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

Temporal sentence grounding in videos aims to detect and localize one targetvideo segment, which semantically corresponds to a given sentence. Existingmethods mainly tackle this task via matching and aligning semantics between asentence and candidate video segments, while neglect the fact that the sentenceinformation plays an important role in temporally correlating and composing thedescribed contents in videos. In this paper, we propose a novel semanticconditioned dynamic modulation (SCDM) mechanism, which relies on the sentencesemantics to modulate the temporal convolution operations for bettercorrelating and composing the sentence related video contents over time. Moreimportantly, the proposed SCDM performs dynamically with respect to the diversevideo contents so as to establish a more precise matching relationship betweensentence and video, thereby improving the temporal grounding accuracy.Extensive experiments on three public datasets demonstrate that our proposedmodel outperforms the state-of-the-arts with clear margins, illustrating theability of SCDM to better associate and localize relevant video contents fortemporal sentence grounding. Our code for this paper is available athttps://github.com/yytzsy/SCDM .

Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos