RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition.
Ziyu LiuZeyi SunYuhang ZangWei LiPan ZhangXiaoyi DongYuanjun XiongDahua LinJiaqi WangPublished in: CoRR (2024)
Keyphrases
- visual recognition
- image classification
- visual recognition tasks
- object recognition
- ranking algorithm
- latent topic models
- category level
- visual classification
- computer vision
- visual categorization
- information retrieval
- visual features
- feature extraction
- machine learning
- human computer interaction
- scene classification
- high resolution
- three dimensional
- image processing