Publication

Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction

Related publications (33)

Graph Chatbot

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.

Understanding the H2/HI ratio in galaxies

Danail Obreschkow

We revisit the mass ratio R between molecular hydrogen (H2) and atomic hydrogen (HI) in different galaxies from a phenomenological and theoretical viewpoint. First, the local H2 mass function (MF) is estimated from the local CO luminosity function (LF) of ...

Wiley-Blackwell2009

Hydro Elastic Behavior of Vibrating Blades

François Avellan, Mohamed Farhat, Philippe Ausoni, Olivier Braun

Fluid-structure investigations in hydraulic machines using coupled simulations are extremely time-consuming; therefore we develop an alternative method. In this paper, a model is proposed to predict fluid-structure coupling by linearizing the hydrodynamic ...

International Association For Hydraulic Research2008

Brownian motion studied with an optical trap

Branimir Lukic

This thesis describes measurements of Brownian motion of a colloidal particle using optical trapping. Two aspects are investigated: (i) influence of inertial effects on Brownian motion, and (ii) effect of the optical trap on Brownian motion. The first part ...

EPFL2008

Local velocity-adapted motion events for spatio-temporal recognition

Barbara Caputo

In this paper we address the problem in motion recognition using event-based local motion representations. We assume that similar patterns of motion contain similar events with consistent motion across image sequences. Using this assumption, we formulate t ...

2007

Embedding Motion in Model-Based Stochastic Tracking

Daniel Gatica-Perez, Jean-Marc Odobez, Silèye Oumar Ba

Particle filtering (PF) is now established as one of the most popular methods for visual tracking. Within this framework, two assumptions are generally made. The first is that the data are temporally independent given the sequence of object states, and the ...

2006

Optimized Motion Simplification for Crowd Animation

Junghyun Ahn

Simulating a huge number of articulate figures in a real-time application is one of the challenging research topics in character animation. Several researchers have tried to improve the performance of animation using the image-based technique such as ‘impo ...

Wiley-Blackwell2006

A biomechanics-based articulation model for medical applications

Anderson Maciel

Computer Graphics came into the medical world especially after the arrival of 3D medical imaging. Computer Graphics techniques are already integrated in the diagnosis procedure by means of the visual tridimensional analysis of computer tomography, magnetic ...

EPFL2005

Motion Level-of-Detail: A Simplification Method on Crowd Scene

Junghyun Ahn

Recent technological improvement in character animation has increased the number of characters that can appear in a virtual scene. Besides, skeletal and mesh structures are expected to be more complex in the future. Therefore, simulating massive characters ...

2004

Embedding motion in model-based stochastic tracking

Daniel Gatica-Perez, Jean-Marc Odobez

2004

Motion likelihood and proposal modeling in Model-Based Stochastic Tracking

Daniel Gatica-Perez, Jean-Marc Odobez

Particle filtering is now established as one of the most popular methods for visual tracking. Within this framework, there are two important considerations. The first one refers to the generic assumption that the observations are temporally independent giv ...

IDIAP2004