Skip to content

Official implementation of SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

active 2023-12-162026-01-25 (UTC)

Complete coverage26,528 / 26,528 hourly files (100%) · 2 absent upstream2023-08-152026-08-24 (UTC)
Events
247
Pushes
24
Pull requests
0
Issues
20
Stars
161
Forks
14

Activity over time

Daily event counts in the loaded window

Line chart, 772 days from 2023-12-16 to 2026-01-25. Pushes: 24 total, peak 22 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 20 total, peak 2 in a day. Comments: 24 total, peak 3 in a day. Stars: 161 total, peak 12 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
wangf3014332409
KarlLi55003
APeiZou3001
XiudingCai3001
kinredon3001
chenqi11263003
liuhui04012002
Colezwhy2000
wuwuwuxxx2001
yiheng0031000
Kaisor-Yuan1001
taiwuyouxu1000
WuHenry-06091000
WeiCL77771000
changhaonan1000
dream-toy1000
xijun-cs1000
jiinhui1000
mc-lan1001
helen1c1000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#9ezebk32025-11-28 07:05
    Using other ViT models yeilds lower miou score
  • Issue#18xijun-cs2024-11-10 11:45
    Attention Map Visualization
  • Issue#17helen1c2024-09-21 14:01
    Reproducing Table 2
  • Issue#16APeiZou2024-09-04 04:18
    训练代码有开源计划吗
  • Issue comment#12APeiZou2024-06-21 02:24
    About the demo
  • Issue#16APeiZou2024-06-14 08:20
    训练代码有开源计划吗
  • Issue comment#15wuwuwuxxx2024-04-01 09:44
    performance degrade when applying a consistent evaluating code with other methods (TCL, GroupVit..)
  • Issue comment#15wangf30142024-03-31 02:43
    performance degrade when applying a consistent evaluating code with other methods (TCL, GroupVit..)
  • Issue#15wuwuwuxxx2024-03-30 09:27
    performance degrade when applying a consistent evaluating code with other methods (TCL, GroupVit..)
  • Issue comment#12KarlLi52024-03-04 13:01
    About the demo
  • Issue comment#12Kaisor-Yuan2024-03-03 06:10
    About the demo
  • Issue#13KarlLi52024-03-02 06:51
    Questions about PAMR
  • Issue comment#12KarlLi52024-03-02 06:39
    About the demo
  • Issue comment#12KarlLi52024-02-29 14:55
    About the demo
  • Issue#11WuHenry-06092024-02-12 05:21
    Reason on a single image and output any category
  • Issue#10jiinhui2024-01-31 00:38
    How to visualize the attention map
  • Issue#9yiheng0032024-01-23 12:12
    Using other ViT models yeilds lower miou score
  • Issue comment#7liuhui04012024-01-22 06:37
    Question about the visualization
  • Issue comment#7chenqi11262024-01-22 02:19
    Question about the visualization
  • Issue comment#7liuhui04012024-01-21 18:41
    Question about the visualization
  • Issue#8dream-toy2024-01-21 02:26
    Code of Learned projection
  • Issue#7KarlLi52024-01-19 07:31
    Question about the visualization
  • Issue comment#5mc-lan2024-01-16 09:10
    Question about performance and hyparameter
  • Issue comment#6kinredon2024-01-15 03:26
    Why directly add the results of q_attn and k_attn instead of normalizing them?
  • Issue#6kinredon2024-01-15 03:26
    Why directly add the results of q_attn and k_attn instead of normalizing them?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 161 stars here means stars gained during the window, not the repo's star count.