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

In this work, we consider the problem of weakly-supervised multi-steplocalization in instructional videos. An established approach to this problemis to rely on a given list of steps. However, in reality, there is often morethan one way to execute a procedure successfully, by following the set of stepsin slightly varying orders. Thus, for successful localization in a given video,recent works require the actual order of procedure steps in the video, to beprovided by human annotators at both training and test times. Instead, here, weonly rely on generic procedural text that is not tied to a specific video. Werepresent the various ways to complete the procedure by transforming the listof instructions into a procedure flow graph which captures the partial order ofsteps. Using the flow graphs reduces both training and test time annotationrequirements. To this end, we introduce the new problem of flow graph to videogrounding. In this setup, we seek the optimal step ordering consistent with theprocedure flow graph and a given video. To solve this problem, we propose a newalgorithm - Graph2Vid - that infers the actual ordering of steps in the videoand simultaneously localizes them. To show the advantage of our proposedformulation, we extend the CrossTask dataset with procedure flow graphinformation. Our experiments show that Graph2Vid is both more efficient thanthe baselines and yields strong step localization results, without the need forstep order annotation.

Graph2Vid: Flow graph to Video Grounding for Weakly-supervised Multi-Step Localization