Publications associées à A Computer Vision System to Localize and Classify Wastes on the Streets

GELEX: Generative AI-Hybrid System for Example-Based Learning

Tanja Christina Käser Jacober, Paola Mejia Domenzain, Aybars Yazici, Jibril Albachir Frej

Traditional example-based learning methods are often limited by static, expert-created content. Hence, they face challenges in scalability, engagement, and effectiveness, as some learners might struggle to relate to the examples or find them relevant. To a ...

Association for Computing Machinery2024

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Seyed Mohammad Mahdi Johari

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 ...

EPFL2024

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Devis Tuia, Thiên-Anh Claris Nguyen, Marc Conrad Russwurm, Gaston Jean Lenczner

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

Elsevier Science Inc2024

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

Evann Pierre Guy Courdier

Deep learning has revolutionized the field of computer vision, a success largely attributable to the growing size of models, datasets, and computational power. Simultaneously, a critical pain point arises as several computer vision applications are deploye ...

EPFL2024

Aggregating Spatial and Photometric Context for Photometric Stereo

David Honzátko

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

EPFL2024

Social Workers and Irregular Migrants in the Assistance Circuit: Making Sense of Paradoxical Inclusion

Maxime Carl Felder, Joan Stavo-Debauge, Sahar Fneich

Despite restrictive policy frameworks, cities sometimes provide support to irregular migrants. Scholars have analysed these forms of inclusion, focusing on policies and tensions between inclusionary approaches by local or urban actors and exclusionary appr ...

2023

A weakly nonlinear amplitude equation approach to the bypass transition in the two-dimensional Lamb–Oseen vortex

François Gallaire, Yves-Marie François Ducimetière

We analytically derive an amplitude equation for the weakly nonlinear evolution of the linearly most amplified response of a non-normal dynamical system. The development generalizes the method proposed in Ducimetière et al. (J. Fluid Mech., vol. 947, 2022, ...

Cambridge University Press2023

Circularity by stock in Sri Lanka: Economic necessity meets urban fabric renovation

Paolo Tombesi, Milinda Pathiraja

Persistent fiscal and political mismanagement, together with the financial pressures of the COVID-19 pandemic, have driven Sri Lanka into a social and economic crisis triggering a decrease in national foreign exchange reserves, an inability to purchase vit ...

FRONTIERS MEDIA SA2023

A Neural-Network-Based Convex Regularizer for Inverse Problems

Michaël Unser, Stanislas Ducotterd, Pakshal Narendra Bohra, Alexis Marie Frederic Goujon, Sebastian Jonas Neumayer

The emergence of deep-learning-based methods to solve image-reconstruction problems has enabled a significant increase in quality. Unfortunately, these new methods often lack reliability and explainability, and there is a growing interest to address these ...

2023

Improving Object Detection under Domain Shifts

Vidit Vidit

Object detection plays a critical role in various computer vision applications, encompassing domains like autonomous vehicles, object tracking, and scene understanding. These applica- tions rely on detectors that generate bounding boxes around known object ...

EPFL2023

Serial dependence in visual perception: A review

Ayberk Ozkirli, Gizay Ceylan, David Pascucci

How does the visual system represent continuity in the constantly changing visual input? A recent proposal is that vision is serially dependent: Stimuli seen a moment ago influence what we perceive in the present. In line with this, recent frameworks sugge ...

2023

Decision support methodology for waste-to-value process integration

Rafael Amorim Leandro De Castro Amoedo

Waste treatment is a complex procedure that comprises multidimensional aspects. The challenges posed by the energy transition and international protocols emphasize the role of waste in its material and energy dimension. With an increasing population and li ...

EPFL2023

On the role of system integration in plastic waste management

François Maréchal, Ivan Daniel Kantor, Julia Granacher

The management of plastic waste is a growing concern that can harm wildlife and ecosystems, and its end-of-life policies are key to mitigating plastic environmental impact. This work presents a decision-making methodology for the thermal and material valor ...

Elsevier2023

Reinforcement bond performance in 3D concrete printing: Explainable ensemble learning augmented by deep generative adversarial networks

Xianlin Wang

Integrating various reinforcements into 3D concrete printing (3DCP) is an efficient method to satisfy critical requirements for structural applications. This paper explores an explainable ensemble machine learning (EML) method to predict the bond failure m ...

Elsevier2023

Controlled physics-informed data generation for deep learning-based remaining useful life prediction under unseen operation conditions

Jian Zhou, Olga Fink

Limited availability of representative time-to-failure (TTF) trajectories either limits the performance of deep learning (DL)-based approaches on remaining useful life (RUL) prediction in practice or even precludes their application. Generating synthetic d ...

2023

Multi-site, Multi-domain Airway Tree Modeling

Boyu Zhang, Jiancheng Yang, Ying Zhu, Yi Wu

Open international challenges are becoming the de facto standard for assessing computer vision and image analysis algorithms. In recent years, new methods have extended the reach of pulmonary airway segmentation that is closer to the limit of image resolut ...

Elsevier2023

Automated Human Motion Analysis and Synthesis

Sena Kiciroglu

Human motion analysis and synthesis is integral to many computer vision applications, from autonomous driving to sports analysis. In this thesis, we address several problems in this domain. First we consider active viewpoint selection for pose estimation w ...

EPFL2023

The JPEG AI Standard: Providing Efficient Human and Machine Visual Data Consumption

Touradj Ebrahimi

The Joint Photographic Experts Group (JPEG) AI learning-based image coding system is an ongoing joint standardization effort between International Organization for Standardization (ISO), International Electrotechnical Commission (IEC), and International Te ...

IEEE COMPUTER SOC2023

From event-based surprise to lifelong learning. A journey in the timescales of adaptation

Martin Louis Lucien Rémy Barry

Humans and animals constantly adapt to their environment over the course of their life. This thesis seeks to integrate various timescales of adaptation, ranging from the adaptation of synaptic connections between spiking neurons (milliseconds), rapid behav ...

EPFL2023

Surfactant-based enrichment of rare earth elements from NdFeB magnet e-waste: Optimisation of cloud formation and rare earths extraction

Christian Ludwig, Rudolf Paul Wilhelm Jozef Struis, Mohamed Tarik, Ajay Bhagwan Patil

Appropriate waste and resource management are essential for a sustainable circular economy with reduced environmental impact. With critical resources, e-waste may serve as indirect raw material. For example, with NdFeB permanent magnets, Neodymium (Nd) and ...

2023