Search Results for author: Jacopo Cavazza

Found 20 papers, 5 papers with code

Semantically Grounded Visual Embeddings for Zero-Shot Learning

no code implementations3 Jan 2022 Shah Nawaz, Jacopo Cavazza, Alessio Del Bue

Zero-shot learning methods rely on fixed visual and semantic embeddings, extracted from independent vision and language models, both pre-trained for other large-scale tasks.

Zero-Shot Learning

From Biased Data to Unbiased Models: a Meta-Learning Approach

no code implementations29 Sep 2021 Ruggero Ragonesi, Valentina Sanguineti, Jacopo Cavazza, Vittorio Murino

It is well known that large deep architectures are powerful models when adequately trained, but may exhibit undesirable behavior leading to confident incorrect predictions, even when evaluated on slightly different test examples.

Meta-Learning

Learning without Seeing nor Knowing: Towards Open Zero-Shot Learning

no code implementations23 Mar 2021 Federico Marmoreo, Julio Ivan Davila Carrazco, Vittorio Murino, Jacopo Cavazza

We formalize OZSL as the problem of recognizing seen and unseen classes (as in GZSL) while also rejecting instances from unknown categories, for which neither visual data nor class embeddings are provided.

Generalized Zero-Shot Learning

Classifier Crafting: Turn Your ConvNet into a Zero-Shot Learner!

no code implementations20 Mar 2021 Jacopo Cavazza

Given that the latter seamlessly generalize towards unseen classes, while requiring not actual unseen data to be computed, we can perform ZSL inference by augmenting the pool of classification rules at test time while keeping the very same representation we learnt: nowhere re-training or fine-tuning on unseen data is performed.

General Classification Zero-Shot Learning

Transductive Zero-Shot Learning by Decoupled Feature Generation

no code implementations5 Feb 2021 Federico Marmoreo, Jacopo Cavazza, Vittorio Murino

In this paper, we address zero-shot learning (ZSL), the problem of recognizing categories for which no labeled visual data are available during training.

Zero-Shot Learning

Learning Unbiased Representations via Mutual Information Backpropagation

1 code implementation13 Mar 2020 Ruggero Ragonesi, Riccardo Volpi, Jacopo Cavazza, Vittorio Murino

We are interested in learning data-driven representations that can generalize well, even when trained on inherently biased data.

Fairness

Scalable and Compact 3D Action Recognition with Approximated RBF Kernel Machines

no code implementations28 Nov 2017 Jacopo Cavazza, Pietro Morerio, Vittorio Murino

Despite the recent deep learning (DL) revolution, kernel machines still remain powerful methods for action recognition.

3D Action Recognition

Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation

1 code implementation ICLR 2018 Pietro Morerio, Jacopo Cavazza, Vittorio Murino

In this work, we face the problem of unsupervised domain adaptation with a novel deep learning approach which leverages on our finding that entropy minimization is induced by the optimal alignment of second order statistics between source and target domains.

General Classification Unsupervised Domain Adaptation

Dropout as a Low-Rank Regularizer for Matrix Factorization

no code implementations13 Oct 2017 Jacopo Cavazza, Pietro Morerio, Benjamin Haeffele, Connor Lane, Vittorio Murino, Rene Vidal

Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways.

An Analysis of Dropout for Matrix Factorization

no code implementations10 Oct 2017 Jacopo Cavazza, Connor Lane, Benjamin D. Haeffele, Vittorio Murino, René Vidal

While the resulting regularizer is closely related to a variational form of the nuclear norm, suggesting that dropout may limit the size of the factorization, we show that it is possible to trivially lower the objective value by doubling the size of the factorization.

A Compact Kernel Approximation for 3D Action Recognition

no code implementations6 Sep 2017 Jacopo Cavazza, Pietro Morerio, Vittorio Murino

In this work we reduce such complexity to be linear by proposing a novel and explicit feature map to approximate the kernel function.

3D Action Recognition

When Kernel Methods meet Feature Learning: Log-Covariance Network for Action Recognition from Skeletal Data

no code implementations3 Aug 2017 Jacopo Cavazza, Pietro Morerio, Vittorio Murino

Human action recognition from skeletal data is a hot research topic and important in many open domain applications of computer vision, thanks to recently introduced 3D sensors.

Action Recognition Temporal Action Localization

What Will I Do Next? The Intention from Motion Experiment

no code implementations3 Aug 2017 Andrea Zunino, Jacopo Cavazza, Atesh Koul, Andrea Cavallo, Cristina Becchio, Vittorio Murino

In this paper, we bridge cognitive and computer vision studies, by demonstrating the effectiveness of video-based approaches for the prediction of human intentions.

Early Classification General Classification

Curriculum Dropout

2 code implementations ICCV 2017 Pietro Morerio, Jacopo Cavazza, Riccardo Volpi, Rene Vidal, Vittorio Murino

This induces an adaptive regularization scheme that smoothly increases the difficulty of the optimization problem.

Image Classification Scheduling

Active Regression with Adaptive Huber Loss

no code implementations5 Jun 2016 Jacopo Cavazza, Vittorio Murino

This paper addresses the scalar regression problem through a novel solution to exactly optimize the Huber loss in a general semi-supervised setting, which combines multi-view learning and manifold regularization.

MULTI-VIEW LEARNING regression

Revisiting Human Action Recognition: Personalization vs. Generalization

no code implementations2 May 2016 Andrea Zunino, Jacopo Cavazza, Vittorio Murino

In particular, considering that each human action in the datasets is performed several times by different subjects, we were able to precisely quantify the effect of inter- and intra-subject variability, so as to figure out the impact of several learning approaches in terms of classification performance.

Action Classification Action Recognition +2

Kernelized Covariance for Action Recognition

no code implementations22 Apr 2016 Jacopo Cavazza, Andrea Zunino, Marco San Biagio, Vittorio Murino

In this paper we aim at increasing the descriptive power of the covariance matrix, limited in capturing linear mutual dependencies between variables only.

3D Action Recognition Descriptive

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