GV-VAD : Exploring Video Generation for Weakly-Supervised Video Anomaly Detection
By: Suhang Cai , Xiaohao Peng , Chong Wang and more
Potential Business Impact:
Spots strange events in videos automatically.
Video anomaly detection (VAD) plays a critical role in public safety applications such as intelligent surveillance. However, the rarity, unpredictability, and high annotation cost of real-world anomalies make it difficult to scale VAD datasets, which limits the performance and generalization ability of existing models. To address this challenge, we propose a generative video-enhanced weakly-supervised video anomaly detection (GV-VAD) framework that leverages text-conditioned video generation models to produce semantically controllable and physically plausible synthetic videos. These virtual videos are used to augment training data at low cost. In addition, a synthetic sample loss scaling strategy is utilized to control the influence of generated synthetic samples for efficient training. The experiments show that the proposed framework outperforms state-of-the-art methods on UCF-Crime datasets. The code is available at https://github.com/Sumutan/GV-VAD.git.
Similar Papers
Pseudo Anomalies Are All You Need: Diffusion-Based Generation for Weakly-Supervised Video Anomaly Detection
CV and Pattern Recognition
Teaches computers to spot trouble without real examples.
DUAL-VAD: Dual Benchmarks and Anomaly-Focused Sampling for Video Anomaly Detection
CV and Pattern Recognition
Finds weird things happening in videos.
RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection
CV and Pattern Recognition
Finds weird things in videos by watching motion and meaning.