Semantic Scene Difference Detection in Daily Life Patroling by Mobile Robots using Pre-Trained Large-Scale Vision-Language Model.
Yoshiki ObinataKento KawaharazukaNaoaki KanazawaNaoya YamaguchiNaoto TsukamotoIori YanokuraShingo KitagawaKoki ShinjoKei OkadaMasayuki InabaPublished in: CoRR (2023)
Keyphrases
- language model
- daily life
- mobile robot
- pre trained
- language modeling
- n gram
- probabilistic model
- information retrieval
- speech recognition
- query expansion
- activity recognition
- smoothing methods
- training data
- computer vision
- single image
- video sequences
- generative model
- training examples
- small number
- action recognition
- data streams
- bayesian networks