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

In this paper, we address the problem of temporal action localization with asingle stage neural network. In the proposed architecture we model the boundarypredictions as uni-variate Gaussian distributions in order to model theiruncertainties, which is the first in this area to the best of our knowledge. Weuse two uncertainty-aware boundary regression losses: first, theKullback-Leibler divergence between the ground truth location of the boundaryand the Gaussian modeling the prediction of the boundary and second, theexpectation of the $\ell_1$ loss under the same Gaussian. We show that withboth uncertainty modeling approaches improve the detection performance by morethan $1.5\%$ in mAP@tIoU=0.5 and that the proposed simple one-stage networkperforms closely to more complex one and two stage networks.

Boundary Uncertainty in a Single-Stage Temporal Action Localization Network