# Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection

arXiv: https://arxiv.org/abs/2301.09489 · HTML: https://mlsanity.com/paper/2301.09489/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 61 references that are in the map.
- First posted on arXiv 23 Jan 2023.

## Builds on (most cited first, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [Hyperspherical Variational Auto-Encoders](https://mlsanity.com/paper/1804.00891/) (2018)
- [Anomaly Detection in Video via Self-Supervised and Multi-Task Learning](https://mlsanity.com/paper/2011.07491/) (2020)
- [Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos](https://mlsanity.com/paper/1903.03295/) (2019)
- [Graph Embedded Pose Clustering for Anomaly Detection](https://mlsanity.com/paper/1912.11850/) (2019)
- [UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection](https://mlsanity.com/paper/2111.08644/) (2021)
- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [Anomaly Detection in Autonomous Driving: A Survey](https://mlsanity.com/paper/2204.07974/) (2022)
- [A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video](https://mlsanity.com/paper/2008.12328/) (2020)
- [Space-Time-Separable Graph Convolutional Network for Pose Forecasting](https://mlsanity.com/paper/2110.04573/) (2021)
- [Pose Flow: Efficient Online Pose Tracking](https://mlsanity.com/paper/1802.00977/) (2018)
- [Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction](https://mlsanity.com/paper/2203.01474/) (2022)
- [SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection](https://mlsanity.com/paper/2207.08003/) (2022)
- [Pose Forecasting in Industrial Human-Robot Collaboration](https://mlsanity.com/paper/2208.07308/) (2022)
- [Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection](https://mlsanity.com/paper/2008.13361/) (2020)
- [Are we certain it's anomalous?](https://mlsanity.com/paper/2211.09224/) (2022)

## Built on by (most cited first, 14 of 14)

- [Compositional Entailment Learning for Hyperbolic Vision-Language Models](https://mlsanity.com/paper/2410.06912/) (2024)
- [Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection](https://mlsanity.com/paper/2307.07205/) (2023)
- [Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detection](https://mlsanity.com/paper/2506.18368/) (2025)
- [Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection](https://mlsanity.com/paper/2412.03044/) (2024)
- [Bounding-Box Trajectories Matter for Video Anomaly Detection](https://mlsanity.com/paper/2605.21957/) (2026)
- [Emotion Recognition from Skeleton Data: A Comprehensive Survey](https://mlsanity.com/paper/2507.18026/) (2025)
- [H2em: Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2512.20029/) (2025)
- [ARGENT: Adaptive Hierarchical Image-Text Representations](https://mlsanity.com/paper/2603.23311/) (2026)
- [Video Anomaly Detection with Contours -- A Study](https://mlsanity.com/paper/2503.19588/) (2025)
- [3D Human-Human Interaction Anomaly Detection](https://mlsanity.com/paper/2512.13560/) (2025)
- [Motion Semantics Guided Normalizing Flow for Privacy-Preserving Video Anomaly Detection](https://mlsanity.com/paper/2603.26745/) (2026)
- [Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detection](https://mlsanity.com/paper/2606.20312/) (2026)
- [STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection](https://mlsanity.com/paper/2608.19987/) (2026)
- [Auditing Observation-Quality Shortcuts in the Evaluation of Person-Centered Motion for Video Anomaly Detection](https://mlsanity.com/paper/2610.16471/) (2026)

## Abstract (arXiv)

Detecting the anomaly of human behavior is paramount to timely recognizing endangering situations, such as street fights or elderly falls. However, anomaly detection is complex since anomalous events are rare and because it is an open set recognition task, i.e., what is anomalous at inference has not been observed at training. We propose COSKAD, a novel model that encodes skeletal human motion by a graph convolutional network and learns to COntract SKeletal kinematic embeddings onto a latent hypersphere of minimum volume for Video Anomaly Detection. We propose three latent spaces: the commonly-adopted Euclidean and the novel spherical and hyperbolic. All variants outperform the state-of-the-art on the most recent UBnormal dataset, for which we contribute a human-related version with annotated skeletons. COSKAD sets a new state-of-the-art on the human-related versions of ShanghaiTech Campus and CUHK Avenue, with performance comparable to video-based methods. Source code and dataset will be released upon acceptance.