Training Algorithms for Multiple Object Tracking

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.

This paper presents a comprehensive framework for extracting georeferenced vehicle trajectories from high-altitude drone imagery, addressing key challenges in urban traffic monitoring and the limitations of traditional ground-based systems. Our approach in ...

Computational methods at the atomic scale based on machine learning have been a fruitful research field in the past decade by merging the advantages of classical and quantum mechanical approaches. While parts of the field are already reaching a mature stat ...

We propose a test -time adaptation for 6D object pose tracking that learns to adapt a pre -trained model to track the 6D pose of novel objects. We consider the problem of 6D object pose tracking as a 3D keypoint detection and matching task and present a mo ...

Semantic segmentation with deep learning plays a crucial role in various fields, including civil engineering, particularly in tasks such as damage assessment and urban planning. This paper addresses the challenge of efficiently training deep learning model ...

In recent years, numerical simulations of hemodynamics have gained significant attention within the medical community, thanks to their ability of non-invasively estimating the blood flow conditions. However, high-fidelity simulations require extensive comp ...

As large, data-driven artificial intelligence models become ubiquitous, guaranteeing high data quality is imperative for constructing models. Crowdsourcing, community sensing, and data filtering have long been the standard approaches to guaranteeing or imp ...

Recently, remarkable progress has been made in the application of machine learning (ML) techniques (e.g., neural networks) to transformer fault diagnosis. However, the diagnostic processes employed by these techniques often suffer from a lack of interpreta ...

Gradient-based learning in multi-layer neural networks displays a number of striking features. In particular, the decrease rate of empirical risk is non-monotone even after averaging over large batches. Long plateaus in which one observes barely any progre ...

Modern integrated circuits are tiny yet incredibly complex technological artifacts, composed of millions and billions of individual structures working in unison. Managing their complexity and facilitating their design drove part of the co-evolution of mode ...

Statistical (machine-learning, ML) models are more and more often used in computational chemistry as a substitute to more expensive ab initio and parametrizable methods. While the ML algorithms are capable of learning physical laws implicitly from data, ad ...

At room temperature, mechanical motion driven by the quantum backaction of light has been observed only in pioneering experiments in which an optical restoring force controls the oscillator stiffness1,2. For solid-state mechanical resonators in which oscil ...

Mechanical resonators are widely used in sensors, transducers and optomechanical systems, where mechanical dissipation sets the ultimate limit to performance. Over the past 15 years, the quality factors in strained mechanical resonators have increased by f ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

Accurately estimating 3D human pose (3D HPE) and joint locations using only 2D keypoints is challenging. The noise in the predictions produced by conventional 2D human pose estimators often impeded the accuracy. In this paper, we present a diffusion-based ...

Mapping behavioural actions to neural activity is a fundamental goal of neuroscience. As our ability to record large neural and behavioural data increases, there is growing interest in modelling neural dynamics during adaptive behaviours to probe neural re ...

VR (Virtual Reality) is a real-time simulation that creates the subjective illusion of being in a virtual world. This thesis explores how integrating the user's body and fingers can be achieved and beneficial for the user to experience VR. At the advent of ...

One significant and simultaneously interesting problem in urban mobility has to do with the study of shared spaces where various categories of users coexist and act together. This paper aims to examine the behavior and preferences of pedestrians and cyclis ...

Calling for increased action on climate change, Fridays for Future (FFF) quickly gained momentum around the world and became highly visible through strikes and protests in more than 150 countries. Considering its scale and magnitude, questions about the im ...

The thesis at hand is concerned with robots' navigation in human crowds. Specifically, methods are developed for planning a mobile robot's local motion between pedestrians, and they are evaluated in experiments where a robot interacts with real pedestrians ...

A crucial building block of responsible artificial intelligence is responsible data governance, including data collection. Its importance is also underlined in the latest EU regulations. The data should be of high quality, foremost correct and representati ...

Training Algorithms for Multiple Object Tracking

Chat with Graph Search

Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagery

Mathematical Analysis and Optimization of Features for Atomistic Machine Learning

Test-time adaptation for 6D pose tracking

Partial annotations in active learning for semantic segmentation

Reduced order models to address temporal complexity and geometrical variability in hemodynamics

Extensions of Peer Prediction Incentive Mechanisms

Explainable Fault Diagnosis of Oil-Immersed Transformers: A Glass-Box Model

Learning Time-Scales in Two-Layers Neural Networks

Graph generative deep learning models with an application to circuit topologies

Encoding quantum-chemical knowledge into machine-learning models of complex molecular properties

Room-temperature quantum optomechanics using an ultralow noise cavity

Ultrahigh-quality-factor micro- and nanomechanical resonators using dissipation dilution

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Diff3DHPE: A Diffusion Model for 3D Human Pose Estimation

Learnable latent embeddings for joint behavioural and neural analysis

From finger animation to full-body embodiment of avatars with different morphologies and proportions

Pedestrian Crossings as a Means of Reducing Conflicts between Cyclists and Pedestrians in Shared Spaces

Perceived impacts of the Fridays for Future climate movement on environmental concern and behaviour in Switzerland

Geometric and Learning Methods for Robots to Navigate in Human Crowds with Application to Smart Mobility Devices

incentive Mechanism Design for Responsible Data Governance: A Large-Scale Field Experiment