Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction

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.

Balancing economic and environmental goals in industrial applications is critical amid challenges like climate change. Multi-objective optimization (MOO) and multi-criteria decision analysis (MCDA) are key tools for addressing conflicting objectives. MOO g ...

In the standard model of particle physics, the chiral anomaly can occur in relativistic plasmas and plays a role in the early Universe, protoneutron stars, heavy-ion collisions, and quantum materials. It gives rise to a magnetic instability if the number d ...

We analyze and compare the satellite halo populations at z similar to 2 in the high-resolution cosmological zoom-in simulations of a 1012 M circle dot target halo (z = 0 mass) carried out on eight widely used astrophysical simulation codes (Art-I, Enzo, Ra ...

ML-based edge devices may face memory and computational errors that affect applications' reliability and performance. These errors can be the result of particular working conditions (e.g., radiation areas in physical experiments or avionics) or could be th ...

A rare case of a quasar acting as a gravitational lens allows a precise determination of the mass of the quasar's host galaxy and offers a new path to studying the connections between supermassive black holes and their host galaxies. ...

Deepfakes - synthetic videos generated by machine learning models - are becoming increasingly sophisticated. While they have several positive use cases, their potential for harm is also high. Deepfake production involves input from multiple engineers, maki ...

Purpose: To develop a self-navigated motion compensation strategy for 3D radial MRI that can compensate for continuous head motion by measuring rigid body motion parameters with high temporal resolution from the central k-space acquisition point (self-enco ...

Data-driven building energy modeling is an emerging solution to facilitate the implementation of energy-flexible buildings. However, its black-box nature hinders interpretation, including with respect to human-building interaction. This drawback may bring ...

Most large galaxies contain Super Massive Black Holes at their centers, drawing matter nearby to form swirling accretion disks emitting electromagnetic radiation. These are Active Galactic Nuclei. The brightest quasars are the most luminous Universe object ...

Biological motor control is versatile, efficient, and depends on proprioceptive feedback. Muscles are flexible and undergo continuous changes, requiring distributed adaptive control mechanisms that continuously account for the body's state. The canonical r ...

In the theory of the bottom-up assembly of cosmic structures, one of the main challenges is to connect the smallest, most inconspicuous galaxies we observe today to the building blocks of more massive galaxies such as our own, the Milky Way. Do these so-ca ...

Weak-lensing studies via cosmic voids are a promising probe of modified gravity (MG). The excess surface mass density (ESD) is widely used as a lensing statistic in weak-lensing research. In this paper, we use the ray-tracing method to study the ESD around ...

We tackle the task of diverse 3D human motion prediction, that is, forecasting multiple plausible future 3D poses given a sequence of observed 3D poses. In this context, a popular approach consists of using a Conditional Variational Autoencoder (CVAE). How ...

It is well known since the works of Utiyama and Kibble that the gravitational force can be obtained by gauging the Poincare group, which puts gravity on the same footing as the standard model fields. The resulting theory-Einstein-Cartan gravity-inevitably ...

Astrobot swarms are used to capture astronomical signals to generate the map of the observable universe for the purpose of dark energy studies. The convergence of each swarm in the course of its coordination has to surpass a particular threshold to yield a ...

Context. The study of galaxy cluster mass profiles (M(r)) provides constraints on the nature of dark matter and on physical processes affecting the mass distribution. The study of galaxy cluster velocity anisotropy profiles (beta (r)) informs the orbits of ...

In this paper, we propose a framework to build a memory of motion for warm-starting an optimal control solver for the locomotion task of a humanoid robot. We use HPP Loco3D, a versatile locomotion planner, to generate offline a set of dynamically consisten ...

Tip Vortex Cavitation (TVC) is a major issue in design and operation of axial hydraulic machines. We investigate the capacity of a flexible trailing thread in alleviating TVC by analyzing the flow-induced motion. For this purpose, a nylon thread with three ...

An asymmetry in the number density of left- and right-handed fermions is known to give rise to a new term in the induction equation that can result in a dynamo instability. At high temperatures, when a chiral asymmetry can survive for long enough, this chi ...

Purpose: To develop a novel framework for rapid, intrinsic head motion measurement in MRI using FID navigators (FIDnavs) from a multichannel head coil array. ...

Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction

Chat with Graph Search

On the role of artificial intelligence in feature oriented multi-criteria decision analysis

Chiral Anomaly and Dynamos from Inhomogeneous Chemical Potential Fluctuations

The AGORA High-resolution Galaxy Simulations Comparison Project. V. Satellite Galaxy Populations in a Cosmological Zoom-in Simulation of a Milky Way-Mass Halo

Hardware-Software co-design Methodologies for Edge AI Optimization

Strong gravitational lensing by AGNs as a probe of the quasar-host relations in the distant Universe

A multimodal measurement of the impact of deepfakes on the ethical reasoning and affective reactions of students

Rapid motion estimation and correction using self-encoded FID navigators in 3D radial MRI

OccuVAE: Integrating unsupervised occupancy inference in data-driven energy modeling for human-centric operation

Strong and micro lensing in distant quasars

Contrasting action and posture coding with hierarchical deep neural network models of proprioception

The formation of the faintest galaxies in cosmological simulations: from the impact of primordial magnetic fields to the metal enrichment of present day dwarfs by first stars

Void Lensing in Cubic Galileon Gravity

Contextually Plausible and Diverse 3D Human Motion Prediction

Einstein-Cartan Portal to Dark Matter

Learning convergence prediction of astrobots in multi-object spectrographs

The GOGREEN survey: Internal dynamics of clusters of galaxies at redshift 0.9-1.4

Learning How to Walk: Warm-starting Optimal Control Solver with Memory of Motion

Mitigating tip vortex cavitation by a flexible trailing thread

Energetics of turbulence generated by chiral MHD dynamos

Head motion measurement and correction using FID navigators