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

Human motion prediction is an essential part for human-robot collaboration.Unlike most of the existing methods mainly focusing on improving theeffectiveness of spatiotemporal modeling for accurate prediction, we takeeffectiveness and efficiency into consideration, aiming at the predictionquality, computational efficiency and the lightweight of the model. Amulti-grained trajectory graph convolutional networks based and lightweightframework is proposed for habit-unrelated human motion prediction.Specifically, we represent human motion as multi-grained trajectories,including joint trajectory and sub-joint trajectory. Based on the advancedrepresentation, multi-grained trajectory graph convolutional networks areproposed to explore the spatiotemporal dependencies at the multiplegranularities. Moreover, considering the right-handedness habit of the vastmajority of people, a new motion generation method is proposed to generate themotion with left-handedness, to better model the motion with less bias to thehuman habit. Experimental results on challenging datasets, including Human3.6Mand CMU Mocap, show that the proposed model outperforms state-of-the-art withless than 0.12 times parameters, which demonstrates the effectiveness andefficiency of our proposed method.

Multi-grained Trajectory Graph Convolutional Networks for Habit-unrelated Human Motion Prediction