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

We introduce the task of weakly supervised learning for detecting human andobject interactions in videos. Our task poses unique challenges as a systemdoes not know what types of human-object interactions are present in a video orthe actual spatiotemporal location of the human and the object. To addressthese challenges, we introduce a contrastive weakly supervised training lossthat aims to jointly associate spatiotemporal regions in a video with an actionand object vocabulary and encourage temporal continuity of the visualappearance of moving objects as a form of self-supervision. To train our model,we introduce a dataset comprising over 6.5k videos with human-objectinteraction annotations that have been semi-automatically curated from sentencecaptions associated with the videos. We demonstrate improved performance overweakly supervised baselines adapted to our task on our video dataset.

Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions