41 citations · 109 across the 18 of their papers we have counts for
20 papers
Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance
Giancarlo Paoletti, Jacopo Cavazza, Cigdem Beyan +1
This paper presents a novel end-to-end method for the problem of skeleton-based unsupervised human action recognition. We propose a new architecture with a convolutional autoencode…
Semantically Grounded Visual Embeddings for Zero-Shot Learning
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. This i…
Classifier Crafting: Turn Your ConvNet into a Zero-Shot Learner!
Jacopo Cavazza
In Zero-shot learning (ZSL), we classify unseen categories using textual descriptions about their expected appearance when observed (class embeddings) and a disjoint pool of seen c…
Learning without Seeing nor Knowing: Towards Open Zero-Shot Learning
Federico Marmoreo, Julio Ivan Davila Carrazco, Vittorio Murino +1
In Generalized Zero-Shot Learning (GZSL), unseen categories (for which no visual data are available at training time) can be predicted by leveraging their class embeddings (e.g., a…
Transductive Zero-Shot Learning by Decoupled Feature Generation
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. We focus on the transducti…
Are Multiple Cross-Correlation Identities better than just Two? Improving the Estimate of Time Differences-of-Arrivals from Blind Audio Signals
Danilo Greco, Jacopo Cavazza, Alessio Del Bue
Given an unknown audio source, the estimation of time differences-of-arrivals (TDOAs) can be efficiently and robustly solved using blind channel identification and exploiting the c…
Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning
Giancarlo Paoletti, Jacopo Cavazza, Cigdem Beyan +1
This paper tackles the problem of human action recognition, defined as classifying which action is displayed in a trimmed sequence, from skeletal data. Albeit state-of-the-art appr…
Learning Unbiased Representations via Mutual Information Backpropagation
Ruggero Ragonesi, Riccardo Volpi, Jacopo Cavazza +1
We are interested in learning data-driven representations that can generalize well, even when trained on inherently biased data. In particular, we face the case where some attribut…
Scalable and Compact 3D Action Recognition with Approximated RBF Kernel Machines
Jacopo Cavazza, Pietro Morerio, Vittorio Murino
Despite the recent deep learning (DL) revolution, kernel machines still remain powerful methods for action recognition. DL has brought the use of large datasets and this is typical…
Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation
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 o…
Dropout as a Low-Rank Regularizer for Matrix Factorization
Jacopo Cavazza, Pietro Morerio, Benjamin Haeffele +3
Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways. Due to its popularity in deep learning, dropout has been applie…
An Analysis of Dropout for Matrix Factorization
Jacopo Cavazza, Connor Lane, Benjamin D. Haeffele +2
Dropout is a simple yet effective algorithm for regularizing neural networks by randomly dropping out units through Bernoulli multiplicative noise, and for some restricted problem…
A Compact Kernel Approximation for 3D Action Recognition
Jacopo Cavazza, Pietro Morerio, Vittorio Murino
3D action recognition was shown to benefit from a covariance representation of the input data (joint 3D positions). A kernel machine feed with such feature is an effective paradigm…
What Will I Do Next? The Intention from Motion Experiment
Andrea Zunino, Jacopo Cavazza, Atesh Koul +3
In computer vision, video-based approaches have been widely explored for the early classification and the prediction of actions or activities. However, it remains unclear whether t…
When Kernel Methods meet Feature Learning: Log-Covariance Network for Action Recognition from Skeletal Data
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. In…
Curriculum Dropout
Pietro Morerio, Jacopo Cavazza, Riccardo Volpi +2
Dropout is a very effective way of regularizing neural networks. Stochastically "dropping out" units with a certain probability discourages over-specific co-adaptations of feature…
Active Regression with Adaptive Huber Loss
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 learn…
Revisiting Human Action Recognition: Personalization vs. Generalization
Andrea Zunino, Jacopo Cavazza, Vittorio Murino
By thoroughly revisiting the classic human action recognition paradigm, this paper aims at proposing a new approach for the design of effective action classification systems. Takin…
Predicting Human Intentions from Motion Only: A 2D+3D Fusion Approach
Andrea Zunino, Jacopo Cavazza, Atesh Koul +3
In this paper, we address the new problem of the prediction of human intents. There is neuro-psychological evidence that actions performed by humans are anticipated by peculiar mot…
Kernelized Covariance for Action Recognition
Jacopo Cavazza, Andrea Zunino, Marco San Biagio +1
In this paper we aim at increasing the descriptive power of the covariance matrix, limited in capturing linear mutual dependencies between variables only. We present a rigorous and…