# FedCVU: Federated Learning for Cross-View Video Understanding

arXiv: https://arxiv.org/abs/2603.21647 · HTML: https://mlsanity.com/paper/2603.21647/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation](https://mlsanity.com/paper/2503.08153/) (2025)
- [Unsupervised Learning of View-invariant Action Representations](https://mlsanity.com/paper/1809.01844/) (2018)
- [RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers](https://mlsanity.com/paper/2502.14377/) (2025)
- [FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance](https://mlsanity.com/paper/2408.08189/) (2024)
- [Learning a Deep Model for Human Action Recognition from Novel Viewpoints](https://mlsanity.com/paper/1602.00828/) (2016)
- [Cross-Entropy Adversarial View Adaptation for Person Re-identification](https://mlsanity.com/paper/1904.01755/) (2019)
- [U-StyDiT: Ultra-high Quality Artistic Style Transfer Using Diffusion Transformers](https://mlsanity.com/paper/2503.08157/) (2025)
- [Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding](https://mlsanity.com/paper/2508.09486/) (2025)
- [Qihoo-T2X: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Any-Task](https://mlsanity.com/paper/2409.04005/) (2024)
- [RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation](https://mlsanity.com/paper/2505.01657/) (2025)
- [Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking](https://mlsanity.com/paper/1607.06408/) (2016)
- [MoFu: Scale-Aware Modulation and Fourier Fusion for Multi-Subject Video Generation](https://mlsanity.com/paper/2512.22310/) (2025)
- [Viewpoint Invariant Action Recognition using RGB-D Videos](https://mlsanity.com/paper/1709.05087/) (2017)

## Abstract (arXiv)

Federated learning (FL) has emerged as a promising paradigm for privacy-preserving multi-camera video understanding. However, applying FL to cross-view scenarios faces three major challenges: (i) heterogeneous viewpoints and backgrounds lead to highly non-IID client distributions and overfitting to view-specific patterns, (ii) local distribution biases cause misaligned representations that hinder consistent cross-view semantics, and (iii) large video architectures incur prohibitive communication overhead. To address these issues, we propose FedCVU, a federated framework with three components: VS-Norm, which preserves normalization parameters to handle view-specific statistics; CV-Align, a lightweight contrastive regularization module to improve cross-view representation alignment; and SLA, a selective layer aggregation strategy that reduces communication without sacrificing accuracy. Extensive experiments on action understanding and person re-identification tasks under a cross-view protocol demonstrate that FedCVU consistently boosts unseen-view accuracy while maintaining strong seen-view performance, outperforming state-of-the-art FL baselines and showing robustness to domain heterogeneity and communication constraints.