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

We address weakly supervised action alignment and segmentation in videos,where only the order of occurring actions is available during training. Wepropose Discriminative Differentiable Dynamic Time Warping (D3TW), the firstdiscriminative model using weak ordering supervision. The key technicalchallenge for discriminative modeling with weak supervision is that the lossfunction of the ordering supervision is usually formulated using dynamicprogramming and is thus not differentiable. We address this challenge with acontinuous relaxation of the min-operator in dynamic programming and extend thealignment loss to be differentiable. The proposed D3TW innovatively solvessequence alignment with discriminative modeling and end-to-end training, whichsubstantially improves the performance in weakly supervised action alignmentand segmentation tasks. We show that our model is able to bypass thedegenerated sequence problem usually encountered in previous work andoutperform the current state-of-the-art across three evaluation metrics in twochallenging datasets.

D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation