Nicola Fanelli

12 papers A 2Journal 5Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Art2Mus: Artwork-to-Music Generation via Visual Conditioning and Large-Scale Cross-Modal Alignment.
CoRR
Ivan Rinaldi, Matteo Mendula, Nicola Fanelli, Florence Levé, Matteo Testi, Giovanna Castellano, Gennaro Vessio
2025 J jnl
ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval.
CoRR
Nicola Fanelli, Gennaro Vessio, Giovanna Castellano
2025 — conf
Generative AI across modalities: insights from our research on domain-aware content generation.
Ital-IA
Giovanna Castellano, Emanuele Colonna, Nicola Fanelli, Lucrezia Laraspata, Ivan Rinaldi, Alberto G. Valerio, Gennaro Vessio
2025 A conf
I Dream My Painting: Connecting MLLMs and Diffusion Models via Prompt Generation for Text-Guided Multi-Mask Inpainting.
WACV
Nicola Fanelli, Gennaro Vessio, Giovanna Castellano
2025 A conf
Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts.
ECAI
Pasquale De Marinis, Nicola Fanelli, Raffaele Scaringi, Emanuele Colonna, Giuseppe Fiameni, Gennaro Vessio, Giovanna Castellano
2025 — conf
Multimodal Artwork Topic Modeling via Fine-Tuned Clip and Knowledge-Driven Prompts.
MLSP
Raffaele Scaringi, Giovanni Stea, Nicola Fanelli, Gennaro Vessio, Giovanna Castellano
2025 — conf
Unveiling Visual Features in Artwork Classification: Towards Explainable Vision Transformers in the Arts.
ICIAP (Workshops 1)
Raffaele Scaringi, Nicola Fanelli, Gennaro Vessio, Giovanna Castellano
2024 — conf
Art2Mus: Bridging Visual Arts and Music Through Cross-Modal Generation.
ECCV Workshops (5)
Ivan Rinaldi, Nicola Fanelli, Giovanna Castellano, Gennaro Vessio
2024 J jnl
Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation.
CoRR
Ivan Rinaldi, Nicola Fanelli, Giovanna Castellano, Gennaro Vessio
2024 J jnl
I Dream My Painting: Connecting MLLMs and Diffusion Models via Prompt Generation for Text-Guided Multi-Mask Inpainting.
CoRR
Nicola Fanelli, Gennaro Vessio, Giovanna Castellano
2024 J jnl
Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts.
CoRR
Pasquale De Marinis, Nicola Fanelli, Raffaele Scaringi, Emanuele Colonna, Giuseppe Fiameni, Gennaro Vessio, Giovanna Castellano
2023 — conf
Exploring the Synergy Between Vision-Language Pretraining and ChatGPT for Artwork Captioning: A Preliminary Study.
ICIAP Workshops (2)
Giovanna Castellano, Nicola Fanelli, Raffaele Scaringi, Gennaro Vessio