7 papers
Grounding Free-Form Instructions for Fashion Complementary Image Generation
Matteo Attimonelli, Claudio Pomo, Alessandro De Bellis +3
Fashion complementary image generation (CIG) aims to create garments that stylistically match a seed item based on user intent, making it a natural multimodal grounding problem whe…
FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matching
Danilo Danese, Angela Lombardi, Matteo Attimonelli +2
Brain Magnetic Resonance Imaging (MRI) plays a central role in studying neurological development, aging, and diseases. One key application is Brain Age Prediction (BAP), which esti…
WaveDiT: Distribution-Aware Wavelet Flow Matching for Efficient 3D Brain MRI Synthesis
Danilo Danese, Angela Lombardi, Giuseppe Fasano +2
Large and demographically balanced datasets are essential for reliable neuroimaging biomarkers. Full-resolution 3D brain MRI synthesis can support data augmentation in this setting…
Do Composed Image Retrieval Benchmarks Require Multimodal Composition?
Matteo Attimonelli, Alessandro De Bellis, Aryo Pradipta Gema +8
Composed Image Retrieval (CIR) is a multimodal retrieval task where a query consists of a reference image and a textual modification, and the goal is to retrieve a target image sat…
Large-scale Benchmarks for Multimodal Recommendation with Ducho
Matteo Attimonelli, Danilo Danese, Angela Di Fazio +3
The common multimodal recommendation pipeline involves (i) extracting multimodal features, (ii) refining their high-level representations to suit the recommendation task, (iii) opt…
Do Recommender Systems Really Leverage Multimodal Content? A Comprehensive Analysis on Multimodal Representations for Recommendation
Claudio Pomo, Matteo Attimonelli, Danilo Danese +2
Multimodal Recommender Systems aim to improve recommendation accuracy by integrating heterogeneous content, such as images and textual metadata. While effective, it remains unclear…