TL;DR
A novel approach, context aware autoencoding to improve the identification of anomalous events in surveillance videos based on the context by leveraging the complementary strengths of video vision transformers (ViViT) and stacked autoencoders.
This research introduces a novel memory-augmented CNN-ConvViT autoencoder framework for unsupervised video anomaly detection and introduces a Temporal-Aware Prototype Memory Module (TAPMM) that explicitly learns normal spatio-temporal behavior patterns.
This study introduces Vision Mamba (ViM), leveraging a Selective State Space Model to capture long-range temporal dependencies with linear computational complexity, validating the ViM as a highly efficient solution that balances computational feasibility with good performance in detecting complex criminal activities at...
Weakly supervised video anomaly detection (WS-VAD) presents a significant challenge in security video surveillance, as it aims to accurately identify anomaly frames in untrimmed videos with only video-level supervision. Several recent studies exploit vision-language pre-training models, e.g., CLIP, to take advantage of...
Transformer with Variational AutoEncoder is presented, a framework that combines a dual-embedding representation pipeline, a Transformer encoder for long-range dependency modeling, and VAE-based latent regularization of encoded features to provide an effective and robust solution for long-term time-series anomaly detec...
An adaptive temporal modeling framework for WSVAD that explicitly accounts for variations in video dynamics across multiple temporal granularities is proposed and an adaptive similarity-based fusion strategy that dynamically integrates anomaly scores into video-level predictions is proposed, replacing fixed top-k aggre...
Qualitative and quantitative results confirm that modeling normal action semantics provides a robust and scalable solution for real-world surveillance anomaly detection.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
