Official implementation of SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference
active 2023-12-16 → 2026-01-25 (UTC)
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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| wangf3014 | 33 | 24 | 0 | 9 |
| KarlLi5 | 5 | 0 | 0 | 3 |
| APeiZou | 3 | 0 | 0 | 1 |
| XiudingCai | 3 | 0 | 0 | 1 |
| kinredon | 3 | 0 | 0 | 1 |
| chenqi1126 | 3 | 0 | 0 | 3 |
| liuhui0401 | 2 | 0 | 0 | 2 |
| Colezwhy | 2 | 0 | 0 | 0 |
| wuwuwuxxx | 2 | 0 | 0 | 1 |
| yiheng003 | 1 | 0 | 0 | 0 |
| Kaisor-Yuan | 1 | 0 | 0 | 1 |
| taiwuyouxu | 1 | 0 | 0 | 0 |
| WuHenry-0609 | 1 | 0 | 0 | 0 |
| WeiCL7777 | 1 | 0 | 0 | 0 |
| changhaonan | 1 | 0 | 0 | 0 |
| dream-toy | 1 | 0 | 0 | 0 |
| xijun-cs | 1 | 0 | 0 | 0 |
| jiinhui | 1 | 0 | 0 | 0 |
| mc-lan | 1 | 0 | 0 | 1 |
| helen1c | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#9ezebk32025-11-28 07:05Using other ViT models yeilds lower miou score
- Issue#18xijun-cs2024-11-10 11:45Attention Map Visualization
- Issue#17helen1c2024-09-21 14:01Reproducing Table 2
- Issue#16APeiZou2024-09-04 04:18训练代码有开源计划吗
- Issue comment#12APeiZou2024-06-21 02:24About the demo
- Issue#16APeiZou2024-06-14 08:20训练代码有开源计划吗
- Issue comment#15wuwuwuxxx2024-04-01 09:44performance degrade when applying a consistent evaluating code with other methods (TCL, GroupVit..)
- Issue comment#15wangf30142024-03-31 02:43performance degrade when applying a consistent evaluating code with other methods (TCL, GroupVit..)
- Issue#15wuwuwuxxx2024-03-30 09:27performance degrade when applying a consistent evaluating code with other methods (TCL, GroupVit..)
- Issue comment#12KarlLi52024-03-04 13:01About the demo
- Issue comment#12Kaisor-Yuan2024-03-03 06:10About the demo
- Issue#13KarlLi52024-03-02 06:51Questions about PAMR
- Issue comment#12KarlLi52024-03-02 06:39About the demo
- Issue comment#12KarlLi52024-02-29 14:55About the demo
- Issue#11WuHenry-06092024-02-12 05:21Reason on a single image and output any category
- Issue#10jiinhui2024-01-31 00:38How to visualize the attention map
- Issue#9yiheng0032024-01-23 12:12Using other ViT models yeilds lower miou score
- Issue comment#7liuhui04012024-01-22 06:37Question about the visualization
- Issue comment#7chenqi11262024-01-22 02:19Question about the visualization
- Issue comment#7liuhui04012024-01-21 18:41Question about the visualization
- Issue#8dream-toy2024-01-21 02:26Code of Learned projection
- Issue#7KarlLi52024-01-19 07:31Question about the visualization
- Issue comment#5mc-lan2024-01-16 09:10Question about performance and hyparameter
- Issue comment#6kinredon2024-01-15 03:26Why directly add the results of q_attn and k_attn instead of normalizing them?
- Issue#6kinredon2024-01-15 03:26Why 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.