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

This paper addresses the problem of 3D pose estimation for multiple people ina few calibrated camera views. The main challenge of this problem is to findthe cross-view correspondences among noisy and incomplete 2D pose predictions.Most previous methods address this challenge by directly reasoning in 3D usinga pictorial structure model, which is inefficient due to the huge state space.We propose a fast and robust approach to solve this problem. Our key idea is touse a multi-way matching algorithm to cluster the detected 2D poses in allviews. Each resulting cluster encodes 2D poses of the same person acrossdifferent views and consistent correspondences across the keypoints, from whichthe 3D pose of each person can be effectively inferred. The proposed convexoptimization based multi-way matching algorithm is efficient and robust againstmissing and false detections, without knowing the number of people in thescene. Moreover, we propose to combine geometric and appearance cues forcross-view matching. The proposed approach achieves significant performancegains from the state-of-the-art (96.3% vs. 90.6% and 96.9% vs. 88% on theCampus and Shelf datasets, respectively), while being efficient for real-timeapplications.

Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views