{"url":"/dataset/street-scene","name":"Street Scene","full_name":null,"description_markdown":"**Street Scene** is a dataset for video anomaly detection. Street Scene consists of 46 training and 35 testing high resolution 1280×720 video sequences taken from a USB camera overlooking a scene of a two-lane street with bike lanes and pedestrian sidewalks during daytime. The dataset is challenging because of the variety of activity taking place such as cars driving, turning, stopping and parking; pedestrians walking, jogging and pushing strollers; and bikers riding in bike lanes. In addition the videos contain changing shadows, moving background such as a flag and trees blowing in the wind, and occlusions caused by trees and large vehicles. There are a total of 56,847 frames for training and 146,410 frames for testing, extracted from the original videos at 15 frames per second. The dataset contains a total of 205 naturally occurring anomalous events ranging from illegal activities such as jaywalking and illegal U-turns to simply those that do not occur in the training set such as pets being walked and a metermaid ticketing a car.\r\n\r\nSource: [A Survey of Single-SceneVideo Anomaly Detection](https://arxiv.org/abs/2004.05993)\r\nImage Source: [https://www.merl.com/demos/video-anomaly-detection](https://www.merl.com/demos/video-anomaly-detection)","description_withheld":null,"homepage":"https://www.merl.com/demos/video-anomaly-detection","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/street-scene-a-new-dataset-and-evaluation","title":"Street Scene: A new dataset and evaluation protocol for video anomaly detection","first_author":"Bharathkumar Ramachandra","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Anomaly Detection","url":"/task/anomaly-detection","datasets_with_task":"/datasets/task/anomaly-detection"},{"name":"Video Anomaly Detection","url":"/task/video-anomaly-detection","datasets_with_task":"/datasets/task/video-anomaly-detection"},{"name":"Video-to-Video Synthesis","url":"/task/video-to-video-synthesis","datasets_with_task":"/datasets/task/video-to-video-synthesis"}],"languages":[],"variants":["Street Scene"],"data_loaders":[],"num_papers_in_archive":26,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/anomaly-detection-on-street-scene","task":"Anomaly Detection","dataset_variant":"Street Scene","rows":1,"metrics":["AUC","RBDC","TBDC"],"first_row_in_archive_order":{"model":"PGM","paper":"/paper/bounding-boxes-and-probabilistic-graphical","metrics":{"AUC":"72.7","RBDC":"30.65","TBDC":"66.03"},"code_links":[{"title":"milestonesys-research/vad-with-pgms","url":"https://github.com/milestonesys-research/vad-with-pgms"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-anomaly-detection-on-street-scene","task":"Video Anomaly Detection","dataset_variant":"Street Scene","rows":1,"metrics":["AUC","RBDC","TBDC"],"first_row_in_archive_order":{"model":"PGM","paper":"/paper/bounding-boxes-and-probabilistic-graphical","metrics":{"AUC":"72.7","RBDC":"30.65","TBDC":"66.03"},"code_links":[{"title":"milestonesys-research/vad-with-pgms","url":"https://github.com/milestonesys-research/vad-with-pgms"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-to-video-synthesis-on-street-scene","task":"Video-to-Video Synthesis","dataset_variant":"Street Scene","rows":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"Few-shot Video-to-Video","paper":"/paper/few-shot-video-to-video-synthesis","metrics":{"FID":"144.24"},"code_links":[{"title":"NVlabs/few-shot-vid2vid","url":"https://github.com/NVlabs/few-shot-vid2vid"},{"title":"livingbio/fewshot-vid2vid","url":"https://github.com/livingbio/fewshot-vid2vid"},{"title":"achen353/imaginaire-fsvid2vid","url":"https://github.com/achen353/imaginaire-fsvid2vid"},{"title":"k4rth33k/vid_to_vid_python3","url":"https://github.com/k4rth33k/vid_to_vid_python3"},{"title":"FredMusoro/few-few","url":"https://github.com/FredMusoro/few-few"},{"title":"rickyHong/few-shot-vid2vid-repl","url":"https://github.com/rickyHong/few-shot-vid2vid-repl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/bounding-boxes-and-probabilistic-graphical","title":"Bounding Boxes and Probabilistic Graphical Models: Video Anomaly Detection Simplified","date":"2024-07-08","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/few-shot-video-to-video-synthesis","title":"Few-shot Video-to-Video Synthesis","date":"2019-10-28","rows_on_this_dataset":1,"code_links":6,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}