Diffexplainer: Towards Cross-modal Global Explanations with Diffusion Models.
Matteo PennisiGiovanni BellittoSimone PalazzoMubarak ShahConcetto SpampinatoPublished in: CoRR (2024)
Keyphrases
- cross modal
- diffusion models
- multi modal
- diffusion model
- information diffusion
- image retrieval
- multimedia retrieval
- visual similarity
- viral marketing
- visual data
- information retrieval
- visual recognition
- influence maximization
- visual features
- high dimensional
- social networks
- diffusion process
- multimedia databases
- natural images
- search engine