BOboromi·Apr 17, 2021
The official code is a README.md file ?? https://github.com/charigyang/motiongrouping
In Self-Supervised Video Object Segmentation by Motion Groupingcharigyang
motiongrouping
Python2021–2021
charigyang / motiongrouping
motiongrouping
Repository accompanying the paper: Self-supervised Video Object Segmentation by Motion Grouping. C. Yang, H. Lamdouar, E. Lu, A. Zisserman, W. Xie.
2Distinct people
2Mentions
0Explicit recommenders
249GitHub stars
What to know before exploring
What it is
Repository accompanying the paper: Self-supervised Video Object Segmentation by Motion Grouping. C. Yang, H. Lamdouar, E. Lu, A. Zisserman, W. Xie.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by hour2 dated mentions
Observed mentions: 2021-04-17 07:00:34 UTC to 2021-04-17 17:37:43 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Apr 17, 07:00 | 2021-04-17 07:00:00 UTC | 2021-04-17 08:00:00 UTC | 1 | 0 | 1 |
| Apr 17, 08:00 | 2021-04-17 08:00:00 UTC | 2021-04-17 09:00:00 UTC | 0 | 0 | 0 |
| Apr 17, 09:00 | 2021-04-17 09:00:00 UTC | 2021-04-17 10:00:00 UTC | 0 | 0 | 0 |
| Apr 17, 10:00 | 2021-04-17 10:00:00 UTC | 2021-04-17 11:00:00 UTC | 0 | 0 | 0 |
| Apr 17, 11:00 | 2021-04-17 11:00:00 UTC | 2021-04-17 12:00:00 UTC | 0 | 0 | 0 |
| Apr 17, 12:00 | 2021-04-17 12:00:00 UTC | 2021-04-17 13:00:00 UTC | 0 | 0 | 0 |
| Apr 17, 13:00 | 2021-04-17 13:00:00 UTC | 2021-04-17 14:00:00 UTC | 0 | 0 | 0 |
| Apr 17, 14:00 | 2021-04-17 14:00:00 UTC | 2021-04-17 15:00:00 UTC | 0 | 0 | 0 |
| Apr 17, 15:00 | 2021-04-17 15:00:00 UTC | 2021-04-17 16:00:00 UTC | 0 | 0 | 0 |
| Apr 17, 16:00 | 2021-04-17 16:00:00 UTC | 2021-04-17 17:00:00 UTC | 0 | 0 | 0 |
| Apr 17, 17:00 | 2021-04-17 17:00:00 UTC | 2021-04-17 18:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
2 sourcesFantastic. The ability to train without labourious labelling/annotations can really help produce effective models appropriate for real-world use cases.
No code as yet, but looking forward to having it released and playing with it: https://github.com/charigyang/motiongrouping
*Edit: It will be interesting to see if this works Video > Image as well. Much of the current video AI work stems from the image foundation, ie split a video into constituent frames and run detection models on those images. But the image detection/segmentation models assume each image is different, and so the process when parsing video this way is unnecessarily complex - sequential video frames in the same scene are more alike than different.
If good segmentation models for video can be more easily trained using this method, then it would be interesting if they can al
Read the rest
so be applied accurately to still images, since a snapshot of a video is a single image anyway.