language modeling
- pose estimation
- probabilistic model
- computer vision
- n gram
- document retrieval
- retrieval model
- speech recognition
- query expansion
- information retrieval
- language modelling
- mixture model
- context sensitive
- vector space model
- test collection
- gaussian processes
- ad hoc information retrieval
- language model for information retrieval
- statistical language models
- document length
- document ranking
- d objects
- relevance model
- human pose
- query terms
- smoothing methods
- dependency structure