|
Download README.md from playbox-dev/SparseQID: direct link, hf CLI and curl.
- Browser
- Download file 1.41 kB
-
https://huggingface.co/playbox-dev/SparseQID/resolve/main/README.md
- Command line
-
hf download hf://playbox-dev/SparseQID/README.md
-
curl -L -o README.md https://huggingface.co/playbox-dev/SparseQID/resolve/main/README.md
1.41 kB
| license: other | |
| license_name: nvidia-open-model-license | |
| license_link: https://huggingface.co/playbox-dev/SparseQID/blob/main/LICENSE | |
| datasets: | |
| - nvidia/PhysicalAI-SmartSpaces | |
| tags: | |
| - computer-vision | |
| - multi-object-tracking | |
| - multi-camera-tracking | |
| - 3d-tracking | |
| # SparseQID checkpoints | |
| Checkpoints for **Online Multi-Camera 3D Tracking via ID Prediction over | |
| Recurrent Sparse Queries**. Source code and instructions are available at | |
| [playbox-dev/SparseQID](https://github.com/playbox-dev/SparseQID). | |
| The submitted model is `ngc-frozen_v128_pe30_it6k.pth`. It achieved 38.01 HOTA | |
| on the 2026 AI City Challenge Track 1 test set. | |
| ## Download | |
| Run from the SparseQID source repository: | |
| ```bash | |
| hf download playbox-dev/SparseQID \ | |
| --include "checkpoints/**" \ | |
| --local-dir . | |
| ``` | |
| ## Files | |
| | Checkpoint | Use | | |
| |---|---| | |
| | `ngc-frozen_v128_pe30_it6k.pth` | Submitted model; frozen NGC detector | | |
| | `ngc-joint_v128_pe30_it5k.pth` | Joint detector and identity training | | |
| | `ngc-ft4k-frozen_v128_pe30_it8k.pth` | Frozen finetuned detector | | |
| | `ngc-ft4k-joint_v128_pe30_it2k.pth` | Joint training with finetuned detector | | |
| | `tok-appearance_v128_pe30_it2k.pth` | Appearance-token ablation | | |
| | `tok-pos-fourier_v128_pe30_it2k.pth` | Fourier-position-token ablation | | |
| | `tok-pos-raw_v128_pe30_it2k.pth` | Raw-position-token ablation | | |
| ## License | |
| See [LICENSE](LICENSE) and [NOTICE](NOTICE). | |