Publication

Benchmarking classification techniques using the Opportunity human activity dataset

Related publications (24)

Explanation of Face Recognition via Saliency Maps

Despite the significant progress in recent years, deep face recognition is often treated as a "black box" and has been criticized for lacking explainability. It becomes increasingly important to understand the characteristics and decisions of deep face rec ...

2023

Recognizing distant faces

Marin Vogelsang, Lukas Vogelsang

As an 'early alerting' sense, one of the primary tasks for the human visual system is to recognize distant objects. In the specific context of facial identification, this ecologically important task has received surprisingly little attention. Most studies ...

PERGAMON-ELSEVIER SCIENCE LTD2023

Complex Daily Activities, Country-Level Diversity, and Smartphone Sensing: A Study in Denmark, Italy, Mongolia, Paraguay, and UK

Daniel Gatica-Perez, Karim Assi, Lakmal Buddika Meegahapola

Smartphones enable understanding human behavior with activity recognition to support peoples daily lives. Prior studies focused on using inertial sensors to detect simple activities (sitting, walking, running, etc.) and were mostly conducted in homogeneous ...

Assoc Computing Machinery2023

Contrasting action and posture coding with hierarchical deep neural network models of proprioception

Pranav Mamidanna, Mackenzie Mathis, Alexander Mathis, Kai Jappe Sandbrink, Matthias Bethge

Biological motor control is versatile, efficient, and depends on proprioceptive feedback. Muscles are flexible and undergo continuous changes, requiring distributed adaptive control mechanisms that continuously account for the body's state. The canonical r ...

eLIFE SCIENCES PUBL LTD2023

Regularization of polynomial networks for image recognition

Volkan Cevher, Bohan Wang, Grigorios Chrysos

Deep Neural Networks (DNNs) have obtained impressive performance across tasks, however they still remain as black boxes, e.g., hard to theoretically analyze. At the same time, Polynomial Networks (PNs) have emerged as an alternative method with a promising ...

2023

Regularization of polynomial networks for image recognition

Volkan Cevher, Bohan Wang, Grigorios Chrysos

Ieee Computer Soc2023

Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition

Tao Lin

In wearable-based human activity recognition (HAR) research, one of the major challenges is the large intra-class variability problem. The collected activity signal is often, if not always, coupled with noises or bias caused by personal, environmental, or ...

ASSOC COMPUTING MACHINERY2022

On the Recognition Performance of BioHashing on state-of-the-art Face Recognition models

Sébastien Marcel, Hatef Otroshi Shahreza

Face recognition has become a popular authentication tool in recent years. Modern state-of-the-art (SOTA) face recognition methods rely on deep neural networks, which extract discriminative features from face images. Although these methods have high recogn ...

IEEE2021

Differentiable Patch Selection for Image Recognition

Aravindh Mahendran, Jean-Baptiste Francis Marie Juliette Cordonnier

Neural Networks require large amounts of memory and compute to process high resolution images, even when only a small part of the image is actually informative for the task at hand. We propose a method based on a differentiable Top-K operator to select the ...

IEEE COMPUTER SOC2021

Poly-NL: Linear Complexity Non-local Layers With 3rd Order Polynomials

Filippos Kokkinos, Grigorios Chrysos

Spatial self-attention layers, in the form of Non-Local blocks, introduce long-range dependencies in Convolutional Neural Networks by computing pairwise similarities among all possible positions. Such pairwise functions underpin the effectiveness of non-lo ...

IEEE2021

Crowding and the importance of grouping and segmentation processes in human vision

Alban Bornet

Human vision has evolved to make sense of a world in which elements almost never appear in isolation. Surprisingly, the recognition of an element in a visual scene is strongly limited by the presence of other nearby elements, a phenomenon known as visual c ...

EPFL2021

Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks

Maksym Andriushchenko, Nicolas Henri Bernard Flammarion, Francesco Croce

A large body of research has focused on adversarial attacks which require to modify all input features with small l2- or l∞-norms. In this paper we instead focus on query-efficient sparse attacks in the black-box setting. Our versatile framework, Sparse-RS ...

2020

Single-Stage 6D Object Pose Estimation

Pascal Fua, Mathieu Salzmann, Yinlin Hu, Wei Wang

Most recent 6D pose estimation frameworks first rely on a deep network to establish correspondences between 3D object keypoints and 2D image locations and then use a variant of a RANSAC-based Perspective-n-Point (PnP) algorithm. This two-stage process, how ...

IEEE2020

Time-Delay Encoded Image Recognition in a Network of Resistively Coupled VO2 on Si Oscillators

Kirsten Emilie Moselund, Siegfried Karg

Oscillatory neural networks based on insulator to metal transition of VO2 switches are implemented for image recognition. The VO2 oscillators are fabricated on silicon in a CMOS compatible process.A fullyconnected network of coupled oscillators is investig ...

Institute of Electrical and Electronics Engineers2020

Trustworthy Face Recognition: Improving Generalization of Deep Face Presentation Attack Detection

Amir Mohammadi

The extremely high recognition accuracy achieved by modern, convolutional neural network (CNN) based face recognition (FR) systems has contributed significantly to the adoption of such systems in a variety of applications, from mundane activities like unlo ...

EPFL2020

Multimodal person recognition in audio-visual streams

Do Hoang Nam Le

Multimedia databases are growing rapidly in size in the digital age. To increase the value of these data and to enhance the user experience, there is a need to make these videos searchable through automatic indexing. Because people appearing and talking in ...

EPFL2019

Using Photorealistic Face Synthesis and Domain Adaptation to Improve Facial Expression Analysis

Jean-Philippe Thiran, Mohammad Saeed Rad, Hazim Kemal Ekenel

Cross-domain synthesizing realistic faces to learn deep models has attracted increasing attention for facial expression analysis as it helps to improve the performance of expression recognition accuracy despite having small number of real training images. ...

IEEE2019

A Geometry-Inspired Decision-Based Attack

Pascal Frossard, Seyed Mohsen Moosavi Dezfooli, Yujia Liu

Deep neural networks have recently achieved tremendous success in image classification. Recent studies have however shown that they are easily misled into incorrect classification decisions by adversarial examples. Adversaries can even craft attacks by que ...

IEEE COMPUTER SOC2019

Theoretical foundations of forward feature selection methods based on mutual information

Francisco Santos Paredes Quartin de Macedo

Feature selection problems arise in a variety of applications, such as microarray analysis, clinical prediction, text categorization, image classification and face recognition, multi-label learning, and classification of internet traffic. Among the various ...

ELSEVIER SCIENCE BV2019

Multispectral Deep Embeddings As a Countermeasure To Custom Silicone Mask Presentation Attacks

Sébastien Marcel

This work focuses on detecting presentation attacks (PA) mounted using custom silicone masks. Face recognition (FR) systems have been shown to be highly vulnerable to PAs based on such masks [1, 2]. Here we explore the use of multispectral data (color imag ...

2019