This is the research I started when I was appointed Assistant Professor, whose three years were funded by the European PON AIM (Attraction and International Mobility) project "Computational Methods for Cultural Heritage".

Understanding visual arts with AI

Visual arts are essential for our societies' cultural, historical, and economic growth. In recent years, a large-scale digitization effort has been made due to technological improvements and the drastic drop in costs, leading to the increasing availability of large digitized artwork collections. This availability, coupled with recent advances in pattern recognition and computer vision, has opened new opportunities for computer science researchers to assist the art community with intelligent tools to analyze and further understand visual arts. Among other benefits, a deeper understanding of visual arts has the potential to make them more accessible to a broader population, both in terms of fruition and creation, thus supporting the spread of culture.

Dataset

Some publications

Rinaldi, I., Fanelli, N., Castellano, G. & Vessio, G. Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation. ECCVW (2024)

arXiv

Castellano, G., Fanelli, N., Scaringi, R. & Vessio, G. Exploring the Synergy Between Vision-Language Pretraining and ChatGPT for Artwork Captioning: A Preliminary Study. FAPER (2023)

ResearchGate

Bianco, T., Castellano, G., Scaringi, R. & Vessio, G. Identifying AI-Generated Art with Deep Learning. CREAI (2023)

open access

Castellano, G. & Vessio, G. A Deep Learning Approach to Clustering Visual Arts. International Journal of Computer Vision (2022)

open access

Castellano, G., Digeno, V., Sansaro, G. & Vessio, G. Leveraging Knowledge Graphs and Deep Learning for automatic art analysis. Knowledge-Based Systems (2022)

open access

Castellano, G. & Vessio, G. Understanding Art with AI: Our Research Experience. AIxIA (2021)

open access

Castellano, G. & Vessio, G. Deep learning approaches to pattern extraction and recognition in paintings and drawings: an overview. Neural Computing and Applications (2021)

open access

Castellano, G., Lella, E. & Vessio, G. Visual link retrieval and knowledge discovery in painting datasets. Multimedia Tools and Applications (2021)

open access

Castellano, G., De Carolis, B., Macchiarulo, N. & Vessio, G. Pepper4Museum: Towards a Human-like Museum Guide. AVI-CH (2020)

open access