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

We address temporal action localization in untrimmed long videos. This isimportant because videos in real applications are usually unconstrained andcontain multiple action instances plus video content of background scenes orother activities. To address this challenging issue, we exploit theeffectiveness of deep networks in temporal action localization via threesegment-based 3D ConvNets: (1) a proposal network identifies candidate segmentsin a long video that may contain actions; (2) a classification network learnsone-vs-all action classification model to serve as initialization for thelocalization network; and (3) a localization network fine-tunes on the learnedclassification network to localize each action instance. We propose a novelloss function for the localization network to explicitly consider temporaloverlap and therefore achieve high temporal localization accuracy. Only theproposal network and the localization network are used during prediction. Ontwo large-scale benchmarks, our approach achieves significantly superiorperformances compared with other state-of-the-art systems: mAP increases from1.7% to 7.4% on MEXaction2 and increases from 15.0% to 19.0% on THUMOS 2014,when the overlap threshold for evaluation is set to 0.5.

Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs