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

Self-supervised pre-training paradigms have been extensively explored in thefield of skeleton-based action recognition. In particular, methods based onmasked prediction have pushed the performance of pre-training to a new height.However, these methods take low-level features, such as raw joint coordinatesor temporal motion, as prediction targets for the masked regions, which issuboptimal. In this paper, we show that using high-level contextualizedfeatures as prediction targets can achieve superior performance. Specifically,we propose Skeleton2vec, a simple and efficient self-supervised 3D actionrepresentation learning framework, which utilizes a transformer-based teacherencoder taking unmasked training samples as input to create latentcontextualized representations as prediction targets. Benefiting from theself-attention mechanism, the latent representations generated by the teacherencoder can incorporate the global context of the entire training samples,leading to a richer training task. Additionally, considering the high temporalcorrelations in skeleton sequences, we propose a motion-aware tube maskingstrategy which divides the skeleton sequence into several tubes and performspersistent masking within each tube based on motion priors, thus forcing themodel to build long-range spatio-temporal connections and focus onaction-semantic richer regions. Extensive experiments on NTU-60, NTU-120, andPKU-MMD datasets demonstrate that our proposed Skeleton2vec outperformsprevious methods and achieves state-of-the-art results.

Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence