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

Understanding users' activities from head-mounted cameras is a fundamentaltask for Augmented and Virtual Reality (AR/VR) applications. A typical approachis to train a classifier in a supervised manner using data labeled by humans.This approach has limitations due to the expensive annotation cost and theclosed coverage of activity labels. A potential way to address theselimitations is to use self-supervised learning (SSL). Instead of relying onhuman annotations, SSL leverages intrinsic properties of data to learnrepresentations. We are particularly interested in learning egocentric videorepresentations benefiting from the head-motion generated by users' dailyactivities, which can be easily obtained from IMU sensors embedded in AR/VRdevices. Towards this goal, we propose a simple but effective approach to learnvideo representation by learning to tell the corresponding pairs of video clipand head-motion. We demonstrate the effectiveness of our learned representationfor recognizing egocentric activities of people and dogs.

How You Move Your Head Tells What You Do: Self-supervised Video Representation Learning with Egocentric Cameras and IMU Sensors