Search Results for author: Paolo Rota

Found 17 papers, 11 papers with code

The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation

1 code implementation ICCV 2023 Giacomo Zara, Alessandro Conti, Subhankar Roy, Stéphane Lathuilière, Paolo Rota, Elisa Ricci

Source-Free Video Unsupervised Domain Adaptation (SFVUDA) task consists in adapting an action recognition model, trained on a labelled source dataset, to an unlabelled target dataset, without accessing the actual source data.

Action Recognition Unsupervised Domain Adaptation

Vocabulary-free Image Classification

1 code implementation NeurIPS 2023 Alessandro Conti, Enrico Fini, Massimiliano Mancini, Paolo Rota, Yiming Wang, Elisa Ricci

We thus formalize a novel task, termed as Vocabulary-free Image Classification (VIC), where we aim to assign to an input image a class that resides in an unconstrained language-induced semantic space, without the prerequisite of a known vocabulary.

Classification Image Classification +4

Rotation Synchronization via Deep Matrix Factorization

1 code implementation9 May 2023 Gk Tejus, Giacomo Zara, Paolo Rota, Andrea Fusiello, Elisa Ricci, Federica Arrigoni

In this paper we address the rotation synchronization problem, where the objective is to recover absolute rotations starting from pairwise ones, where the unknowns and the measures are represented as nodes and edges of a graph, respectively.

Matrix Completion Simultaneous Localization and Mapping

AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation

1 code implementation CVPR 2023 Giacomo Zara, Subhankar Roy, Paolo Rota, Elisa Ricci

Open-set Unsupervised Video Domain Adaptation (OUVDA) deals with the task of adapting an action recognition model from a labelled source domain to an unlabelled target domain that contains "target-private" categories, which are present in the target but absent in the source.

Action Recognition Domain Adaptation +1

Simplifying Open-Set Video Domain Adaptation with Contrastive Learning

1 code implementation9 Jan 2023 Giacomo Zara, Victor Guilherme Turrisi da Costa, Subhankar Roy, Paolo Rota, Elisa Ricci

In this work we address a more realistic scenario, called open-set video domain adaptation (OUVDA), where the target dataset contains "unknown" semantic categories that are not shared with the source.

Action Recognition Contrastive Learning +1

Deep Unsupervised Key Frame Extraction for Efficient Video Classification

no code implementations12 Nov 2022 Hao Tang, Lei Ding, Songsong Wu, Bin Ren, Nicu Sebe, Paolo Rota

The proposed TSDPC is a generic and powerful framework and it has two advantages compared with previous works, one is that it can calculate the number of key frames automatically.

Classification Video Classification

Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation

1 code implementation26 Mar 2022 Guanglei Yang, Enrico Fini, Dan Xu, Paolo Rota, Mingli Ding, Moin Nabi, Xavier Alameda-Pineda, Elisa Ricci

This problem has been widely investigated in the research community and several Incremental Learning (IL) approaches have been proposed in the past years.

Contrastive Learning Image Classification +5

Continual Attentive Fusion for Incremental Learning in Semantic Segmentation

1 code implementation1 Feb 2022 Guanglei Yang, Enrico Fini, Dan Xu, Paolo Rota, Mingli Ding, Hao Tang, Xavier Alameda-Pineda, Elisa Ricci

To fill this gap, in this paper we introduce a novel attentive feature distillation approach to mitigate catastrophic forgetting while accounting for semantic spatial- and channel-level dependencies.

Incremental Learning Semantic Segmentation

Variational Structured Attention Networks for Deep Visual Representation Learning

1 code implementation5 Mar 2021 Guanglei Yang, Paolo Rota, Xavier Alameda-Pineda, Dan Xu, Mingli Ding, Elisa Ricci

Specifically, we integrate the estimation and the interaction of the attentions within a probabilistic representation learning framework, leading to Variational STructured Attention networks (VISTA-Net).

Depth Estimation Representation Learning +1

Curriculum Learning: A Survey

no code implementations25 Jan 2021 Petru Soviany, Radu Tudor Ionescu, Paolo Rota, Nicu Sebe

Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on random data shuffling, without any additional computational costs.

BIG-bench Machine Learning Clustering

Variational Structured Attention Networks for Dense Pixel-Wise Prediction

1 code implementation1 Jan 2021 Guanglei Yang, Paolo Rota, Xavier Alameda-Pineda, Dan Xu, Mingli Ding, Elisa Ricci

State-of-the-art performances in dense pixel-wise prediction tasks are obtained with specifically designed convolutional networks.

Low-Budget Label Query through Domain Alignment Enforcement

no code implementations1 Jan 2020 Jurandy Almeida, Cristiano Saltori, Paolo Rota, Nicu Sebe

Deep learning revolution happened thanks to the availability of a massive amount of labelled data which have contributed to the development of models with extraordinary inference capabilities.

Unsupervised Domain Adaptation

Curriculum Self-Paced Learning for Cross-Domain Object Detection

no code implementations15 Nov 2019 Petru Soviany, Radu Tudor Ionescu, Paolo Rota, Nicu Sebe

To alleviate this problem, researchers proposed various domain adaptation methods to improve object detection results in the cross-domain setting, e. g. by translating images with ground-truth labels from the source domain to the target domain using Cycle-GAN.

Domain Adaptation Object +2

Indirect Match Highlights Detection with Deep Convolutional Neural Networks

no code implementations2 Oct 2017 Marco Godi, Paolo Rota, Francesco Setti

Highlights in a sport video are usually referred as actions that stimulate excitement or attract attention of the audience.

The S-Hock Dataset: Analyzing Crowds at the Stadium

no code implementations CVPR 2015 Davide Conigliaro, Paolo Rota, Francesco Setti, Chiara Bassetti, Nicola Conci, Nicu Sebe, Marco Cristani

In the dataset, a massive annotation has been carried out, focusing on the spectators at different levels of details: at a higher level, people have been labeled depending on the team they are supporting and the fact that they know the people close to them; going to the lower levels, standard pose information has been considered (regarding the head, the body) but also fine grained actions such as hands on hips, clapping hands etc.

Head Pose Estimation Sociology

Cannot find the paper you are looking for? You can Submit a new open access paper.