MatchLive-baseline / README.md
Becomebright's picture
Weights and test predictions of MatchLive-baseline
cb6fc97 verified
|
Raw History Blame Contribute Delete
1.77 kB
---
license: other
license_name: mixed
tags:
- soccer
- video-question-answering
- soccernet
---
# MatchLive baseline — weights and test predictions
Files for [MatchLive-baseline](https://github.com/Becomebright/MatchLive-baseline), the
video-based baseline of the
[SoccerNet Challenge 2027 – Soccer Streaming VQA](https://github.com/jyrao/soccernet-streaming-vqa-challenge).
Laid out like the code repository, so the weights download into place from its root:
```bash
hf download Becomebright/MatchLive-baseline --include "checkpoints/*" --local-dir .
```
| Path | Size | What it is |
|---|---|---|
| `checkpoints/rfdetr-l.onnx` | 122 MB | RF-DETR-L detector (ball, goalkeeper, referee, player), ONNX |
| `checkpoints/jersey_dinov3_convnext_tiny-20_matches.onnx` | 112 MB | jersey-number classifier (DINOv3 ConvNeXt-tiny backbone + linear head; numbers 0–99 and "unreadable"), ONNX |
| `results/submission_test.json` | 0.4 MB | MatchLive (`gemini-3.8-flash`): predictions on the 700 test questions, in the challenge's submission format |
| `results/submission_test_qwen.json` | 0.4 MB | MatchLive (`Qwen3.8-27B` served locally): the same |
Accuracy (%), scored with the challenge's `codes/eval_predictions.py`:
| | counting | recall_event_time | recall_event_player | event_team | event_player | causal reasoning | **Average** |
|---|---|---|---|---|---|---|---|
| `submission_test.json` | 58.3 | 82.0 | 96.1 | 96.6 | 96.9 | 76.9 | **84.5** |
| `submission_test_qwen.json` | 42.9 | 70.5 | 79.1 | 84.7 | 72.3 | 53.8 | 67.2 |
## License
The jersey-number classifier is built on a DINOv3 backbone and is subject to Meta's DINOv3
License. The predictions refer to the SoccerNet SN-VQA-2027 test questions, provided by
SoccerNet under its data agreement.