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

Analyzing the story behind TV series and movies often requires understandingwho the characters are and what they are doing. With improving deep facemodels, this may seem like a solved problem. However, as face detectors getbetter, clustering/identification needs to be revisited to address increasingdiversity in facial appearance. In this paper, we address video face clusteringusing unsupervised methods. Our emphasis is on distilling the essentialinformation, identity, from the representations obtained using deep pre-trainedface networks. We propose a self-supervised Siamese network that can be trainedwithout the need for video/track based supervision, and thus can also beapplied to image collections. We evaluate our proposed method on three videoface clustering datasets. The experiments show that our methods outperformcurrent state-of-the-art methods on all datasets. Video face clustering islacking a common benchmark as current works are often evaluated with differentmetrics and/or different sets of face tracks.

Self-Supervised Learning of Face Representations for Video Face Clustering