Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model.
Shraman PramanickGuangxing HanRui HouSayan NagSer-Nam LimNicolas BallasQifan WangRama ChellappaAmjad AlmahairiPublished in: CoRR (2023)
Keyphrases
- coarse to fine
- language model
- general purpose
- language modeling
- multiscale
- multiresolution
- n gram
- speech recognition
- document retrieval
- probabilistic model
- object detection
- image registration
- query expansion
- information retrieval
- hierarchical segmentation
- retrieval model
- matching scheme
- statistical language models
- smoothing methods
- computer vision
- language modelling
- query terms
- ad hoc information retrieval
- context sensitive
- language model for information retrieval
- mixture model
- translation model
- dynamic programming
- similarity measure
- test collection
- cross lingual
- relevance model
- statistical machine translation
- model selection
- document length
- image processing