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

Weakly-supervised temporal action localization (WTAL) in untrimmed videos hasemerged as a practical but challenging task since only video-level labels areavailable. Existing approaches typically leverage off-the-shelf segment-levelfeatures, which suffer from spatial incompleteness and temporal incoherence,thus limiting their performance. In this paper, we tackle this problem from anew perspective by enhancing segment-level representations with a simple yeteffective graph convolutional network, namely action complement graph network(ACGNet). It facilitates the current video segment to perceive spatial-temporaldependencies from others that potentially convey complementary clues,implicitly mitigating the negative effects caused by the two issues above. Bythis means, the segment-level features are more discriminative and robust tospatial-temporal variations, contributing to higher localization accuracies.More importantly, the proposed ACGNet works as a universal module that can beflexibly plugged into different WTAL frameworks, while maintaining theend-to-end training fashion. Extensive experiments are conducted on theTHUMOS'14 and ActivityNet1.2 benchmarks, where the state-of-the-art resultsclearly demonstrate the superiority of the proposed approach.

ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization