µFlow Accepted at ECCV 2026
Our paper has been accepted at ECCV 2026.
µFlow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors
Orazio Pontorno, …
The Image Processing Laboratory is part of the Department of Mathematics and Computer Science of the University of Catania, Italy. IPLAB’s research focuses in the areas of Image Processing, Computer Vision, Machine Learning and Computer Graphics. The main scientific activities of IPLAB are related to: Image and Video Understanding, and Enhancement, First Person (Egocentric) Vision, Medical Imaging, Archeomatica and Cultural Heritage, Multimedia Forensics, Assistive Technologies.
Interests
- Image Processing
- Computer Vision
- Machine Learning
EgoVis Distinguished Paper Award 2024/2025
Our papers Differentiable Task Graph Learning (NeurIPS 2024) and Ego-Exo4D (CVPR 2024) received the EgoVis Distinguished Paper Award 2024/2025, …
Task Graph Maximum Likelihood Estimation Accepted at TPAMI
Our paper Task Graph Maximum Likelihood Estimation for Procedural Activity Understanding in Egocentric Videos by Luigi Seminara, Giovanni Maria …
Integrating Affordances and Attention Models Accepted at TPAMI
Our paper Integrating Affordances and Attention models for Short-Term Object Interaction Anticipation by Lorenzo Mur-Labadia, Ruben Martinez-Cantin, …
ViterbiPlanNet Accepted at CVPR 2026
One paper has been accepted at CVPR 2026.
ViterbiPlanNet: Injecting Procedural Knowledge via Differentiable Viterbi for Planning in Instructional …
IEEE Access
We are thrilled to announce that our paper “Attractor-Aware Hyperbolic Lipschitz-Constrained Reinforcement Learning for FX Market: LLM-Structured …
MetroXRAINE 2025
From October 22 to 24, Massimo Orazio Spata have attended MetroXRAINE 2025 IEEE Conference in Ancona, where I presented with an oral two research …
IEEE/CVF WACV (Winter Conference on Application of Computer Vision) 2026
Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis’ accepted at IEEE/CVF WACV (Winter Conference on Application of …
EURASIP Journal on Information Security
CNNMC: A Convolutional Neural Network with Monte Carlo Dropout for Speaker Recognition. Authors: Massimo Orazio Spata, Alessandro Ortis, Georgia …
AAAI 2026
I’m super excited to share that our paper “TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptation” has been accepted at AAAI 2026! …
Simulation Modelling Practice and Theory
I’m very pleased to share that our latest paper, “Multi-agent reinforcement learning and variational inequality models for international trade …
1st AADD‑2025 Challenge: Adversarial Attacks on Deepfake Detectors
We are very proud to announce that the 1st AADD‑2025 Challenge: Adversarial Attacks on Deepfake Detectors, held as a grand challenge at ACM …
1st Deepfake Forensics Workshop: Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media
We are thrilled to announce that the 1st Deepfake Forensics Workshop: Detection, Attribution, Recognition, and Adversarial Challenges in the Era …
Ecological Informatics
Georgia Fargetta, Stefano Anile, Luigi Priano, Massimo Orazio Spata, Alessandro Ortis, and Sebastiano Battiato are …
Plasmare il futuro con l’AI applicata
Happy to contribute next week (28/10/2025) – thanks to Xenia Progetti for inviting me! Prof Giovanni Maria Farinella
IEEE Access
The paper entitled “A Novel Adversarial Gray-Box Attack on DCT-based Face Deepfake Detectors” has been accepted at IEEE Access …