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

3D human pose estimation (HPE) is crucial in many fields, such as humanbehavior analysis, augmented reality/virtual reality (AR/VR) applications, andself-driving industry. Videos that contain multiple potentially occluded peoplecaptured from freely moving monocular cameras are very common in real-worldscenarios, while 3D HPE for such scenarios is quite challenging, partiallybecause there is a lack of such data with accurate 3D ground truth labels inexisting datasets. In this paper, we propose a temporal regression network witha gated convolution module to transform 2D joints to 3D and recover the missingoccluded joints in the meantime. A simple yet effective localization approachis further conducted to transform the normalized pose to the global trajectory.To verify the effectiveness of our approach, we also collect a new movingcamera multi-human (MMHuman) dataset that includes multiple people with heavyocclusion captured by moving cameras. The 3D ground truth joints are providedby accurate motion capture (MoCap) system. From the experiments onstatic-camera based Human3.6M data and our own collected moving-camera baseddata, we show that our proposed method outperforms most state-of-the-art2D-to-3D pose estimation methods, especially for the scenarios with heavyocclusions.

Exploring Severe Occlusion: Multi-Person 3D Pose Estimation with Gated Convolution