Multimodal person recognition in audio-visual streams

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Decisions about a current visual stimulus are systematically biased by recently encountered stimuli, a phenomenon known as serial dependence. In human vision, for instance, we tend to report the features of current images as more similar â i.e., an attra ...

Viewers of 360-degree videos are provided with both visual modality to characterize their surrounding views and audio modality to indicate the sound direction. Though both modalities are important for saliency prediction, little work has been done by joint ...

Epilepsy, a major neurological disease, requires careful diagnosis and treatment. However, the detection of epileptic seizures remains a significant challenge. Current clinical practice relies on expert analysis of EEG signals, a process that is time-consu ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

This paper presents a novel hybrid framework for generating and updating a synthetic population. We call it hybrid because it combines model-based and data-driven approaches. Existing generators produce a snapshot of synthetic data that becomes outdated ov ...

This document contains all the data and the details of the analysis used in the manuscript titled " Control of Ge island coalescence for the formation of nanowires on silicon." https://doi.org/10.1039/D3NH00573A ...

In the last few years, stroke ranked as the second most common cause of death and is the third most significant condition affecting disability-adjusted life years (DALYs) worldwide. Being the most prevalent and quality of life impacting post-stroke symptom ...

This work studies the learning process over social networks under partial and random information sharing. In traditional social learning models, agents exchange full belief information with each other while trying to infer the true state of nature. We stud ...

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

Genome-wide chromatin conformation capture assays provide formidable insights into the spatial organization of genomes. However, due to the complexity of the data structure, their integration in multi-omics workflows remains challenging. We present data st ...

This data set contains the data collected during the FNS project Green Piezo (Grant no. 179064) in association with the recent publication entitled “3D printing of customizable transient bioelectronics and sensors”. This work aims to study and demonstrate ...

Image information about the state of a building after an earthquake, which can be collected without endangering the post-earthquake reconnaissance activities, can be used to reduce uncertainties in response predictions for future seismic events. This paper ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Multimodal person recognition in audio-visual streams

Chat with Graph Search

Serial Dependence in Human Visual Perception and Decision-Making

SVGC-AVA: 360-Degree Video Saliency Prediction With Spherical Vector-Based Graph Convolution and Audio-Visual Attention

Resource-Efficient Continual Learning for Personalized Online Seizure Detection

Understanding generalization and robustness in modern deep learning

Hybrid Simulator for Capturing Dynamics of Synthetic Populations

Data set for control of Ge island coalescence for the formation of nanowires on silicon

Probing and modulating inter-areal coupling in the cortical visual motion processing pathway with non-invasive brain stimulation

Social Opinion Formation and Decision Making Under Communication Trends

Meta-learning to address diverse Earth observation problems across resolutions

Machine Learning for Modeling Stock Returns

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Orchestrating chromosome conformation capture analysis with Bioconductor

Dataset for '3D printing of customizable transient bioelectronics and sensors'

Reducing uncertainties in response predictions of earthquake-damaged masonry buildings using data from image-based inspection

Advancing Self-Supervised Deep Learning for 3D Scene Understanding