Spatio-temporal video anomaly detection via CNN-ViT autoencoder and farneback optical flow

TASG-VAD: Weakly Supervised Video Anomaly Detection via Temporal Variation Attention and Adaptive Saliency Guidance

To alleviate the model’s reliance on dominant anomalous segments, TASG-VAD introduces an Adaptive Saliency Guidance (ASG) strategy, which performs intra-video saliency ranking and dynamic masking to guide the model toward overlooked subtle anomalies.

FASTe: Framework With Application-Driven Spatio-Temporal Efficiency for Video Anomaly Detection

FASTe introduces a LogSumExp-based multiple instance learning (MIL) aggregation strategy for robust training on variable-length inputs, and introduces frame-level anomaly localization under weak supervision, without requiring dense labels.

Reconstructive Visual Tuning for Weakly Supervised Video Anomaly Detection

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...

Non-IID robust federated video anomaly detection with hybrid 3D CNN-transformer encoding and global differential privacy for multi-camera surveillance

Anomaly Detection in Surveillance Video: An Unsupervised Unity Encoder Approach

Vision Mamba With Joint Spatiotemporal Features for Efficient Video Representation Learning in Self-Supervised Scheme

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...