# VelocityNet: Real-Time Crowd Anomaly Detection via Person-Specific Velocity Analysis

arXiv: https://arxiv.org/abs/2510.18187 · HTML: https://mlsanity.com/paper/2510.18187/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Builds on (most cited first, 15 of 15)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [SpeedNet: Learning the Speediness in Videos](https://mlsanity.com/paper/2004.06130/) (2020)
- [Anomaly Detection in Video Sequence with Appearance-Motion Correspondence](https://mlsanity.com/paper/1908.06351/) (2019)
- [MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask](https://mlsanity.com/paper/2003.10955/) (2020)
- [FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation](https://mlsanity.com/paper/2303.01237/) (2023)
- [A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video](https://mlsanity.com/paper/2008.12328/) (2020)
- [Abnormal Event Detection in Videos using Generative Adversarial Nets](https://mlsanity.com/paper/1708.09644/) (2017)
- [SKFlow: Learning Optical Flow with Super Kernels](https://mlsanity.com/paper/2205.14623/) (2022)
- [SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection](https://mlsanity.com/paper/2207.08003/) (2022)
- [FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation](https://mlsanity.com/paper/2103.04524/) (2021)
- [An Attribute-based Method for Video Anomaly Detection](https://mlsanity.com/paper/2212.00789/) (2022)

## Abstract (arXiv)

Detecting anomalies in crowded scenes is challenging due to severe inter-person occlusions and highly dynamic, context-dependent motion patterns. Existing approaches often struggle to adapt to varying crowd densities and lack interpretable anomaly indicators. To address these limitations, we introduce VelocityNet, a dual-pipeline framework that combines head detection and dense optical flow to extract person-specific velocities. Hierarchical clustering categorizes these velocities into semantic motion classes (halt, slow, normal, and fast), and a percentile-based anomaly scoring system measures deviations from learned normal patterns. Experiments demonstrate the effectiveness of our framework in real-time detection of diverse anomalous motion patterns within densely crowded environments.