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

Training state-of-the-art models for human pose estimation in videos requiresdatasets with annotations that are really hard and expensive to obtain.Although transformers have been recently utilized for body pose sequencemodeling, related methods rely on pseudo-ground truth to augment the currentlylimited training data available for learning such models. In this paper, weintroduce PoseBERT, a transformer module that is fully trained on 3D MotionCapture (MoCap) data via masked modeling. It is simple, generic and versatile,as it can be plugged on top of any image-based model to transform it in avideo-based model leveraging temporal information. We showcase variants ofPoseBERT with different inputs varying from 3D skeleton keypoints to rotationsof a 3D parametric model for either the full body (SMPL) or just the hands(MANO). Since PoseBERT training is task agnostic, the model can be applied toseveral tasks such as pose refinement, future pose prediction or motioncompletion without finetuning. Our experimental results validate that addingPoseBERT on top of various state-of-the-art pose estimation methodsconsistently improves their performances, while its low computational costallows us to use it in a real-time demo for smoothly animating a robotic handvia a webcam. Test code and models are available athttps://github.com/naver/posebert.

PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling