PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via Prompting.
Zixin GuoTzu-Jui Julius WangSelen PehlivanAbduljalil RadmanJorma LaaksonenPublished in: SIGIR (2023)
Keyphrases
- cross modal
- weakly supervised
- multi modal
- multimedia retrieval
- object detectors
- image retrieval
- multimedia databases
- superpixels
- object class
- topic models
- visual similarity
- semi supervised
- named entities
- computer vision
- supervised learning
- training set
- natural language
- information retrieval systems
- text mining
- visual features
- text classification
- object detection
- multimedia
- image processing
- search engine