Poster: Translating Vision into Words: Advancing Object Recognition with Visual-Language Models.
Haruki YonekuraHamada RizkHirozumi YamaguchiPublished in: MobiSys (2024)
Keyphrases
- language model
- n gram
- object recognition
- computer vision
- language modeling
- document representation
- out of vocabulary
- statistical language modeling
- translation model
- probabilistic model
- multiword
- language modelling
- speech recognition
- retrieval model
- document retrieval
- word error rate
- information retrieval
- test collection
- statistical language models
- visual information
- document level
- bag of words
- query expansion
- context sensitive
- pseudo relevance feedback
- smoothing methods
- visual features
- image understanding
- vector space model
- ad hoc information retrieval
- image features
- query specific
- document ranking
- passage retrieval
- word segmentation
- cross lingual
- text documents
- keywords
- hidden markov models
- language models for information retrieval