# Multi-Scale Temporal Domain Alignment for Federated Video Domain Adaptation

arXiv: https://arxiv.org/abs/2608.29186 · HTML: https://mlsanity.com/paper/2608.29186/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 18 of 18)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Moments in Time Dataset: one million videos for event understanding](https://mlsanity.com/paper/1801.03150/) (2018)
- [Multi-Modal Domain Adaptation for Fine-Grained Action Recognition](https://mlsanity.com/paper/2001.09691/) (2020)
- [Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting](https://mlsanity.com/paper/2402.05956/) (2024)
- [Temporal Attentive Alignment for Large-Scale Video Domain Adaptation](https://mlsanity.com/paper/1907.12743/) (2019)
- [KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation](https://mlsanity.com/paper/2011.09757/) (2020)
- [ARID: A New Dataset for Recognizing Action in the Dark](https://mlsanity.com/paper/2006.03876/) (2020)
- [Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning](https://mlsanity.com/paper/2210.02326/) (2022)
- [Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective](https://mlsanity.com/paper/2208.07365/) (2022)
- [Multi-Source Video Domain Adaptation with Temporal Attentive Moment Alignment](https://mlsanity.com/paper/2109.09964/) (2021)
- [Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2211.10412/) (2022)
- [Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting](https://mlsanity.com/paper/2302.05049/) (2023)
- [UFDA: Universal Federated Domain Adaptation with Practical Assumptions](https://mlsanity.com/paper/2311.15570/) (2023)
- [Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data](https://mlsanity.com/paper/2412.13757/) (2024)
- [Transferable-guided Attention Is All You Need for Video Domain Adaptation](https://mlsanity.com/paper/2407.01375/) (2024)

## Abstract (arXiv)

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-labels on the target-server. A novel L2 variance penalty enforces cross-scale consistency during scale-based knowledge distillation, preventing a singular dominant scale. The late fusion aggregates features across different scales, where the fusion head is trained via knowledge distillation using confidence-weighted aggregation of scale-wise predictions, enabling the model to effectively exploit complementary temporal information for final predictions. Experiments on Epic-Kitchens-55 and Daily-DA demonstrate state-of-the-art performances, with gains up to 28.47% over current FDA methods. Ablation studies prove that multi-scale distillation and scale coordination are critical for effective temporal knowledge transfer.