GTA-Crime: A Synthetic Dataset and Generation Framework for Fatal Violence Detection with Adversarial Snippet-Level Domain Adaptation
This addresses the problem of rare and ethically challenging data collection for fatal violence detection in video anomaly detection, though it is incremental as it builds on existing synthetic data and domain adaptation methods.
The paper tackles the difficulty of detecting fatal incidents like shootings and stabbings in surveillance videos by introducing GTA-Crime, a synthetic dataset and generation framework using Grand Theft Auto 5, and demonstrates that incorporating it with a snippet-level domain adaptation strategy enhances real-world fatal violence detection accuracy.
Recent advancements in video anomaly detection (VAD) have enabled identification of various criminal activities in surveillance videos, but detecting fatal incidents such as shootings and stabbings remains difficult due to their rarity and ethical issues in data collection. Recognizing this limitation, we introduce GTA-Crime, a fatal video anomaly dataset and generation framework using Grand Theft Auto 5 (GTA5). Our dataset contains fatal situations such as shootings and stabbings, captured from CCTV multiview perspectives under diverse conditions including action types, weather, time of day, and viewpoints. To address the rarity of such scenarios, we also release a framework for generating these types of videos. Additionally, we propose a snippet-level domain adaptation strategy using Wasserstein adversarial training to bridge the gap between synthetic GTA-Crime features and real-world features like UCF-Crime. Experimental results validate our GTA-Crime dataset and demonstrate that incorporating GTA-Crime with our domain adaptation strategy consistently enhances real world fatal violence detection accuracy. Our dataset and the data generation framework are publicly available at https://github.com/ta-ho/GTA-Crime.