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

Point-Level temporal action localization (PTAL) aims to localize actions inuntrimmed videos with only one timestamp annotation for each action instance.Existing methods adopt the frame-level prediction paradigm to learn from thesparse single-frame labels. However, such a framework inevitably suffers from alarge solution space. This paper attempts to explore the proposal-basedprediction paradigm for point-level annotations, which has the advantage ofmore constrained solution space and consistent predictions among neighboringframes. The point-level annotations are first used as the keypoint supervisionto train a keypoint detector. At the location prediction stage, a simple buteffective mapper module, which enables back-propagation of training errors, isthen introduced to bridge the fully-supervised framework with weak supervision.To our best of knowledge, this is the first work to leverage thefully-supervised paradigm for the point-level setting. Experiments on THUMOS14,BEOID, and GTEA verify the effectiveness of our proposed method bothquantitatively and qualitatively, and demonstrate that our method outperformsstate-of-the-art methods.

Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses