Vittorio Murino

Active-Labelling by Adaptive Huber Loss Regression

2016 · arXiv (Cornell University)

This paper addresses the scalar regression problem presenting a solution for optimizing the Huber loss in a general semi-supervised setting, which combines multi-view learning and manifold regularization. To this aim, we propose a principled algorithm …

Predicting Intentions from Motion: The Subject-Adversarial Adaptation Approach

2019 · International Journal of Computer Vision

Abstract This paper aims at investigating the action prediction problem from a pure kinematic perspective. Specifically, we address the problem of recognizing future actions, indeed human intentions, underlying a same initial (and apparently unrelated) motor …

Cleaning Noisy Labels by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation

2022 · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Conventional Unsupervised Domain Adaptation (UDA) methods presume source and target domain data to be simultaneously available during training. Such an assumption may not hold in practice, as source data is often inaccessible (e.g., due to …