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/

Zendy Plus

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

Zendy Tools

Zendy Open

Predicting human motion is critical for assistive robots and AR/VRapplications, where the interaction with humans needs to be safe andcomfortable. Meanwhile, an accurate prediction depends on understanding boththe scene context and human intentions. Even though many works studyscene-aware human motion prediction, the latter is largely underexplored due tothe lack of ego-centric views that disclose human intent and the limiteddiversity in motion and scenes. To reduce the gap, we propose a large-scalehuman motion dataset that delivers high-quality body pose sequences, scenescans, as well as ego-centric views with the eye gaze that serves as asurrogate for inferring human intent. By employing inertial sensors for motioncapture, our data collection is not tied to specific scenes, which furtherboosts the motion dynamics observed from our subjects. We perform an extensivestudy of the benefits of leveraging the eye gaze for ego-centric human motionprediction with various state-of-the-art architectures. Moreover, to realizethe full potential of the gaze, we propose a novel network architecture thatenables bidirectional communication between the gaze and motion branches. Ournetwork achieves the top performance in human motion prediction on the proposeddataset, thanks to the intent information from eye gaze and the denoised gazefeature modulated by the motion. Code and data can be found athttps://github.com/y-zheng18/GIMO.

GIMO: Gaze-Informed Human Motion Prediction in Context