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

Fully supervised skeleton-based action recognition has achieved greatprogress with the blooming of deep learning techniques. However, these methodsrequire sufficient labeled data which is not easy to obtain. In contrast,self-supervised skeleton-based action recognition has attracted more attention.With utilizing the unlabeled data, more generalizable features can be learnedto alleviate the overfitting problem and reduce the demand of massive labeledtraining data. Inspired by the MAE, we propose a spatial-temporal maskedautoencoder framework for self-supervised 3D skeleton-based action recognition(SkeletonMAE). Following MAE's masking and reconstruction pipeline, we utilizea skeleton-based encoder-decoder transformer architecture to reconstruct themasked skeleton sequences. A novel masking strategy, named Spatial-TemporalMasking, is introduced in terms of both joint-level and frame-level for theskeleton sequence. This pre-training strategy makes the encoder outputgeneralizable skeleton features with spatial and temporal dependencies. Giventhe unmasked skeleton sequence, the encoder is fine-tuned for the actionrecognition task. Extensive experiments show that our SkeletonMAE achievesremarkable performance and outperforms the state-of-the-art methods on both NTURGB+D and NTU RGB+D 120 datasets.

SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition