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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Traffic anomaly detection (TAD) in driving videos is critical for ensuringthe safety of autonomous driving and advanced driver assistance systems.Previous single-stage TAD methods primarily rely on frame prediction, makingthem vulnerable to interference from dynamic backgrounds induced by the rapidmovement of the dashboard camera. While two-stage TAD methods appear to be anatural solution to mitigate such interference by pre-extractingbackground-independent features (such as bounding boxes and optical flow) usingperceptual algorithms, they are susceptible to the performance of first-stageperceptual algorithms and may result in error propagation. In this paper, weintroduce TTHF, a novel single-stage method aligning video clips with textprompts, offering a new perspective on traffic anomaly detection. Unlikeprevious approaches, the supervised signal of our method is derived fromlanguages rather than orthogonal one-hot vectors, providing a morecomprehensive representation. Further, concerning visual representation, wepropose to model the high frequency of driving videos in the temporal domain.This modeling captures the dynamic changes of driving scenes, enhances theperception of driving behavior, and significantly improves the detection oftraffic anomalies. In addition, to better perceive various types of trafficanomalies, we carefully design an attentive anomaly focusing mechanism thatvisually and linguistically guides the model to adaptively focus on the visualcontext of interest, thereby facilitating the detection of traffic anomalies.It is shown that our proposed TTHF achieves promising performance,outperforming state-of-the-art competitors by +5.4% AUC on the DoTA dataset andachieving high generalization on the DADA dataset.

Text-Driven Traffic Anomaly Detection with Temporal High-Frequency Modeling in Driving Videos