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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Self-supervised learning has shown great potentials in improving the videorepresentation ability of deep neural networks by getting supervision from thedata itself. However, some of the current methods tend to cheat from thebackground, i.e., the prediction is highly dependent on the video backgroundinstead of the motion, making the model vulnerable to background changes. Tomitigate the model reliance towards the background, we propose to remove thebackground impact by adding the background. That is, given a video, we randomlyselect a static frame and add it to every other frames to construct adistracting video sample. Then we force the model to pull the feature of thedistracting video and the feature of the original video closer, so that themodel is explicitly restricted to resist the background influence, focusingmore on the motion changes. We term our method as \emph{Background Erasing}(BE). It is worth noting that the implementation of our method is so simple andneat and can be added to most of the SOTA methods without much efforts.Specifically, BE brings 16.4% and 19.1% improvements with MoCo on the severelybiased datasets UCF101 and HMDB51, and 14.5% improvement on the less biaseddataset Diving48.

Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning