# Weakly Supervised Two-Stage Training Scheme for Deep Video Fight Detection Model

arXiv: https://arxiv.org/abs/2209.11477 · HTML: https://mlsanity.com/paper/2209.11477/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 23 Sep 2022.

## Builds on (most cited first, 18 of 18)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Label Propagation for Deep Semi-supervised Learning](https://mlsanity.com/paper/1904.04717/) (2019)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection](https://mlsanity.com/paper/1903.07256/) (2019)
- [MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection](https://mlsanity.com/paper/2104.01633/) (2021)
- [Abnormal Event Detection in Videos using Generative Adversarial Nets](https://mlsanity.com/paper/1708.09644/) (2017)
- [Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection](https://mlsanity.com/paper/1908.04321/) (2019)
- [Abnormal Event Detection in Videos using Spatiotemporal Autoencoder](https://mlsanity.com/paper/1701.01546/) (2017)
- [Localizing Anomalies from Weakly-Labeled Videos](https://mlsanity.com/paper/2008.08944/) (2020)
- [RWF-2000: An Open Large Scale Video Database for Violence Detection](https://mlsanity.com/paper/1911.05913/) (2019)
- [Vision-based Fight Detection from Surveillance Cameras](https://mlsanity.com/paper/2002.04355/) (2020)
- [Detection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition](https://mlsanity.com/paper/2205.11394/) (2022)

## Built on by (most cited first, 5 of 5)

- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision](https://mlsanity.com/paper/2307.03353/) (2023)
- [Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimation](https://mlsanity.com/paper/2311.12043/) (2023)
- [MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modeling](https://mlsanity.com/paper/2306.17201/) (2023)
- [Identifying Spatio-Temporal Drivers of Extreme Events](https://mlsanity.com/paper/2410.24075/) (2024)

## Abstract (arXiv)

Fight detection in videos is an emerging deep learning application with today's prevalence of surveillance systems and streaming media. Previous work has largely relied on action recognition techniques to tackle this problem. In this paper, we propose a simple but effective method that solves the task from a new perspective: we design the fight detection model as a composition of an action-aware feature extractor and an anomaly score generator. Also, considering that collecting frame-level labels for videos is too laborious, we design a weakly supervised two-stage training scheme, where we utilize multiple-instance-learning loss calculated on video-level labels to train the score generator, and adopt the self-training technique to further improve its performance. Extensive experiments on a publicly available large-scale dataset, UBI-Fights, demonstrate the effectiveness of our method, and the performance on the dataset exceeds several previous state-of-the-art approaches. Furthermore, we collect a new dataset, VFD-2000, that specializes in video fight detection, with a larger scale and more scenarios than existing datasets. The implementation of our method and the proposed dataset will be publicly available at https://github.com/Hepta-Col/VideoFightDetection.