Warning

Please note that the publication lists from Infoscience integrated into the EPFL website, lab or people pages are frozen following the launch of the new version of platform. The owners of these pages are invited to recreate their publication list from Infoscience. For any assistance, please consult the Infoscience help or contact support.

2024

TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression

M. Shukla; M. Salzmann; A. Alahi

2024-07-21. 41st International Conference on Machine Learning (ICML) 2024, Vienna, Austria, July 21-27, 2024.

2024

TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Dynamic Voxels Based on Ego-Conditioned Prediction: An Integrated Spatio-Temporal Framework for Motion Planning

Social-Transmotion: Promptable Human Trajectory Prediction

When Your AI Becomes a Target: AI Security Incidents and Best Practices

Machine Learning Security Against Data Poisoning: Are We There Yet?

Voices from the Frontline: Revealing the AI Practitioners’ viewpoint on the European AI Act

Toward Reliable Human Pose Forecasting With Uncertainty

Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?

2023

Rethinking data augmentation for adversarial robustness

Toward contactless human thermal monitoring: A framework for Machine Learning-based human thermo-physiology modeling augmented with computer vision

Adversarial vulnerability bounds for Gaussian process classification

Real-Time Localization for Closed-Loop Control of Assistive Furniture

Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning

Non-intrusive physiological parameters sensing for personalized human thermal comfort prediction

The Metaverse as a Virtual Model of Platform Urbanism: Its Converging AIoT, XReality, Neurotech, and Nanobiotech and Their Applications, Challenges, and Risks

A generic diffusion-based approach for 3D human pose prediction in the wild

The automated collapse data constructor technique and the data-driven methodology for seismic collapse risk assessment

Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking

DeepSportradar-v2: a Multi-Sport Computer Vision Dataset for Sport Understandings

Traffic perception from aerial images using butterfly fields

Manipulating Trajectory Prediction with Backdoors

Towards more Practical Threat Models in Artificial Intelligence Security

Learning Robust and Adaptive Representations: from Interactions, for Interactions

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning

On Pitfalls of Test-time Adaptation

Machine Learning Security in Industry: A Quantitative Survey

Training Traffic Light Behavior with End-to-End Learning

Body Part-Based Representation Learning for Occluded Person Re-Identification

Safety-Compliant Generative Adversarial Networks for Human Trajectory Forecasting

Composite Relationship Fields with Transformers for Scene Graph Generation

2022

VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation

Proxy methods for detection of inhalation exposure in simulated office environments

The Rising Impacts of the COVID-19 Pandemic and the Russia-Ukraine War: Energy Transition, Climate Justice, Global Inequality, and Supply Chain Disruption

Emerging Trends and Knowledge Structures of Urbanization and Environmental Sustainability: A Regional Perspective

Are the trajectory prediction models generalizable?

Vehicle trajectory prediction works, but not everywhere

SoccerNet 2022 Challenges Results

A Lightweight Goal-Based model for Trajectory Prediction

STATNet: Spatial-temporal attention in the traffic prediction

Deep Learning Methods for Socially-Aware Human Trajectory Forecasting

Visual Scene Understanding for Transportation: From Detecting Objects To Relationships

Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecasting

Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective

Automated Detection Of Isolated Rem Sleep Behavior Disorder (Irbd) During Single Night In-Lab Video-Polysomnography (Psg) Using Computer Vision

Pedestrian 3D Bounding Box Prediction

Are socially-aware trajectory prediction models really socially-aware?

Simple Yet Effective Action Recognition for Autonomous Driving

Reshaping Perception for Autonomous Driving with Semantic Keypoints

Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion

OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association

Detecting 32 Pedestrian Attributes for Autonomous Vehicles

Perceiving Humans: from Monocular 3D Localization to Social Distancing

2021

A Shared Representation for Photorealistic Driving Simulators

TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?

Injecting Knowledge in Data-driven Vehicle Trajectory Predictors

Learning Decoupled Representations for Human Pose Forecasting

DriverGym: Democratising Reinforcement Learning for Autonomous Driving

Human Trajectory Forecasting in Crowds: A Deep Learning Perspective

Modified Joint Channel-and-Data Estimation for One-Bit Massive MIMO

Keypoint Communities

Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving

Social NCE: Contrastive Learning of Socially-aware Motion Representations

Guest Editorial: Introduction to the Special Issue on Long-Term Human Motion Prediction

Pedestrian intention prediction: A convolutional bottom-up multi-task approach

Interpretable Social Anchors for Human Trajectory Forecasting in Crowds

Deep visual Re-identification with confidence

MonStereo: When Monocular and Stereo Meet at the Tail of 3D Human Localization

Adaptive hot water production based on Supervised Learning

2020

Detecting 32 Pedestrian Attributes for Autonomous Vehicles

Automatic detection of hand hygiene using computer vision technology

Pedestrian Intention Prediction: A Multi-task Perspective

Next Steps for Image Synthesis using Semantic Segmentation

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation