Search Results for author: Andrea Cavallaro

Found 41 papers, 20 papers with code

Affordance segmentation of hand-occluded containers from exocentric images

no code implementations22 Aug 2023 Tommaso Apicella, Alessio Xompero, Edoardo Ragusa, Riccardo Berta, Andrea Cavallaro, Paolo Gastaldo

To train the model, we annotated the visual affordances of an existing dataset with mixed-reality images of hand-held containers in third-person (exocentric) images.

Mixed Reality Semantic Segmentation

A mixed-reality dataset for category-level 6D pose and size estimation of hand-occluded containers

no code implementations18 Nov 2022 Xavier Weber, Alessio Xompero, Andrea Cavallaro

In this paper, we present a mixed-reality dataset of hand-occluded containers for category-level 6D object pose and size estimation.

6D Pose Estimation using RGB Mixed Reality

Content-based Graph Privacy Advisor

1 code implementation20 Oct 2022 Dimitrios Stoidis, Andrea Cavallaro

People may be unaware of the privacy risks of uploading an image online.

BON: An extended public domain dataset for human activity recognition

no code implementations12 Sep 2022 Girmaw Abebe Tadesse, Oliver Bent, Komminist Weldemariam, Md. Abrar Istiak, Taufiq Hasan, Andrea Cavallaro

Body-worn first-person vision (FPV) camera enables to extract a rich source of information on the environment from the subject's viewpoint.

Human Activity Recognition

Cross-Camera View-Overlap Recognition

no code implementations24 Aug 2022 Alessio Xompero, Andrea Cavallaro

We propose a decentralised view-overlap recognition framework that operates across freely moving cameras without the need of a reference 3D map.

On the limits of perceptual quality measures for enhanced underwater images

no code implementations12 Jul 2022 Chau Yi Li, Andrea Cavallaro

The appearance of objects in underwater images is degraded by the selective attenuation of light, which reduces contrast and causes a colour cast.

Image Enhancement

Generating gender-ambiguous voices for privacy-preserving speech recognition

1 code implementation3 Jul 2022 Dimitrios Stoidis, Andrea Cavallaro

Our voice encodes a uniquely identifiable pattern which can be used to infer private attributes, such as gender or identity, that an individual might wish not to reveal when using a speech recognition service.

Privacy Preserving Representation Learning +2

On the reversibility of adversarial attacks

no code implementations1 Jun 2022 Chau Yi Li, Ricardo Sánchez-Matilla, Ali Shahin Shamsabadi, Riccardo Mazzon, Andrea Cavallaro

We refer to this property as the reversibility of an adversarial attack, and quantify reversibility as the accuracy in retrieving the original class or the true class of an adversarial example.

Adversarial Attack

Data augmentation with mixtures of max-entropy transformations for filling-level classification

no code implementations8 Mar 2022 Apostolos Modas, Andrea Cavallaro, Pascal Frossard

We address the problem of distribution shifts in test-time data with a principled data augmentation scheme for the task of content-level classification.

Data Augmentation Transfer Learning

Training privacy-preserving video analytics pipelines by suppressing features that reveal information about private attributes

1 code implementation5 Mar 2022 Chau Yi Li, Andrea Cavallaro

However, the features extracted by a deep neural network that was trained to predict a specific, consensual attribute (e. g. emotion) may also encode and thus reveal information about private, protected attributes (e. g. age or gender).

Emotion Recognition Privacy Preserving

Is Cross-Attention Preferable to Self-Attention for Multi-Modal Emotion Recognition?

1 code implementation18 Feb 2022 Vandana Rajan, Alessio Brutti, Andrea Cavallaro

Generally, models that fuse complementary information from multiple modalities outperform their uni-modal counterparts.

Emotion Classification Emotion Recognition

Cross-Modal Knowledge Transfer via Inter-Modal Translation and Alignment for Affect Recognition

no code implementations2 Aug 2021 Vandana Rajan, Alessio Brutti, Andrea Cavallaro

For this reason, we aim to improve the performance of uni-modal affect recognition models by transferring knowledge from a better-performing (or stronger) modality to a weaker modality during training.

Sentiment Analysis Sentiment Classification +2

Protecting gender and identity with disentangled speech representations

no code implementations22 Apr 2021 Dimitrios Stoidis, Andrea Cavallaro

Besides its linguistic content, our speech is rich in biometric information that can be inferred by classifiers.

Privacy Preserving Representation Learning +2

An embedded multichannel sound acquisition system for drone audition

no code implementations17 Jan 2021 Michael Clayton, Lin Wang, Andrew McPherson, Andrea Cavallaro

Microphone array techniques can improve the acoustic sensing performance on drones, compared to the use of a single microphone.

Underwater image filtering: methods, datasets and evaluation

no code implementations22 Dec 2020 Chau Yi Li, Riccardo Mazzon, Andrea Cavallaro

The growing interest in underwater image filtering methods--including learning-based approaches used for both restoration and enhancement--and the associated challenges call for a comprehensive review of the state of the art.

Underwater Image Restoration

Robust Latent Representations via Cross-Modal Translation and Alignment

no code implementations3 Nov 2020 Vandana Rajan, Alessio Brutti, Andrea Cavallaro

The proposed multi-modal training framework uses cross-modal translation and correlation-based latent space alignment to improve the representations of the weaker modalities.

Emotion Recognition Translation

Benchmark for Anonymous Video Analytics

no code implementations30 Sep 2020 Ricardo Sanchez-Matilla, Andrea Cavallaro

Out-of-home audience measurement aims to count and characterize the people exposed to advertising content in the physical world.

Age and Gender Estimation

Semantically Adversarial Learnable Filters

2 code implementations13 Aug 2020 Ali Shahin Shamsabadi, Changjae Oh, Andrea Cavallaro

The proposed framework combines a structure loss and a semantic adversarial loss in a multi-task objective function to train a fully convolutional neural network.

DANA: Dimension-Adaptive Neural Architecture for Multivariate Sensor Data

2 code implementations5 Aug 2020 Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, Hamed Haddadi

We introduce a dimension-adaptive pooling (DAP) layer that makes DNNs flexible and more robust to changes in sensor availability and in sampling rate.

Human Activity Recognition Imputation +1

Exploiting vulnerabilities of deep neural networks for privacy protection

1 code implementation19 Jul 2020 Ricardo Sanchez-Matilla, Chau Yi Li, Ali Shahin Shamsabadi, Riccardo Mazzon, Andrea Cavallaro

To address these limitations, we present an adversarial attack {that is} specifically designed to protect visual content against { unseen} classifiers and known defenses.

Adversarial Attack Quantization

Towards robust sensing for Autonomous Vehicles: An adversarial perspective

no code implementations14 Jul 2020 Apostolos Modas, Ricardo Sanchez-Matilla, Pascal Frossard, Andrea Cavallaro

Autonomous Vehicles rely on accurate and robust sensor observations for safety critical decision-making in a variety of conditions.

Autonomous Vehicles Decision Making

Novel-View Human Action Synthesis

1 code implementation6 Jul 2020 Mohamed Ilyes Lakhal, Davide Boscaini, Fabio Poiesi, Oswald Lanz, Andrea Cavallaro

We first estimate the 3D mesh of the target body and transfer the rough textures from the 2D images to the mesh.

Novel View Synthesis Video Generation

PrivEdge: From Local to Distributed Private Training and Prediction

1 code implementation12 Apr 2020 Ali Shahin Shamsabadi, Adria Gascon, Hamed Haddadi, Andrea Cavallaro

To address this problem, we propose PrivEdge, a technique for privacy-preserving MLaaS that safeguards the privacy of users who provide their data for training, as well as users who use the prediction service.

Image Compression Privacy Preserving

DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments

2 code implementations12 Apr 2020 Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas, Soteris Demetriou, Ilias Leontiadis, Andrea Cavallaro, Hamed Haddadi

We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs).

Image Classification

Multi-view shape estimation of transparent containers

1 code implementation27 Nov 2019 Alessio Xompero, Ricardo Sanchez-Matilla, Apostolos Modas, Pascal Frossard, Andrea Cavallaro

The 3D localisation of an object and the estimation of its properties, such as shape and dimensions, are challenging under varying degrees of transparency and lighting conditions.

Semantic Segmentation

ColorFool: Semantic Adversarial Colorization

2 code implementations CVPR 2020 Ali Shahin Shamsabadi, Ricardo Sanchez-Matilla, Andrea Cavallaro

Instead, adversarial attacks that generate unrestricted perturbations are more robust to defenses, are generally more successful in black-box settings and are more transferable to unseen classifiers.

Adversarial Attack Colorization +1

Privacy and Utility Preserving Sensor-Data Transformations

1 code implementation14 Nov 2019 Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, Hamed Haddadi

Sensitive inferences and user re-identification are major threats to privacy when raw sensor data from wearable or portable devices are shared with cloud-assisted applications.

Activity Recognition

EdgeFool: An Adversarial Image Enhancement Filter

2 code implementations27 Oct 2019 Ali Shahin Shamsabadi, Changjae Oh, Andrea Cavallaro

This loss function accounts for both image detail enhancement and class misleading objectives.

Denoising Image Enhancement

Learning Generalisable Omni-Scale Representations for Person Re-Identification

5 code implementations15 Oct 2019 Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, Tao Xiang

An effective person re-identification (re-ID) model should learn feature representations that are both discriminative, for distinguishing similar-looking people, and generalisable, for deployment across datasets without any adaptation.

Unsupervised Domain Adaptation Unsupervised Person Re-Identification

ConflictNET: End-to-End Learning for Speech-based Conflict Intensity Estimation

1 code implementation26 Sep 2019 Vandana Rajan, Alessio Brutti, Andrea Cavallaro

Computational paralinguistics aims to infer human emotions, personality traits and behavioural patterns from speech signals.

Towards Characterizing and Limiting Information Exposure in DNN Layers

no code implementations13 Jul 2019 Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas, Andrea Cavallaro, Hamed Haddadi

Pre-trained Deep Neural Network (DNN) models are increasingly used in smartphones and other user devices to enable prediction services, leading to potential disclosures of (sensitive) information from training data captured inside these models.

Omni-Scale Feature Learning for Person Re-Identification

12 code implementations ICCV 2019 Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, Tao Xiang

As an instance-level recognition problem, person re-identification (ReID) relies on discriminative features, which not only capture different spatial scales but also encapsulate an arbitrary combination of multiple scales.

Person Re-Identification

Concealing the identity of faces in oblique images with adaptive hopping Gaussian mixtures

no code implementations29 Oct 2018 Omair Sarwar, Bernhard Rinner, Andrea Cavallaro

To address this issue, we propose to pseudo-randomly modify the appearance of face regions in the images using a privacy filter that prevents a human or a face recogniser from inferring the identities of people.

Face Recognition

Mobile Sensor Data Anonymization

1 code implementation26 Oct 2018 Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, Hamed Haddadi

Motion sensors such as accelerometers and gyroscopes measure the instant acceleration and rotation of a device, in three dimensions.

Activity Recognition

A Multi-perspective Approach To Anomaly Detection For Self-aware Embodied Agents

no code implementations17 Mar 2018 Mohamad Baydoun, Mahdyar Ravanbakhsh, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Andrea Cavallaro, Carlo S. Regazzoni

This paper focuses on multi-sensor anomaly detection for moving cognitive agents using both external and private first-person visual observations.

Anomaly Detection

Protecting Sensory Data against Sensitive Inferences

1 code implementation21 Feb 2018 Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, Hamed Haddadi

Results show that the proposed framework maintains the usefulness of the transformed data for activity recognition, with an average loss of only around three percentage points, while reducing the possibility of gender classification to around 50\%, the target random guess, from more than 90\% when using raw sensor data.

Activity Recognition Gender Classification +1

Distributed One-class Learning

no code implementations10 Feb 2018 Ali Shahin Shamsabadi, Hamed Haddadi, Andrea Cavallaro

A major advantage of the proposed filter over existing distributed learning approaches is that users cannot access, even indirectly, the parameters of other users.

Blocking One-class classifier

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