Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models.
Jeonghwan KimHeng JiPublished in: CoRR (2024)
Keyphrases
- fine grained
- language model
- visual concepts
- language modeling
- coarse grained
- probabilistic model
- n gram
- object recognition
- query expansion
- information retrieval
- test collection
- computer vision
- retrieval model
- access control
- relevance model
- action recognition
- query terms
- machine learning
- feature extraction
- co occurrence
- image content
- visual information
- image annotation
- object categories
- image understanding
- semantic concepts
- image collections
- information retrieval systems