VirtuWander: Enhancing Multi-modal Interaction for Virtual Tour Guidance through Large Language Models.
Zhan WangLin-Ping YuanLiangwei WangBingchuan JiangWei ZengPublished in: CoRR (2024)
Keyphrases
- multi modal
- language model
- language modeling
- n gram
- probabilistic model
- query expansion
- document retrieval
- information retrieval
- language modelling
- speech recognition
- multi modality
- retrieval model
- test collection
- statistical language models
- audio visual
- document ranking
- language models for information retrieval
- high dimensional
- cross modal
- smoothing methods
- context sensitive
- video search
- pseudo relevance feedback
- image annotation
- statistical language modeling
- natural language processing