Skip to content

New generation of CLIP with fine grained discrimination capability, ICML2025

active 2025-04-292026-06-16 (UTC)

Partial coverage11,466 / 12,463 hourly files (92%) · 2 absent upstream · 994 failed, retryable2025-03-092026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
387
Pushes
22
Pull requests
0
Issues
27
Stars
288
Forks
10

Activity over time

Daily event counts in the loaded window

Line chart, 414 days from 2025-04-29 to 2026-06-16. Pushes: 22 total, peak 6 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 27 total, peak 2 in a day. Comments: 38 total, peak 3 in a day. Stars: 288 total, peak 23 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#59Chenjg022026-04-03 07:12
    Stage1 checkpoint
  • Issue#57fjm-NEW2026-03-07 14:47
    已经安装最新的transformers5.3.0,运行测试样例代码还是报依赖问题。
  • Issue#57fjm-NEW2026-03-07 14:38
    已经安装最新的transformers5.3.0,运行测试样例代码还是报依赖问题。
  • Issue comment#55SHN7x2026-01-09 08:34
    关于FineHARD数据集
  • Issue#53SteveTanggithub2025-12-25 09:14
    How can I test the box classification task with the Siglip2 model?
  • Issue comment#48binwang7772025-12-23 09:07
    Question about using SigLIP loss in FG-CLIP
  • Issue comment#45LeoYang062025-12-21 01:40
    如何转换图像侧和文本侧编码器onnx模型
  • Issue comment#45yoletPig2025-11-21 08:23
    如何转换图像侧和文本侧编码器onnx模型
  • Issue#36JJJJerry2025-11-20 03:25
    resize_short_edge函数
  • Issue comment#44binwang7772025-11-19 07:51
    大神 能否使用get_image_dense_feature得到的特征进行检索 。请帮我解答
  • Issue comment#4413015105462025-11-18 03:13
    大神 能否使用get_image_dense_feature得到的特征进行检索 。请帮我解答
  • Issue#45Jayzhen20002025-11-14 07:12
    如何转换图像侧和文本侧编码器onnx模型
  • Issue#43Clearelk2025-11-10 13:43
    FineHARD数据集根本就弄不了呀
  • Issue comment#42yuxie112025-11-10 07:38
    推理分数的范围?
  • Issue comment#39binwang7772025-11-04 07:18
    环境报错
  • Issue#39perfyperfect2025-10-29 05:30
    环境报错
  • Issue#38sanjin-g2025-10-22 06:52
    FG-CLIP最初版本下架了吗
  • Issue comment#37binwang7772025-10-21 10:26
    transformers version
  • Issue comment#36binwang7772025-10-20 02:24
    resize_short_edge函数
  • Issue#36JJJJerry2025-10-17 02:20
    resize_short_edge函数
  • Issue#23david-leon2025-10-17 01:28
    中文情况Chinese search
  • Issue#31geniusxxx2025-10-16 09:53
    When is the fg-clip v2 paper coming?
  • Issue comment#31geniusxxx2025-10-16 09:53
    When is the fg-clip v2 paper coming?
  • Issue#35geniusxxx2025-10-16 09:53
    Input Resolution & Flickr30k Metric in Table 3 (FG-CLIP2 Paper)
  • Issue comment#23yuxie112025-10-16 06:08
    中文情况Chinese search

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 288 stars here means stars gained during the window, not the repo's star count.