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 aims to localize actioninstances in videos with only video-level action labels. Existing methodsmainly embrace a localization-by-classification pipeline that optimizes thesnippet-level prediction with a video classification loss. However, thisformulation suffers from the discrepancy between classification and detection,resulting in inaccurate separation of foreground and background (F\&B)snippets. To alleviate this problem, we propose to explore the underlyingstructure among the snippets by resorting to unsupervised snippet clustering,rather than heavily relying on the video classification loss. Specifically, wepropose a novel clustering-based F\&B separation algorithm. It comprises twocore components: a snippet clustering component that groups the snippets intomultiple latent clusters and a cluster classification component that furtherclassifies the cluster as foreground or background. As there are noground-truth labels to train these two components, we introduce a unifiedself-labeling mechanism based on optimal transport to produce high-qualitypseudo-labels that match several plausible prior distributions. This ensuresthat the cluster assignments of the snippets can be accurately associated withtheir F\&B labels, thereby boosting the F\&B separation. We evaluate our methodon three benchmarks: THUMOS14, ActivityNet v1.2 and v1.3. Our method achievespromising performance on all three benchmarks while being significantly morelightweight than previous methods. Code is available athttps://github.com/Qinying-Liu/CASE

Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach