HR-ShanghaiTech

Overview edit

Variants: HR-ShanghaiTech

Associated Benchmarks

This dataset is used in 1 benchmark:

• Video Anomaly Detection - Metrics: AUC

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• PoseWatch: A Transformer-based Architecture for Human-centric Video Anomaly Detection Using Spatio-temporal Pose Tokenization (2024) -
• An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Prediction (2024) -
• Holistic Representation Learning for Multitask Trajectory Anomaly Detection (2023) -
• Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection (2023) -
• Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection (2023) -
• BiPOCO: Bi-Directional Trajectory Prediction with Pose Constraints for Pedestrian Anomaly Detection (2022) -
• Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection (2021) -
• Graph Embedded Pose Clustering for Anomaly Detection (2019) -
• Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection (2019) -
• Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos (2019) -
• Future Frame Prediction for Anomaly Detection -- A New Baseline (2017) -
• Learning Temporal Regularity in Video Sequences (2016) -