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

In this work, we consider the problem of cross-domain 3D action recognitionin the open-set setting, which has been rarely explored before. Specifically,there is a source domain and a target domain that contain the skeletonsequences with different styles and categories, and our purpose is to clusterthe target data by utilizing the labeled source data and unlabeled target data.For such a challenging task, this paper presents a novel approach dubbed CoDTto collaboratively cluster the domain-shared features and target-specificfeatures. CoDT consists of two parallel branches. One branch aims to learndomain-shared features with supervised learning in the source domain, while theother is to learn target-specific features using contrastive learning in thetarget domain. To cluster the features, we propose an online clusteringalgorithm that enables simultaneous promotion of robust pseudo label generationand feature clustering. Furthermore, to leverage the complementarity ofdomain-shared features and target-specific features, we propose a novelcollaborative clustering strategy to enforce pair-wise relationship consistencybetween the two branches. We conduct extensive experiments on multiplecross-domain 3D action recognition datasets, and the results demonstrate theeffectiveness of our method.

Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition