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/

Zendy Plus

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

Zendy Tools

Zendy Open

Recognizing human actions from point cloud videos has attracted tremendousattention from both academia and industry due to its wide applications likeautomatic driving, robotics, and so on. However, current methods for pointcloud action recognition usually require a huge amount of data with manualannotations and a complex backbone network with high computation costs, whichmakes it impractical for real-world applications. Therefore, this paperconsiders the task of semi-supervised point cloud action recognition. Wepropose a Masked Pseudo-Labeling autoEncoder (\textbf{MAPLE}) framework tolearn effective representations with much fewer annotations for point cloudaction recognition. In particular, we design a novel and efficient\textbf{De}coupled \textbf{s}patial-\textbf{t}emporal Trans\textbf{Former}(\textbf{DestFormer}) as the backbone of MAPLE. In DestFormer, the spatial andtemporal dimensions of the 4D point cloud videos are decoupled to achieveefficient self-attention for learning both long-term and short-term features.Moreover, to learn discriminative features from fewer annotations, we design amasked pseudo-labeling autoencoder structure to guide the DestFormer toreconstruct features of masked frames from the available frames. Moreimportantly, for unlabeled data, we exploit the pseudo-labels from theclassification head as the supervision signal for the reconstruction offeatures from the masked frames. Finally, comprehensive experiments demonstratethat MAPLE achieves superior results on three public benchmarks and outperformsthe state-of-the-art method by 8.08\% accuracy on the MSR-Action3D dataset.

MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognition