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

Existing skeleton-based action recognition methods typically follow acentralized learning paradigm, which can pose privacy concerns when exposinghuman-related videos. Federated Learning (FL) has attracted much attention dueto its outstanding advantages in privacy-preserving. However, directly applyingFL approaches to skeleton videos suffers from unstable training. In this paper,we investigate and discover that the heterogeneous human topology graphstructure is the crucial factor hindering training stability. To address thislimitation, we pioneer a novel Federated Skeleton-based Action Recognition(FSAR) paradigm, which enables the construction of a globally generalized modelwithout accessing local sensitive data. Specifically, we introduce an AdaptiveTopology Structure (ATS), separating generalization and personalization bylearning a domain-invariant topology shared across clients and adomain-specific topology decoupled from global model aggregation.Furthermore,we explore Multi-grain Knowledge Distillation (MKD) to mitigate the discrepancybetween clients and server caused by distinct updating patterns throughaligning shallow block-wise motion features. Extensive experiments on multipledatasets demonstrate that FSAR outperforms state-of-the-art FL-based methodswhile inherently protecting privacy.

FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation