Instance-level video segmentation from object tracks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Instance-level video segmentation from object tracks


We address the problem of segmenting multiple object instances in complex videos. Our method does not require manual pixel-level annotation for training, and relies instead on readily-available object detectors or visual object tracking only. Given object bounding boxes at input, we cast video segmentation as a weakly-supervised learning problem. Our proposed objective combines (a) a discrim-inative clustering term for background segmentation, (b) a spectral clustering one for grouping pixels of same object instances, and (c) linear constraints enabling instance-level segmentation. We propose a convex relaxation of this problem and solve it efficiently using the Frank-Wolfe algorithm. We report results and compare our method to several base-lines on a new video dataset for multi-instance person seg-mentation.
Fichier principal
Vignette du fichier
seguin2016multi.pdf (2.88 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01255765 , version 1 (13-01-2016)


  • HAL Id : hal-01255765 , version 1


Guillaume Seguin, Piotr Bojanowski, Rémi Lajugie, Ivan Laptev. Instance-level video segmentation from object tracks. CVPR 2016, IEEE, Jun 2016, Las Vegas, United States. ⟨hal-01255765⟩
630 View
1277 Download


Gmail Facebook X LinkedIn More