{"success":true,"data":{"author":"Vajira Thambawita et al., Simula Metropolitan Center for Digital Engineering and OsloMet","bucketAccessType":"public","bucketName":"SimulaMet-HOST/VISEM-Tracking","bucketPrefix":"","category":"Medicine","cloudProvider":"huggingface","createdAt":"2026-11-14T14:15:11.888Z","description":"VISEM-Tracking is a human spermatozoa tracking dataset published in Scientific Data (2023) by Simula and Oslo Metropolitan University. According to the paper it provides 20 video recordings of 30 seconds (29,196 frames) of wet sperm preparations under the microscope, with manually annotated bounding-box coordinates for every frame, a set of sperm characteristics analysed by domain experts, and additional unlabelled video clips for self-supervised or unsupervised learning. Boxes carry three classes: sperm, cluster, and small or pinhead. The authors report baseline detection with YOLOv5, and this repository includes their best YOLOv5 checkpoints. As measured 2026-11-14 the repository, uploaded by the authors' group, holds VISEM_tracking.zip (about 6.4 GB) plus a best_checkpoints folder; unzip to get the videos, extracted frames and YOLO-format label text files, readable with OpenCV and any YOLO toolkit. Used for sperm detection and multi-object tracking, motility and kinematics estimation, and andrology and fertility research. Released under CC BY 4.0 on Zenodo; cite Thambawita et al. 2023.","displayTitle":"VISEM-Tracking: human spermatozoa tracking video dataset","doi":"10.5281/zenodo.7293726","id":"b38cf8e4-c88a-5d90-907d-4aac145035a0","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/records/7293726","objectCountEstimate":121,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2212.02842","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"SimulaMet-HOST/VISEM-Tracking\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"SimulaMet-HOST/VISEM-Tracking\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=SimulaMet-HOST, license:cc-by-4.0, size_categories:n<1K, format:imagefolder, downloads=436"],"format":"mixed","generatedAt":"2026-11-14T14:15:14.542Z","layout":{"example":"best_checkpoints/yolov5l/results.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"               epoch,      train/box_loss,      train/obj_loss,      train/cls_loss,   metrics/precision,      metrics/recall,     metrics/mAP_0.5,metrics/mAP_0.5:0.95,        val/box_loss,        val/obj_loss,        val/cls_loss,               x/lr0,               x/lr1,               x/lr2\n                   0,            0.066245,             0.10754,           0.0089176,             0.26562,             0.22717,             0.16398,            0.051107,            0.057773,              0.1267,        ","encoding":"utf8","key":"best_checkpoints/yolov5l/results.csv","truncatedAt":512}],"sampleObjects":["VISEM_tracking.zip","best_checkpoints/.DS_Store","best_checkpoints/yolov5l/.DS_Store","best_checkpoints/yolov5l/F1_curve.png","best_checkpoints/yolov5l/PR_curve.png"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\ntask_categories:\n- object-detection\ntags:\n- sperm\n- VISEM-Tracking\n- sperm tracking\n- tracking\npretty_name: VISEM-Tracking\nsize_categories:\n- 1B<n<10B\n---\n## To use this dataset for your research, please cite the following preprint. Full-paper will be available soon.\n\n[Preprint](https://arxiv.org/abs/2212.02842)\n\n### Citation:\n@article{thambawita2022visem, \ntitle={VISEM-Tracking: Human Spermatozoa Tracking Dataset}, \nauthor={Thambawita, Vajira and Hicks, Steven A and Stor{\\aa}s, Andrea M and Nguyen, Thu and Andersen, Jorunn M and Witczak, Oliwia and Haugen, Trine B and Hammer, Hugo L, and Halvorsen, P{\\aa}l and Riegler, Michael A}, \njournal={arXiv preprint arXiv:2212.02842}, year={2022} \n}\n☝️ ☝️ ☝️\n\n### Motivation and background\n\nManual evaluation of a sperm sample using a microscope is time-consuming and requires costly experts who have extensive training. In addition, the validity of manual sperm analysis becomes unreliable due to limited reproducibility and high inter-personnel variations due to the complexity of tracking, identifying, and counting sperm in fresh samples. The existing computer-aided sperm analyzer systems are not working well enough for application in a real clinical setting due to unreliability caused by the consistency of the semen sample. Therefore, we need to research new methods for automated sperm analysis.\n\n### Target group\n\nThe task is of interest to researchers in the areas of machine learning (classification and detection), visual content analysis, and multimodal fusion. Overall, this task is intended to encourage the multimedia community to help improve the healthcare system through the application of their knowledge and methods to reach the next level of computer and multimedia-assisted diagnosis, detection, and interpretation.\n\n### Class Label Mapping\nsperm: 0\ncluster: 1\nsmall or pinhead: 2","encoding":"utf8","key":"README.md","name":"README.md","size":1889,"truncated":false}],"sourceObjectKey":"best_checkpoints/yolov5l/results.csv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/SimulaMet-HOST/VISEM-Tracking/best_checkpoints/yolov5l/results.csv\")\ndf.head()","starterSamplePath":"best_checkpoints/yolov5l/F1_curve.png","totalObjects":121},"summary":"VISEM-Tracking is a human spermatozoa tracking dataset published in Scientific Data (2023) by Simula and Oslo Metropolitan University.","title":"VISEM-Tracking: human spermatozoa tracking video dataset","updatedAt":"2026-11-14T17:32:46.568Z","visibility":"public","websiteUrl":"https://zenodo.org/records/7293726"}}