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 tackle the problem of Human Locomotion Forecasting, a task for jointlypredicting the spatial positions of several keypoints on the human body in thenear future under an egocentric setting. In contrast to the previous work thataims to solve either the task of pose prediction or trajectory forecasting inisolation, we propose a framework to unify the two problems and address thepractically useful task of pedestrian locomotion prediction in the wild. Amongthe major challenges in solving this task is the scarcity of annotatedegocentric video datasets with dense annotations for pose, depth, or egomotion.To surmount this difficulty, we use state-of-the-art models to generate (noisy)annotations and propose robust forecasting models that can learn from thisnoisy supervision. We present a method to disentangle the overall pedestrianmotion into easier to learn subparts by utilizing a pose completion and adecomposition module. The completion module fills in the missing key-pointannotations and the decomposition module breaks the cleaned locomotion down toglobal (trajectory) and local (pose keypoint movements). Further, with QuasiRNN as our backbone, we propose a novel hierarchical trajectory forecastingnetwork that utilizes low-level vision domain specific signals like egomotionand depth to predict the global trajectory. Our method leads tostate-of-the-art results for the prediction of human locomotion in theegocentric view. Project pade: https://karttikeya.github.io/publication/plf/

Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision