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

In this paper, we delve into semi-supervised 2D human pose estimation. Theprevious method ignored two problems: (i) When conducting interactive trainingbetween large model and lightweight model, the pseudo label of lightweightmodel will be used to guide large models. (ii) The negative impact of noisepseudo labels on training. Moreover, the labels used for 2D human poseestimation are relatively complex: keypoint category and keypoint position. Tosolve the problems mentioned above, we propose a semi-supervised 2D human poseestimation framework driven by a position inconsistency pseudo label correctionmodule (SSPCM). We introduce an additional auxiliary teacher and use the pseudolabels generated by the two teacher model in different periods to calculate theinconsistency score and remove outliers. Then, the two teacher models areupdated through interactive training, and the student model is updated usingthe pseudo labels generated by two teachers. To further improve the performanceof the student model, we use the semi-supervised Cut-Occlude based on pseudokeypoint perception to generate more hard and effective samples. In addition,we also proposed a new indoor overhead fisheye human keypoint datasetWEPDTOF-Pose. Extensive experiments demonstrate that our method outperforms theprevious best semi-supervised 2D human pose estimation method. We will releasethe code and dataset at https://github.com/hlz0606/SSPCM.

Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module