Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when deployed in noisy envi ...
Detecting people from 2D images and analyzing their motion in 3D have been long standing computer vision problems central to numerous applications such as autonomous driving and athletic training. Recently, with the availability of large amounts of trainin ...
During the Artificial Intelligence (AI) revolution of the past decades, deep neural networks have been widely used and have achieved tremendous success in visual recognition. Unfortunately, deploying deep models is challenging because of their huge model s ...
The field of artificial intelligence is set to fuel the future of mobility by driving forward the transition from advanced driver-assist systems to fully autonomous vehicles (AV). Yet the current technology, backed by cutting-edge deep learning techniques, ...
Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data. To fix this vulnerability, prior works have built complex data augmentation strategies, combining multi ...
Atherosclerosis is a complex disease altering vasculature morphology, and subsequently flow, with progressive plaque formation, mural disruption, and lumen occlusion. Determination of clinically-relevant plaque components-particularly calcium, lipid, and f ...
Object-centric learning has gained significant attention over the last years as it can serve as a powerful tool to analyze complex scenes as a composition of simpler entities. Well-established tasks in computer vision, such as object detection or instance ...
Deep neural networks (DNNs) have achieved great success in image classification and recognition compared to previous methods. However, recent works have reported that DNNs are very vulnerable to adversarial examples that are intentionally generated to misl ...
We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input besides the RGB ...
