Datasets › UCSD Ped2

UCSD Ped2 (UCSD Anomaly Detection Dataset)

Introduced in Anomaly detection in crowded scenes1 Jan 2010 archive 2025-07-28

The UCSD Anomaly Detection Dataset was acquired with a stationary camera mounted at an elevation, overlooking pedestrian walkways. The crowd density in the walkways was variable, ranging from sparse to very crowded. In the normal setting, the video contains only pedestrians. Abnormal events are due to either: the circulation of non pedestrian entities in the walkways anomalous pedestrian motion patterns Commonly occurring anomalies include bikers, skaters, small carts, and people walking across a walkway or in the grass that surrounds it. A few instances of people in wheelchair were also recorded. All abnormalities are naturally occurring, i.e. they were not staged for the purposes of assembling the dataset. The data was split into 2 subsets, each corresponding to a different scene. The video footage recorded from each scene was split into various clips of around 200 frames.

Source: The UCSD Anomaly Detection Dataset Image Source: http://www.svcl.ucsd.edu/publications/conference/2010/cvpr2010/cvpr_anomaly_2010.pdf

Benchmarks archive 2025-07-28

All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

18 shown of 18 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 92. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
VADMamba: Exploring State Space Models for Fast Video Anomaly Detection 1 1 27 Mar 2025 not harvested
UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection 1 1 28 Feb 2025 not harvested
Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models 1 2 14 Jul 2024 ran 2 of 2 samples (0 unverified)
MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection 1 2 21 Mar 2024 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Making Anomalies More Anomalous: Video Anomaly Detection Using a Novel Generator and Destroyer 1 1 26 Feb 2024 not harvested
VALD-GAN: video anomaly detection using latent discriminator augmented GAN 0 1 18 Oct 2023 not harvested
STemGAN: spatio-temporal generative adversarial network for video anomaly detection 0 1 22 Sep 2023 not harvested
Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors 1 1 21 Jun 2023 not harvested
Diversity-Measurable Anomaly Detection 1 2 9 Mar 2023 ran 6 of 11 samples (5 unverified; 11 pointer-only for licence)
An Attribute-based Method for Video Anomaly Detection 4 1 1 Dec 2022 ran 2 of 3 samples (1 unverified; 3 pointer-only for licence)
Spatio-temporal predictive tasks for abnormal event detection in videos 0 1 27 Oct 2022 not harvested
Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection 1 1 7 Sep 2022 not harvested
Attention-based residual autoencoder for video anomaly detection 1 1 25 May 2022 not harvested
FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation 1 1 16 Jun 2021 not harvested
Anomaly Detection in Video via Self-Supervised and Multi-Task Learning 1 1 15 Nov 2020 not harvested
A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video 2 2 27 Aug 2020 ran 3 of 3 samples (0 unverified; 3 pointer-only for licence)
HAMLET: A Hierarchical Multimodal Attention-based Human Activity Recognition Algorithm 0 1 3 Aug 2020 not harvested
Abnormal Event Detection in Videos using Generative Adversarial Nets 0 1 31 Aug 2017 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • UCSD Ped2
  • UCSD-MIT Human Motion

2 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections