Zobrazeno 1 - 10
of 808
pro vyhledávání: '"Murino, P"'
Gaze Target Detection (GTD), i.e., determining where a person is looking within a scene from an external viewpoint, is a challenging task, particularly in 3D space. Existing approaches heavily rely on analyzing the person's appearance, primarily focu
Externí odkaz:
http://arxiv.org/abs/2409.17886
Autor:
Ciranni, Massimiliano, Molinaro, Luca, Barbano, Carlo Alberto, Fiandrotti, Attilio, Murino, Vittorio, Pastore, Vito Paolo, Tartaglione, Enzo
In the last few years, due to the broad applicability of deep learning to downstream tasks and end-to-end training capabilities, increasingly more concerns about potential biases to specific, non-representative patterns have been raised. Many works f
Externí odkaz:
http://arxiv.org/abs/2408.09570
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In essence, such
Externí odkaz:
http://arxiv.org/abs/2408.04955
Autor:
Pastore, Vito Paolo, Ciranni, Massimiliano, Marinelli, Davide, Odone, Francesca, Murino, Vittorio
It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization abilities and low
Externí odkaz:
http://arxiv.org/abs/2407.17449
This paper presents a classification framework based on learnable data augmentation to tackle the One-Shot Unsupervised Domain Adaptation (OS-UDA) problem. OS-UDA is the most challenging setting in Domain Adaptation, as only one single unlabeled targ
Externí odkaz:
http://arxiv.org/abs/2310.02201
Objects are crucial for understanding human-object interactions. By identifying the relevant objects, one can also predict potential future interactions or actions that may occur with these objects. In this paper, we study the problem of Short-Term O
Externí odkaz:
http://arxiv.org/abs/2308.08303
In this technical report, we describe the Guided-Attention mechanism based solution for the short-term anticipation (STA) challenge for the EGO4D challenge. It combines the object detections, and the spatiotemporal features extracted from video clips
Externí odkaz:
http://arxiv.org/abs/2305.16066
Short-term action anticipation (STA) in first-person videos is a challenging task that involves understanding the next active object interactions and predicting future actions. Existing action anticipation methods have primarily focused on utilizing
Externí odkaz:
http://arxiv.org/abs/2305.12953
Autor:
Carrazco, Julio Ivan Davila, Kadam, Suvarna Kishorkumar, Morerio, Pietro, Del Bue, Alessio, Murino, Vittorio
Publikováno v:
22nd International Conference on IMAGE ANALYSIS AND PROCESSING (ICIAP) 2023
In this paper, we introduce a novel framework for the challenging problem of One-Shot Unsupervised Domain Adaptation (OSUDA), which aims to adapt to a target domain with only a single unlabeled target sample. Unlike existing approaches that rely on l
Externí odkaz:
http://arxiv.org/abs/2305.04628
Existing Source-free Unsupervised Domain Adaptation (SUDA) approaches inherently exhibit catastrophic forgetting. Typically, models trained on a labeled source domain and adapted to unlabeled target data improve performance on the target while droppi
Externí odkaz:
http://arxiv.org/abs/2304.07374