[ICCV 2025] The official PyTorch implementation of Learning Streaming Video Representation via Multitask Training.
active 2025-06-26 → 2026-02-12 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 232 days from 2025-06-26 to 2026-02-12. Pushes: 18 total, peak 7 in a day. Pull requests: 4 total, peak 3 in a day. Issues: 10 total, peak 2 in a day. Comments: 12 total, peak 5 in a day. Stars: 35 total, peak 2 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 |
|---|---|---|---|---|
| Go2Heart | 26 | 16 | 3 | 7 |
| haibara-ai | 11 | 0 | 0 | 4 |
| Kyson9 | 1 | 0 | 0 | 0 |
| BodongDu | 1 | 0 | 0 | 1 |
| dependabot[bot] | 1 | 0 | 1 | 0 |
| zhouyuan888888 | 1 | 0 | 0 | 0 |
| dakloepfer | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#13zhouyuan8888882025-12-31 13:41question about fixed frame number
- Issue#11haibara-ai2025-12-16 09:25Is Streamformer-Qwen2.5 version finetuned with the same recipe of Streamformer-Vicuna in the paper?
- Issue comment#11haibara-ai2025-11-18 03:20Is Streamformer-Qwen2.5 version finetuned with the same recipe of Streamformer-Vicuna in the paper?
- Issue comment#12Go2Heart2025-11-17 14:04call for Datasets Annotations.
- Issue comment#12BodongDu2025-11-13 04:04call for Datasets Annotations.
- Issue#11haibara-ai2025-10-29 01:30Is Streamformer-Qwen2.5 version finetuned with the same recipe of Streamformer-Vicuna in the paper?
- Issue comment#10Go2Heart2025-10-16 07:07Where can we find the text labels or prompt template of the pre-training data?
- Issue comment#9haibara-ai2025-10-16 07:00Question about VQA benchmark reproducing
- Issue#9haibara-ai2025-10-16 07:00Question about VQA benchmark reproducing
- Issue comment#9haibara-ai2025-10-09 02:10Question about VQA benchmark reproducing
- Issue comment#9Go2Heart2025-09-25 08:41Question about VQA benchmark reproducing
- Issue comment#9Go2Heart2025-09-25 07:29Question about VQA benchmark reproducing
- Issue comment#9Go2Heart2025-09-25 06:42Question about VQA benchmark reproducing
- Issue comment#6Go2Heart2025-09-25 05:49How to reproduce the metric number on VQA/MLVU task?
- Issue comment#6haibara-ai2025-09-25 05:45How to reproduce the metric number on VQA/MLVU task?
- Issue comment#6Go2Heart2025-09-24 06:32How to reproduce the metric number on VQA/MLVU task?
- Pull request#7dependabot[bot]2025-09-24 06:30
- Issue#5haibara-ai2025-09-12 07:36Download link of OAD pre-compute features is broken
- Issue#5haibara-ai2025-09-11 07:21Download link of OAD pre-compute features is broken
- Issue#5haibara-ai2025-09-10 07:59Download link of OAD pre-compute features is broken
- Issue#5haibara-ai2025-09-10 07:52Download link of OAD pre-compute features is broken
- Issue#4dakloepfer2025-09-04 21:38Video-QA Checkpoints
- Issue#3Kyson92025-08-28 02:44Are there any experiments on classification retrieval tasks?
- Pull request#2Go2Heart2025-07-13 09:07
- Pull request#2Go2Heart2025-07-13 09:07
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 35 stars here means stars gained during the window, not the repo's star count.