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

This paper presents a novel approach for temporal and semantic segmentationof edited videos into meaningful segments, from the point of view of thestorytelling structure. The objective is to decompose a long video into moremanageable sequences, which can in turn be used to retrieve the mostsignificant parts of it given a textual query and to provide an effectivesummarization. Previous video decomposition methods mainly employed perceptualcues, tackling the problem either as a story change detection, or as asimilarity grouping task, and the lack of semantics limited their ability toidentify story boundaries. Our proposal connects together perceptual, audio andsemantic cues in a specialized deep network architecture designed with acombination of CNNs which generate an appropriate embedding, and clusters shotsinto connected sequences of semantic scenes, i.e. stories. A retrievalpresentation strategy is also proposed, by selecting the semantically andaesthetically "most valuable" thumbnails to present, considering the query inorder to improve the storytelling presentation. Finally, the subjective natureof the task is considered, by conducting experiments with different annotatorsand by proposing an algorithm to maximize the agreement between automaticresults and human annotators.

Recognizing and Presenting the Storytelling Video Structure with Deep Multimodal Networks