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

The objective of this work is person-clustering in videos -- groupingcharacters according to their identity. Previous methods focus on the narrowertask of face-clustering, and for the most part ignore other cues such as theperson's voice, their overall appearance (hair, clothes, posture), and theediting structure of the videos. Similarly, most current datasets evaluate onlythe task of face-clustering, rather than person-clustering. This limits theirapplicability to downstream applications such as story understanding whichrequire person-level, rather than only face-level, reasoning. In this paper wemake contributions to address both these deficiencies: first, we introduce aMulti-Modal High-Precision Clustering algorithm for person-clustering in videosusing cues from several modalities (face, body, and voice). Second, weintroduce a Video Person-Clustering dataset, for evaluating multi-modalperson-clustering. It contains body-tracks for each annotated character,face-tracks when visible, and voice-tracks when speaking, with their associatedfeatures. The dataset is by far the largest of its kind, and covers films andTV-shows representing a wide range of demographics. Finally, we show theeffectiveness of using multiple modalities for person-clustering, explore theuse of this new broad task for story understanding through characterco-occurrences, and achieve a new state of the art on all available datasetsfor face and person-clustering.

Face, Body, Voice: Video Person-Clustering with Multiple Modalities