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

Finding relevant moments and highlights in videos according to naturallanguage queries is a natural and highly valuable common need in the currentvideo content explosion era. Nevertheless, jointly conducting moment retrievaland highlight detection is an emerging research topic, even though itscomponent problems and some related tasks have already been studied for awhile. In this paper, we present the first unified framework, named UnifiedMulti-modal Transformers (UMT), capable of realizing such joint optimizationwhile can also be easily degenerated for solving individual problems. As far aswe are aware, this is the first scheme to integrate multi-modal (visual-audio)learning for either joint optimization or the individual moment retrieval task,and tackles moment retrieval as a keypoint detection problem using a novelquery generator and query decoder. Extensive comparisons with existing methodsand ablation studies on QVHighlights, Charades-STA, YouTube Highlights, andTVSum datasets demonstrate the effectiveness, superiority, and flexibility ofthe proposed method under various settings. Source code and pre-trained modelsare available at https://github.com/TencentARC/UMT.

UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection