SOURCE-LINKED INTELLIGENCE

Multi-Scale Temporal Domain Alignment for Federated Video Domain Adaptation

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Federated Video Domain Adaptation (FVDA) enables collaborative learning across distributed and non-IID video datasets while preserving privacy, but is under-explored due to challenges in aligning temporal information. We propose Multi-scalE Temporal domAin aLignment (METAL), a novel framework that leverages temporal information at multiple resolutions to improve cross-domain video action recognition with only model parameter transfers. METAL trains per-scale transformer encoders on source-clients, then performs independent knowledge voting at each temporal scale to generate robust pseudo-label

Read original source ↗ Open in workspace

recordType

paper

region

Global