An offical repo for ECCV 2024 Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching
active 2024-07-12 → 2026-07-06 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 725 days from 2024-07-12 to 2026-07-06. Pushes: 49 total, peak 15 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 18 total, peak 4 in a day. Comments: 21 total, peak 6 in a day. Stars: 102 total, peak 13 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 |
|---|---|---|---|---|
| TruemanV5 | 59 | 44 | 0 | 7 |
| mistletoe111 | 8 | 0 | 0 | 4 |
| MultimodalGeo | 8 | 5 | 0 | 3 |
| layumi | 2 | 0 | 2 | 0 |
| 554773162 | 2 | 0 | 0 | 2 |
| johnbager | 2 | 0 | 0 | 1 |
| tyrofanfan | 2 | 0 | 0 | 2 |
| zxy1124 | 1 | 0 | 0 | 0 |
| LHL3341 | 1 | 0 | 0 | 0 |
| LiAngCheng-nwpu | 1 | 0 | 0 | 1 |
| ZhouShunlong | 1 | 0 | 0 | 0 |
| wuhaitao2178827 | 1 | 0 | 0 | 1 |
| 1000xLukaoo | 1 | 0 | 0 | 0 |
| NielsRogge | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#13wuhaitao21788272025-12-14 11:26Not enough memory
- Issue comment#13LiAngCheng-nwpu2025-12-11 11:28Not enough memory
- Issue#12zxy11242025-04-15 13:52No case listed in the paper was found
- Issue#11TruemanV52025-03-20 15:06作者您好，想问一下您finetuned一共就花了一轮吗？？
- Issue#10TruemanV52025-03-20 15:04您好，想咨询一下预训练权重。如果我想构建基于您的框架的模型，但是又有所替换，那如何能得到最开始在16M图像上的预训练权重呢？
- Issue comment#10TruemanV52025-03-20 15:04您好，想咨询一下预训练权重。如果我想构建基于您的框架的模型，但是又有所替换，那如何能得到最开始在16M图像上的预训练权重呢？
- Issue comment#9TruemanV52025-03-20 15:02您好，对于那些标签为null的边界框，模型是否会去在测试的时候去进行grounding推理啊；这样不会影响模型的训练吗？
- Issue comment#11tyrofanfan2025-03-18 04:48作者您好，想问一下您finetuned一共就花了一轮吗？？
- Issue comment#115547731622025-03-18 04:40作者您好，想问一下您finetuned一共就花了一轮吗？？
- Issue comment#11tyrofanfan2025-03-10 14:09作者您好，想问一下您finetuned一共就花了一轮吗？？
- Issue comment#115547731622025-03-03 06:34作者您好，想问一下您finetuned一共就花了一轮吗？？
- Issue#11mistletoe1112025-02-09 02:28作者您好，想问一下您finetuned一共就花了一轮吗？？
- Issue#10mistletoe1112025-02-02 08:07您好，想咨询一下预训练权重。如果我想构建基于您的框架的模型，但是又有所替换，那如何能得到最开始在16M图像上的预训练权重呢？
- Issue comment#9mistletoe1112025-02-02 07:53您好，对于那些标签为null的边界框，模型是否会去在测试的时候去进行grounding推理啊；这样不会影响模型的训练吗？
- Issue comment#9TruemanV52025-02-02 04:53您好，对于那些标签为null的边界框，模型是否会去在测试的时候去进行grounding推理啊；这样不会影响模型的训练吗？
- Issue#9mistletoe1112025-02-01 03:27您好，对于那些标签为null的边界框，模型是否会去在测试的时候去进行grounding推理啊；这样不会影响模型的训练吗？
- Issue#8TruemanV52025-01-30 16:05您好，我使用3090一块跑了您的eval代码，发现测出来与您的差异很大，想问一下我应该怎么做
- Issue#7TruemanV52025-01-30 16:05Extension for Geo-localization
- Issue comment#8TruemanV52025-01-30 16:04您好，我使用3090一块跑了您的eval代码，发现测出来与您的差异很大，想问一下我应该怎么做
- Issue comment#8mistletoe1112025-01-30 15:27您好，我使用3090一块跑了您的eval代码，发现测出来与您的差异很大，想问一下我应该怎么做
- Issue comment#8mistletoe1112025-01-30 15:22您好，我使用3090一块跑了您的eval代码，发现测出来与您的差异很大，想问一下我应该怎么做
- Issue comment#7TruemanV52025-01-30 15:22Extension for Geo-localization
- Issue comment#8TruemanV52025-01-30 15:21您好，我使用3090一块跑了您的eval代码，发现测出来与您的差异很大，想问一下我应该怎么做
- Issue comment#8mistletoe1112025-01-30 15:17您好，我使用3090一块跑了您的eval代码，发现测出来与您的差异很大，想问一下我应该怎么做
- Issue#8mistletoe1112025-01-30 15:15您好，我使用3090一块跑了您的eval代码，发现测出来与您的差异很大，想问一下我应该怎么做
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 102 stars here means stars gained during the window, not the repo's star count.