Search Results for author:
Found 44 papers, 21 papers with code
Open-vocabulary object 6D pose estimation
We introduce the new setting of open-vocabulary object 6D pose estimation, in which a textual prompt is used to specify the object of interest.
Human-interpretable and deep features for image privacy classification
Privacy is a complex, subjective and contextual concept that is difficult to define.
Black-box Attacks on Image Activity Prediction and its Natural Language Explanations
We show that we can create adversarial images that manipulate the explanations of an activity recognition model by having access only to its final output.
Affordance segmentation of hand-occluded containers from exocentric images
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.
A mixed-reality dataset for category-level 6D pose and size estimation of hand-occluded containers
In this paper, we present a mixed-reality dataset of hand-occluded containers for category-level 6D object pose and size estimation.
Content-based Graph Privacy Advisor
People may be unaware of the privacy risks of uploading an image online.
BON: An extended public domain dataset for human activity recognition
Body-worn first-person vision (FPV) camera enables to extract a rich source of information on the environment from the subject's viewpoint.
Cross-Camera View-Overlap Recognition
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
The appearance of objects in underwater images is degraded by the selective attenuation of light, which reduces contrast and causes a colour cast.
Generating gender-ambiguous voices for privacy-preserving speech recognition
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.
On the reversibility of adversarial attacks
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.
Data augmentation with mixtures of max-entropy transformations for filling-level classification
We address the problem of distribution shifts in test-time data with a principled data augmentation scheme for the task of content-level classification.
Training privacy-preserving video analytics pipelines by suppressing features that reveal information about private attributes
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).
Is Cross-Attention Preferable to Self-Attention for Multi-Modal Emotion Recognition?
Generally, models that fuse complementary information from multiple modalities outperform their uni-modal counterparts.
Cross-Modal Knowledge Transfer via Inter-Modal Translation and Alignment for Affect Recognition
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.
The CORSMAL benchmark for the prediction of the properties of containers
In this paper, we present a range of methods and an open framework to benchmark acoustic and visual perception for the estimation of the capacity of a container, and the type, mass, and amount of its content.
Protecting gender and identity with disentangled speech representations
Besides its linguistic content, our speech is rich in biometric information that can be inferred by classifiers.
Improving filling level classification with adversarial training
We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass.
An embedded multichannel sound acquisition system for drone audition
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
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.
FoolHD: Fooling speaker identification by Highly imperceptible adversarial Disturbances
Speaker identification models are vulnerable to carefully designed adversarial perturbations of their input signals that induce misclassification.
Robust Latent Representations via Cross-Modal Translation and Alignment
The proposed multi-modal training framework uses cross-modal translation and correlation-based latent space alignment to improve the representations of the weaker modalities.
Benchmark for Anonymous Video Analytics
Out-of-home audience measurement aims to count and characterize the people exposed to advertising content in the physical world.
Semantically Adversarial Learnable Filters
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
We introduce a dimension-adaptive pooling (DAP) layer that makes DNNs flexible and more robust to changes in sensor availability and in sampling rate.
Exploiting vulnerabilities of deep neural networks for privacy protection
To address these limitations, we present an adversarial attack {that is} specifically designed to protect visual content against { unseen} classifiers and known defenses.
Towards robust sensing for Autonomous Vehicles: An adversarial perspective
Autonomous Vehicles rely on accurate and robust sensor observations for safety critical decision-making in a variety of conditions.
Novel-View Human Action Synthesis
We first estimate the 3D mesh of the target body and transfer the rough textures from the 2D images to the mesh.
DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments
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).
PrivEdge: From Local to Distributed Private Training and Prediction
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.
Multi-view shape estimation of transparent containers
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.
ColorFool: Semantic Adversarial Colorization
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.
Privacy and Utility Preserving Sensor-Data Transformations
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.
EdgeFool: An Adversarial Image Enhancement Filter
This loss function accounts for both image detail enhancement and class misleading objectives.
Learning Generalisable Omni-Scale Representations for Person Re-Identification
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
Computational paralinguistics aims to infer human emotions, personality traits and behavioural patterns from speech signals.
Towards Characterizing and Limiting Information Exposure in DNN Layers
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
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.
Ranked #2 on
Person Re-Identification
on MSMT17-C
Concealing the identity of faces in oblique images with adaptive hopping Gaussian mixtures
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.
Mobile Sensor Data Anonymization
Motion sensors such as accelerometers and gyroscopes measure the instant acceleration and rotation of a device, in three dimensions.
Video Summarisation by Classification with Deep Reinforcement Learning
Most existing video summarisation methods are based on either supervised or unsupervised learning.
A Multi-perspective Approach To Anomaly Detection For Self-aware Embodied Agents
This paper focuses on multi-sensor anomaly detection for moving cognitive agents using both external and private first-person visual observations.
Protecting Sensory Data against Sensitive Inferences
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.
Distributed One-class Learning
A major advantage of the proposed filter over existing distributed learning approaches is that users cannot access, even indirectly, the parameters of other users.
