By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting.
Hyungjun YoonBiniyam Aschalew ToleraTaesik GongKimin LeeSung-Ju LeePublished in: CoRR (2024)
Keyphrases
- sensor data
- language model
- language modeling
- sensor networks
- n gram
- document retrieval
- probabilistic model
- sensor measurements
- data streams
- information retrieval
- query expansion
- speech recognition
- language modelling
- statistical language models
- multiple sensors
- context sensitive
- retrieval model
- visual information
- smoothing methods
- health monitoring
- smart environments
- human activities
- test collection
- language model for information retrieval
- raw sensor data
- sensor readings
- relevance model
- visual features
- language models for information retrieval
- translation model
- low level
- ad hoc information retrieval
- query terms
- video search
- vector space model
- monitoring system
- multi modal
- earth observation