Search Results for author: Vincent Charvillat

Found 4 papers, 1 papers with code

Improving Vehicle Re-Identification using CNN Latent Spaces: Metrics Comparison and Track-to-track Extension

1 code implementation • 21 Oct 2019 • Geoffrey Roman-Jimenez, Patrice Guyot, Thierry Malon, Sylvie Chambon, Vincent Charvillat, Alain Crouzil, André Péninou, Julien Pinquier, Florence Sedes, Christine Sénac

We compared T2TP with I2TP using the same CNN models.

Retrieval Vehicle Re-Identification

Paper
Code

Using Curvilinear Features in Focus for Registering a Single Image to a 3D Object

no code implementations • 26 Feb 2018 • Hatem A. Rashwan, Sylvie Chambon, Pierre Gurdjos, Géraldine Morin, Vincent Charvillat

The results presented highlight the quality of the features detected, in term of repeatability, and also the interest of the approach for registration and pose estimation.

Pose Estimation

Paper
Add Code

Quality Control in Crowdsourced Object Segmentation

no code implementations • 1 May 2015 • Ferran Cabezas, Axel Carlier, Amaia Salvador, Xavier Giró-i-Nieto, Vincent Charvillat

This paper explores processing techniques to deal with noisy data in crowdsourced object segmentation tasks.

Interactive Segmentation Object +2

Paper
Add Code

The toulouse vanishing points dataset

no code implementations • Proceedings of the 6th ACM Multimedia Systems Conference 2015 • Vincent Angladon, Simone Gasparini, Vincent Charvillat

In this paper, we present the Toulouse Vanishing Points Dataset, a public photographs database of Manhattan scenes taken with an iPad Air 1.

Scene Understanding

Paper
Add Code

Cannot find the paper you are looking for? You can Submit a new open access paper.