Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond.
Yongqi LiWenjie WangLeigang QuLiqiang NieWenjie LiTat-Seng ChuaPublished in: ACL (1) (2024)
Keyphrases
- cross modal
- language model
- image retrieval
- image database
- document retrieval
- visual similarity
- retrieval model
- multi modal
- query expansion
- content based retrieval
- test collection
- multimedia retrieval
- language models for information retrieval
- information retrieval
- information retrieval systems
- probabilistic model
- image features
- relevance model
- multimedia databases
- image data
- language modeling
- object recognition
- retrieval systems
- visual data
- relevance feedback
- image collections
- image annotation
- low level features
- image set
- automatic image annotation
- image classification
- n gram
- document collections
- semantic similarity
- vector space
- generative model
- smoothing methods