Publication

Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking

Related publications (27)

Device for measuring a force exerted on an object

Simon Nessim Henein, Charles Baur, Mohammad Hussein Kahrobaiyan, Mohamed Gamal Abdelrahman Ahmed Zanaty

The present invention relates to a device for measuring a contact force exerted by an object on a probe comprising a lever and said probe for contacting the object. The lever is pivotably coupled to a body by coupling means. The device comprising a fixed f ...

2020

Statistical Aspects of Wasserstein Distances

Victor Panaretos, Yoav Zemel

Wasserstein distances are metrics on probability distributions inspired by the problem of optimal mass transportation. Roughly speaking, they measure the minimal effort required to reconfigure the probability mass of one distribution in order to recover th ...

ANNUAL REVIEWS2019

Engineered nanostructures' characterization by spectral interferometric microscopy

Toralf Scharf, Michail Symeonidis

We characterize engineered nanostructures with sizes smaller than half a wavelength using spectrally resolved interferometry. We analyze the response of the meta-atom of interest, which has a raspberry-like geometry. To identify the origin of the response, ...

SPIE-INT SOC OPTICAL ENGINEERING2019

Segmentation-driven 6D Object Pose Estimation

Pascal Fua, Mathieu Salzmann, Joachim Ludovic Hugonot, Yinlin Hu

The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algorithm. I ...

IEEE2019

Methods and apparatus for three-dimensional fabrication by tomographic back projections

Christophe Moser, Damien Claude-Marie Loterie, Paul Delrot

A method for producing a three-dimensional object comprising computing a sequence of back-projections describing the three-dimensional object to be formed from different orientation angles of said object, defining a sequence of patterns of light using said ...

2019

Training Algorithms for Multiple Object Tracking

Andrii Maksai

Multiple object tracking is a crucial Computer Vision Task. It aims at locating objects of interest in the image sequences, maintaining their identities, and identifying their trajectories over time. A large portion of current research focuses on tracking ...

EPFL2019

Espace public comme objet per se? Une analyse critique de la conception contemporaine

Sonia Monique Curnier

The recognition during the second half of the 20th century of the essential role played by public spaces in the definition of qualitative urban life has led to a reconsideration of their design. This has occurred in many different forms, such as the emerge ...

EPFL2018