Skip to content

[CVPR 2024] Official implementation of the paper "Visual In-context Learning"

active 2023-12-202026-03-27 (UTC)

Partial coverage18,181 / 23,280 hourly files (78%) · 2 absent upstream · 5,098 failed, retryable2023-12-162026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
302
Pushes
7
Pull requests
1
Issues
26
Stars
219
Forks
14

Activity over time

Daily event counts in the loaded window

Line chart, 829 days from 2023-12-20 to 2026-03-27. Pushes: 7 total, peak 4 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 26 total, peak 2 in a day. Comments: 33 total, peak 6 in a day. Stars: 219 total, peak 8 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

Recent activity

Latest issues, pull requests and releases

  • Issue#42wmrenr2025-10-31 02:14
    object detection
  • Issue comment#20JW-Yuan2025-09-09 07:34
    DAVIS17 does not have video_objects_info.json
  • Issue#40wangcsdn192025-07-24 06:33
    训练代码
  • Issue#40wangcsdn192025-07-24 06:19
    训练代码
  • Issue#39zzz1231231231232025-03-28 03:24
    参考分割评估
  • Issue comment#20Adong172025-02-11 01:49
    DAVIS17 does not have video_objects_info.json
  • Issue comment#36CLL1122024-12-24 03:12
    Thanks for your great work, but right now I can't seem to open the demo
  • Issue comment#24kywish2024-10-10 02:40
    请问这个demo是如何使用的
  • Issue#33Tianananana2024-09-20 02:40
    Finetuning model on a single dataset
  • Issue#31sssssshf2024-07-17 03:09
    蒸馏
  • Issue comment#24yongzhouwangbowen2024-07-14 03:20
    请问这个demo是如何使用的
  • Issue comment#30mandal42024-07-09 04:32
    too high CPU usage
  • Issue#30mandal42024-07-09 04:32
    too high CPU usage
  • Issue#30mandal42024-07-09 02:10
    too high CPU usage
  • Issue comment#28eisp-tgq2024-07-04 16:51
    Prompts don't inform mask proposal?
  • Issue comment#19FengLi-ust2024-07-02 05:29
    torch.cat error in evaluation
  • Issue comment#21FengLi-ust2024-07-02 05:27
    Inference code
  • Issue comment#28JoshMSmith442024-07-02 05:27
    Prompts don't inform mask proposal?
  • Issue comment#28FengLi-ust2024-07-02 05:26
    Prompts don't inform mask proposal?
  • Issue comment#27FengLi-ust2024-07-02 05:23
    为什么在训练过程中需要positive and negative visual prompt samples?
  • Issue comment#24FengLi-ust2024-07-02 05:19
    请问这个demo是如何使用的
  • Issue#28JoshMSmith442024-06-29 00:01
    Prompts don't inform mask proposal?
  • Issue comment#10mandal42024-06-27 06:34
    What's the diff between the local demo and online demo?
  • Issue#27dbcSep032024-06-27 06:22
    为什么在训练过程中需要positive and negative visual prompt samples?
  • Issue comment#18mandal42024-06-12 04:28
    Question: example code for input bboxes?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 219 stars here means stars gained during the window, not the repo's star count.