18 datasets found

Abnormal Event Detection at 150 FPS in MATLAB dataset

A new large-scale dataset for video anomaly detection, Street Scene, contains 46 training video sequences and 35 testing video sequences taken from a static USB camera looking...

UCSD Ped1 & Ped2 dataset for single-scene video anomaly detection

Anomalies are rare and anomaly detection is often therefore framed as One-Class Classification (OCC), i.e. trained solely on normalcy. Leading OCC techniques constrain the...

The UCF-Crime and XD-Violence datasets are used for weakly supervised video anomaly detection.

Object-centric auto-encoders and dummy anomalies for abnormal event detection in video.

Clustering driven deep autoencoder for video anomaly detection.

Video anomaly detection is often seen as one-class classification (OCC) problem due to the limited availability of anomaly examples.

A benchmark dataset for anomaly detection in videos

Video anomaly detection is a challenging task not only because it involves solving many sub-tasks such as motion representation, object localization and action recognition, but...

The UBnormal dataset is a recent and large dataset proposed for supervised anomaly detection. In contrast to other benchmarks, it is a synthetic dataset created with Cinema4D....

The Avenue data set consists of 16 training videos with a total 15328 frames and 21 test videos with a total of 15324.

The Ped2 dataset comprises of 16 training and 12 test videos and all videos have the same scene in the background.

Video Anomaly Detection (VAD) is an open-set recognition task, which is usually formulated as a one-class classification (OCC) problem, where training data is comprised of...

The ShanghaiTech dataset includes 330 training and 107 test videos recorded at 13 different background locations.

The CUHK Avenue dataset comprises one scene captured by a camera looking at an avenue near a subway entrance from a nearly horizontal view angle.

A benchmark for anomaly detection in crowded scenes. It contains 19600 frames captured using two different cameras.

The proposed Multi-scale Spatial-Temporal Interaction Network (MSTI-Net) for unsupervised Video Anomaly Detection (VAD).