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 our approach to the third YouTube-8M video understandingcompetition that challenges par-ticipants to localize video-level labels atscale to the pre-cise time in the video where the label actually occurs.Ourmodel is an ensemble of frame-level models such as GatedNetVLAD and NeXtVLADand various BERT models withtest-time augmentation. We explore multiple ways toag-gregate BERT outputs as video representation and variousways to combinevisual and audio information. We proposetest-time augmentation as shiftingvideo frames to one leftor right unit, which adds variety to the predictionsand em-pirically shows improvement in evaluation metrics. We firstpre-train themodel on the 4M training video-level data, andthen fine-tune the model on 237Kannotated video segment-level data. We achieve MAP@100K 0.7871 on privatetest-ing video segment data, which is ranked 9th over 283 teams.

BERT for Large-scale Video Segment Classification with Test-time Augmentation