| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Instance-level video segmentation from object tracks
Abstract : 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.
Cited literature [46 references]
https://hal.inria.fr/hal-01255765
Contributor : Guillaume Seguin <>
Submitted on : Wednesday, January 13, 2016 - 10:44:29 PM
Last modification on : Wednesday, October 14, 2020 - 4:11:35 AM
Long-term archiving on: : Friday, November 11, 2016 - 5:04:25 AM
Contributor : Guillaume Seguin <>
Submitted on : Wednesday, January 13, 2016 - 10:44:29 PM
Last modification on : Wednesday, October 14, 2020 - 4:11:35 AM
Long-term archiving on: : Friday, November 11, 2016 - 5:04:25 AM
File
seguin2016multi.pdf
Files produced by the author(s)