Skip to content

[CVPR2025] Project for "HyperSeg: Towards Universal Visual Segmentation with Large Language Model".

active 2024-11-282026-03-31 (UTC)

Partial coverage14,544 / 17,633 hourly files (82%) · 2 absent upstream · 3,089 failed, retryable2024-08-062026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
121
Pushes
14
Pull requests
0
Issues
8
Stars
89
Forks
3

Activity over time

Daily event counts in the loaded window

Line chart, 489 days from 2024-11-28 to 2026-03-31. Pushes: 14 total, peak 11 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 8 total, peak 1 in a day. Comments: 7 total, peak 1 in a day. Stars: 89 total, peak 6 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
congvvc141400
perp1000
mjhxd1000
ld-xy1000
yytang251000
Adong171000
Xamexer1001
yoon281000
feivellau1001
JayParanjape1000
ForestWang1001
TangSuger71001
MinusOne21001
Zhangtianyun69111001
zhang-yige1000
wanghao155368707321001

Recent activity

Latest issues, pull requests and releases

  • Issue#19mjhxd2026-02-04 08:25
    training code
  • Issue comment#13Zhangtianyun69112025-07-02 10:43
    Results of HyperSeg for Panoptic Segmentation are Low
  • Issue#16yytang252025-06-13 06:06
    When will the training code be released?
  • Issue comment#13TangSuger72025-03-14 03:39
    Results of HyperSeg for Panoptic Segmentation are Low
  • Issue comment#13feivellau2025-03-13 02:11
    Results of HyperSeg for Panoptic Segmentation are Low
  • Issue#11yoon282025-02-21 03:03
    I think I found a bug in your codes
  • Issue#10zhang-yige2025-01-25 06:25
    Will you expand the SEG token to NUM_OBJECT_QUERIES when preparing input labels?
  • Issue comment#7Xamexer2025-01-18 23:38
    Demo for inference a single image with prompt?
  • Issue comment#5wanghao155368707322025-01-14 02:53
    A problem about perciver fuction
  • Issue comment#7MinusOne22025-01-02 06:04
    Demo for inference a single image with prompt?
  • Issue#8ld-xy2024-12-24 03:18
    hello
  • Issue comment#7ForestWang2024-12-23 02:28
    Demo for inference a single image with prompt?
  • Issue#7perp2024-12-21 05:57
    Demo for inference a single image with prompt?
  • Issue#5Adong172024-12-20 02:33
    A problem about perciver fuction
  • Issue#3JayParanjape2024-12-07 20:17
    Using HyperSeg for Panoptic Segmentation

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 89 stars here means stars gained during the window, not the repo's star count.