{"success":true,"data":{"author":"Sainte Fare Garnot, Landrieu, Chehata (IGN France / LASTIG); TACO repackaging by ISP, Universitat de Valencia","bucketAccessType":"public","bucketName":"isp-uv-es/pastis-r-taco","bucketPrefix":"","category":"Agriculture & Environment","cloudProvider":"huggingface","createdAt":"2026-11-16T14:11:25.634Z","description":"PASTIS-R is the radar-augmented version of PASTIS, the reference benchmark for panoptic segmentation of agricultural parcels from satellite image time series (ICCV 2021; ISPRS 2022). It has 2,433 patches of 128x128 pixels at 10 m over four Sentinel-2 tiles in France, each with a full year of Sentinel-2 L2A (10 bands, 37 to 61 dates), Sentinel-1 ascending orbit (3 layers, 65 to 71 dates) and Sentinel-1 descending orbit (69 to 70 dates). Targets are an 18-crop semantic map built from the French Land Parcel Identification System, plus the parcel identifier of every pixel for instance and panoptic evaluation with metrics such as panoptic quality. The release defines five cross-validation folds; this copy uses folds 1-3, 4 and 5 as train, validation and test (1,455, 482, 496) and carries the fold so any 5-fold run can be rebuilt. Series keep their native variable length. About 53 GB in TACO format, read with tacoreader. Original on Zenodo under CC BY 4.0; cite Sainte Fare Garnot and Landrieu 2021.","displayTitle":"PASTIS-R: Panoptic Segmentation of Agricultural Parcels from Sentinel-1 and Sentinel-2 Time Series (TACO)","doi":"10.1109/ICCV48922.2021.00483","id":"665ac57a-0fb6-5abd-ad09-56c0902d796e","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/records/5735646","objectCountEstimate":17,"probeStatus":"ok","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"isp-uv-es/pastis-r-taco\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"isp-uv-es/pastis-r-taco\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=isp-uv-es, license:cc-by-4.0, size_categories:1K<n<10K, downloads=123"],"format":"mixed","generatedAt":"2026-11-16T14:11:34.407Z","layout":{"example":"assets/logos.png","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"assets/logos.png","truncatedAt":512}],"sampleObjects":["assets/logos.png","assets/sample_0.png","assets/sample_1.png","assets/sample_2.png","assets/sample_3.png"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\npretty_name: \"PASTIS-R (panoptic agricultural time series, optical + SAR)\"\nsize_categories:\n- 1K<n<10K\ntask_categories:\n- image-segmentation\ntags:\n- earth-observation\n- remote-sensing\n- taco\n---\n\n<p align=\"center\"><img src=\"assets/logos.png\" width=\"546\" alt=\"Image and Signal Processing Group, Universitat de València · ELLIOT\"></p>\n\n# PASTIS-R (panoptic agricultural time series, optical + SAR)\n\n> **This is a repackaging, not a new dataset.** It is **PASTIS-R (panoptic agricultural time series, optical + SAR)** by IGN France (Sainte Fare Garnot and Landrieu), ESA Copernicus / Sentinel-1, Sentinel-2, converted to TACO. Pixel values and labels are kept as released except where the description below says otherwise. All credit belongs to the original authors: if you use it, please cite them and follow their licence.\n>\n> [original dataset](https://github.com/VSainteuf/pastis-benchmark) · [paper](https://doi.org/10.1109/ICCV48922.2021.00483) · licence: CC-BY-4.0\n>\n> Repackaged into TACO by the [Image and Signal Processing Group (ISP)](https://isp.uv.es/), Universitat de València, within the [ELLIOT](https://elliot-ai.eu) project.\n\n## Citation\n\nPlease cite the original work:\n\n```bibtex\n@inproceedings{garnot2021pastis,\n  title     = {Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks},\n  author    = {Sainte Fare Garnot, Vivien and Landrieu, Loic},\n  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},\n  pages     = {4852--4861},\n  year      = {2021},\n  doi       = {10.1109/ICCV48922.2021.00483}\n}\n@article{garnot2022multimodal,\n  title   = {Multi-modal temporal attention models for crop mapping from satellite time series},\n  author  = {Sainte Fare Garnot, Vivien and Landrieu, Loic and Chehata, Nesrine},\n  journal = {ISPRS Journal of Photogrammetry and Remote Sensing},\n  volume  = {187},\n  pages   = {294--305},\n  year    = {2022},\n  doi     = {10.1016/j.isprsjprs.2022.03.012}\n}\n```\n\n## About the data\n\n2433 patches of 128x128 at 10 m over four Sentinel-2 tiles in France, each with a full year of Sentinel-2 L2A (10 bands, 37-61 frames), Sentinel-1 ascending (3 layers, 65-71) and Sentinel-1 descending (69-70).\n\n**2,433 samples** · splits: `test` 496 · `train` 1,455 · `validation` 482 · tasks: `panoptic-segmentation`, `semantic-segmentation`\n\nPackaged as [TACO v3](https://asterisk.coop/taco/spec/).\n\n<details>\n<summary>Full description</summary>\n\n**Target.** Panoptic segmentation of agricultural parcels: an 18-crop semantic map plus the land-register parcel id of every pixel.\n\n**Series.** All three are variable leaves, so no frame is fabricated to make them a common length.\n\n**Splits.** The release ships five cross-validation folds and no split. Folds 1-3/4/5 are used as train/val/test, and the fold is carried, so a 5-fold run needs nothing from the source: train 1455, val 482, test 496.\n\n</details>\n\n## Getting started\n\n```bash\ngit clone --recursive https://github.com/OscarPellicer/taco\npip install -e \"taco/python[ml]\"     # builds the reader: C++23, CMake, Ninja, pkg-config, libcurl >= 7.83, OpenSSL >= 3\n```\n\nRead it straight from the Hub:\n\n```python\nfrom huggingface_hub import snapshot_download\nfrom taco.ml import Dataset, plot_sample\n\npath = snapshot_download(\"isp-uv-es/pastis-r-taco\", repo_type=\"dataset\")\nds = Dataset(path)                  # the repository is the container: parts + .tacocat\nplot_sample(ds[0])\n```\n\nor from a local copy:\n\n```python\nds = Dataset(\"pastis-r\")\nsample = ds[0]                      # {slot name: SlotValue}, arrays decoded\nsample[\"s2\"].array.shape\n```\n\nMetadata without decoding anything:\n\n```python\nimport taco\ntaco.read(\"pastis-r/.tacocat\")              # one Arrow table, levels joined\n```\n\n## Samples\n\n![sample](assets/sample_0.png)\n![sample](assets/sample_1.png)\n![sample](assets/sample_2.png)\n![sample](assets/sample_3.png)\n![sample](assets/sample_4.png)\n\n## What a sample contains\n\n| role | slot | holds | modality | detail |\n|---|---|---|---|---|\n| input | `s2` | raster_series | multispect","encoding":"utf8","key":"README.md","name":"README.md","size":4927,"truncated":true}],"sourceObjectKey":"assets/logos.png","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"isp-uv-es/pastis-r-taco\", filename=\"assets/logos.png\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"assets/logos.png","totalObjects":17},"summary":"PASTIS-R is the radar-augmented version of PASTIS, the reference benchmark for panoptic segmentation of agricultural parcels from satellite image time series (ICCV 2021; ISPRS…","title":"PASTIS-R: Panoptic Segmentation of Agricultural Parcels from Sentinel-1 and Sentinel-2 Time Series (TACO)","updatedAt":"2026-11-16T16:13:08.849Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/isp-uv-es/pastis-r-taco"}}