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

4D human sensing and modeling are fundamental tasks in vision and graphicswith numerous applications. With the advances of new sensors and algorithms,there is an increasing demand for more versatile datasets. In this work, wecontribute HuMMan, a large-scale multi-modal 4D human dataset with 1000 humansubjects, 400k sequences and 60M frames. HuMMan has several appealingproperties: 1) multi-modal data and annotations including color images, pointclouds, keypoints, SMPL parameters, and textured meshes; 2) popular mobiledevice is included in the sensor suite; 3) a set of 500 actions, designed tocover fundamental movements; 4) multiple tasks such as action recognition, poseestimation, parametric human recovery, and textured mesh reconstruction aresupported and evaluated. Extensive experiments on HuMMan voice the need forfurther study on challenges such as fine-grained action recognition, dynamichuman mesh reconstruction, point cloud-based parametric human recovery, andcross-device domain gaps.

HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling