From Pose to Behavior: Advancing Multi-Individual Pose Estimation and Hierarchical Action Segmentation with Transformers

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Automatically tracking and segmenting every video entity remains a significant challenge. Despite rapid advancements in video segmentation, even state-of-the-art models like SAM 2 struggle to consistently track all entities across a video—a task we refer t ...

Commercial high-voltage circuit breaker (CB) condition monitoring systems rely on directly observable physical parameters such as gas filling pressure with pre-defined thresholds. While these parameters are crucial, they only cover a small subset of malfun ...

Machine learning has experienced significant growth in the smart building sector, whether for building modeling or energy management. Data-driven approaches leverage available measurements to bypass the slow and costly calibration of physics-based models, ...

A multispectral camera setup is used to infer a 2D map of plasma parameters in a tokamak from spectral emissions. However, the light measured by these cameras is line integrated in the toroidal direction, whereas emissivities on the poloidal plane are nece ...

Machine learning has demonstrated superior performance in predicting vast materials properties. However, predicting a spectral-like continuous material property such as phonon density of states (DOS) is more challenging for machine learning. In this work, ...

Retrieval-Augmented Generation (RAG) is a widely used strategy in Large-Language Models (LLMs) to extrapolate beyond the inherent pre-trained knowledge. Hence, RAG is crucial when working in data-sparse fields such as Chemistry. The evaluation of RAG syste ...

Anomaly detection (AD) is essential in identifying rare and often critical events in complex systems, finding applications in fields such as network intrusion detection, financial fraud detection, and fault detection in infrastructure and industrial system ...

Structure-based drug design (SBDD) aims to design small-molecule ligands that bind with high affinity and specificity to pre-determined protein targets. Generative SBDD methods leverage structural data of drugs with their protein targets to propose new dru ...

Healthy aging often entails a decline in cognitive and motor functions, affecting independence and quality of life in older adults. Brain stimulation shows potential to enhance these functions, but studies show variable effects. Previous studies have tried ...

This paper presents a framework for dynamic object catching using a quadruped robot's front legs while it stands on its rear legs. The system integrates computer vision, trajectory prediction, and leg control to enable the quadruped to visually detect, tra ...

DNA-wrapped single-walled carbon nanotubes (DNA-SWCNTs) have demonstrated great versatility as optical sensors. SWCNTs emit a near-infrared fluorescence that is responsive to the slightest changes in their environment, enabling the creation of sensors that ...

In the field of cultural heritage, the use of non-destructive techniques to determine the state ofconservation of an artifact is of the utmost importance, to avoid damage to the object itself. In this paper, we present a data pipeline and several machine l ...

Deep neural networks (DNN) have become an essential tool to tackle challenging tasks in many fields of computer science. However, their high computational complexity limits their applicability. Specialized DNN accelerators have been developed to accommodat ...

Information collected through sensor measurements has the potential to improve knowledge of complex-system behavior, leading to better decisions related to system management. In this situation, and particularly when using digital twins, the quality of sens ...

Near-term quantum devices can be used to build quantum machine learning models, such as quantum kernel methods and quantum neural networks (QNN), to perform classification tasks. There have been many proposals on how to use variational quantum circuits as ...

Tuberculosis (TB) is a major global health challenge, with approximately 1.4 million deaths per year. There is still a need to develop novel treatments for patients infected with Mycobacterium tuberculosis (Mtb). There have been many large-scale phenotypic ...

Modern cities dynamically face several challenges including digitalization, sustainability, resilience and economic development. Urban planners and designers must develop urban forms that address these challenges. With the integration of new communication ...

Improving maintenance scheduling of generation units in an electricity market would increase the safety and reliability of the system. This problem can be modeled as a multi-agent bi-level decision-making problem associated with some safety constraints. In ...

As distribution shifts are inescapable in realistic clinical scenarios due to inconsistencies in imaging protocols, scanner vendors, and across different centers, well-trained deep models incur a domain generalization problem in unseen environments. Despit ...

Forecasting pedestrians' future motions is essential for autonomous driving systems to safely navigate in urban areas. However, existing prediction algorithms often overly rely on past observed trajectories and tend to fail around abrupt dynamic changes, s ...

From Pose to Behavior: Advancing Multi-Individual Pose Estimation and Hierarchical Action Segmentation with Transformers

Chattez avec Graph Search

EntitySAM: Segment Everything in Video

Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers

Fully data-driven and modular building thermal control with physically consistent modeling

Machine learning enhanced tomographic reconstruction for multispectral imaging on TCV

Rapid prediction of phonon density of states by crystal attention graph neural network and high-throughput screening of candidate substrates for wide bandgap electronic cooling

ChemLit-QA: a human evaluated dataset for chemistry RAG tasks

NNG-Mix: Improving Semi-Supervised Anomaly Detection with Pseudo-Anomaly Generation

Structure-based drug design with equivariant diffusion models

Native learning ability and not age determines the effects of brain stimulation

Dynamic Object Catching with Quadruped Robot Front Legs

Prediction of mycotoxin response of DNA-wrapped nanotube sensor with machine learning

Data analysis techniques for the visualization and classification of historical vehicle engines' health status using data-driven solutions

Hardware-Software Co-design for Improved Resource Utilization in DNN Accelerators

Methodology for selecting measurement points that optimize information gain for model updating

Exploring quantum perceptron and quantum neural network structures with a teacher-student scheme

Machine Learning Models for Mycobacterium tuberculosis In Vitro Activity: Prediction and Target Visualization

Reviewing the application of machine learning methods to model urban form indicators in planning decision support systems : potential, issues and challenges

Multi-agent maintenance scheduling of generation unit in electricity market using safe deep reinforcement learning algorithm

OptTTA: Learnable Test-Time Augmentation for Source-Free Medical Image Segmentation Under Domain Shift

Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion