Published February 22, 2022 | Version v1

Unsupervised Multiple-Object Tracking with a Dynamical Variational Autoencoder

  • 1. Inria Grenoble Rhône-Alpes
  • 2. Grenoble-INP, Institut Polytechnique de Grenoble

Description

This is the public dataset of synthetic trajectories and MOT17-3T, which is used in paper Unsupervised Multiple-Object Tracking with a Dynamical Variational Autoencoder. The source code can be found here.

Files

MOT17-3T.zip

Files (1.7 GB)

Name Size
md5:e94236dcfedcb0a496130358a409d128
1.7 GB Preview Download
md5:a78b828c8b03f902e7afa2e60d83b4e6
30.9 MB Preview Download