Towards open-ended Video Anomaly Detection (VAD), existing methods often exhibit
biased detection when faced with challenging or unseen events and lack interpretability. To …

In recent years, video anomaly detection has been extensively investigated in both
unsupervised and weakly supervised settings to alleviate costly temporal labeling. Despite …

How can we enable models to comprehend video anomalies occurring over varying
temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods …

Point-supervised temporal action localization pursues high-accuracy action detection under
low-cost data annotation. Despite recent advances, a significant challenge remains: sparse …

Data-driven fully-supervised online action detection algorithms heavily rely on manual
annotations, which are challenging to obtain in real-world applications. Current research …

In sewer pipe closed‐circuit television inspection, accurate temporal defect localization is
essential for effective pipe assessment. Industry standards typically do not require time …

Existing zero-shot temporal action detection (ZSTAD) methods predominantly use fully
supervised or unsupervised strategies to recognize unseen activities. However, these …

Point-supervised Temporal Action Localization (PS-TAL) detects temporal intervals of
actions in untrimmed videos with a label-efficient paradigm. However, most existing methods …

Standardized regulation of livestreaming is an important element of cyberspace governance.
Temporal action localization (TAL) can localize the occurrence of specific actions to better …

The purpose of weakly-supervised temporal action localization (WTAL) task is to
simultaneously classify and localize action instances in untrimmed videos with only video …