collaborators

7 papers

cs.CV2025

Semantically Guided Action Anticipation

Anxhelo Diko, Antonino Furnari, Luigi Cinque +1

Unsupervised domain adaptation remains a critical challenge in enabling the knowledge transfer of models across unseen domains. Existing methods struggle to balance the need for do…

cs.LG2025

Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization

Federico Fontana, Anxhelo Diko, Romeo Lanzino +4

The rapid evolution of deepfake generation technologies poses critical challenges for detection systems, as non-continual learning methods demand frequent and expensive retraining.…

cs.CV2025

ReWind: Understanding Long Videos with Instructed Learnable Memory

Anxhelo Diko, Tinghuai Wang, Wassim Swaileh +2

Vision-Language Models (VLMs) are crucial for applications requiring integrated understanding textual and visual information. However, existing VLMs struggle with long videos due t…

cs.LG2024

CycleBNN: Cyclic Precision Training in Binary Neural Networks

Federico Fontana, Romeo Lanzino, Anxhelo Diko +2

This paper works on Binary Neural Networks (BNNs), a promising avenue for efficient deep learning, offering significant reductions in computational overhead and memory footprint to…

cs.CV2024

ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections

Anxhelo Diko, Danilo Avola, Marco Cascio +1

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such feat…

cs.CV2024

Semantically Guided Representation Learning For Action Anticipation

Anxhelo Diko, Danilo Avola, Bardh Prenkaj +2

Action anticipation is the task of forecasting future activity from a partially observed sequence of events. However, this task is exposed to intrinsic future uncertainty and the d…