English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

A self-supervised multi-task learning (SSMTL) framework for video anomalydetection was recently introduced in literature. Due to its highly accurateresults, the method attracted the attention of many researchers. In this work,we revisit the self-supervised multi-task learning framework, proposing severalupdates to the original method. First, we study various detection methods, e.g.based on detecting high-motion regions using optical flow or backgroundsubtraction, since we believe the currently used pre-trained YOLOv3 issuboptimal, e.g. objects in motion or objects from unknown classes are neverdetected. Second, we modernize the 3D convolutional backbone by introducingmulti-head self-attention modules, inspired by the recent success of visiontransformers. As such, we alternatively introduce both 2D and 3D convolutionalvision transformer (CvT) blocks. Third, in our attempt to further improve themodel, we study additional self-supervised learning tasks, such as predictingsegmentation maps through knowledge distillation, solving jigsaw puzzles,estimating body pose through knowledge distillation, predicting masked regions(inpainting), and adversarial learning with pseudo-anomalies. We conductexperiments to assess the performance impact of the introduced changes. Uponfinding more promising configurations of the framework, dubbed SSMTL++v1 andSSMTL++v2, we extend our preliminary experiments to more data sets,demonstrating that our performance gains are consistent across all data sets.In most cases, our results on Avenue, ShanghaiTech and UBnormal raise thestate-of-the-art performance bar to a new level.

SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection