Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond.
Yongqi LiWenjie WangLeigang QuLiqiang NieWenjie LiTat-Seng ChuaPublished in: CoRR (2024)
Keyphrases
- cross modal
- language model
- image retrieval
- visual similarity
- image database
- document retrieval
- retrieval model
- test collection
- multi modal
- multimedia retrieval
- information retrieval
- query expansion
- content based retrieval
- language modeling
- multimedia databases
- visual data
- text retrieval
- relevance model
- image data
- visual information
- language models for information retrieval
- image annotation
- smoothing methods
- retrieval systems
- image understanding
- n gram
- document collections
- probabilistic model
- image features
- web images
- object recognition
- visual words
- relevance feedback
- automatic image annotation
- image classification
- visual features
- visual content
- video data
- image search