# Return of Frustratingly Easy Unsupervised Video Domain Adaptation

arXiv: https://arxiv.org/abs/2605.19510 · HTML: https://mlsanity.com/paper/2605.19510/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 52 references that are in the map.
- First posted on arXiv 19 May 2026.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Scaling Egocentric Vision: The EPIC-KITCHENS Dataset](https://mlsanity.com/paper/1804.02748/) (2018)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Multi-Modal Domain Adaptation for Fine-Grained Action Recognition](https://mlsanity.com/paper/2001.09691/) (2020)
- [Temporal Attentive Alignment for Large-Scale Video Domain Adaptation](https://mlsanity.com/paper/1907.12743/) (2019)
- [Adversarial Cross-Domain Action Recognition with Co-Attention](https://mlsanity.com/paper/1912.10405/) (2019)
- [Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing](https://mlsanity.com/paper/2110.15128/) (2021)
- [Learning Cross-modal Contrastive Features for Video Domain Adaptation](https://mlsanity.com/paper/2108.11974/) (2021)
- [Audio-Adaptive Activity Recognition Across Video Domains](https://mlsanity.com/paper/2203.14240/) (2022)
- [Aligning Correlation Information for Domain Adaptation in Action Recognition](https://mlsanity.com/paper/2107.04932/) (2021)
- [Adversarial Bipartite Graph Learning for Video Domain Adaptation](https://mlsanity.com/paper/2007.15829/) (2020)
- [Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition](https://mlsanity.com/paper/2203.04559/) (2022)
- [Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective](https://mlsanity.com/paper/2208.07365/) (2022)
- [Diversifying Spatial-Temporal Perception for Video Domain Generalization](https://mlsanity.com/paper/2310.17942/) (2023)
- [AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation](https://mlsanity.com/paper/2304.01110/) (2023)
- [The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation](https://mlsanity.com/paper/2308.09139/) (2023)
- [Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2211.10412/) (2022)
- [Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training](https://mlsanity.com/paper/2312.02914/) (2023)
- [Unsupervised Domain Adaptation for Video Transformers in Action Recognition](https://mlsanity.com/paper/2207.12842/) (2022)
- [Conditional Extreme Value Theory for Open Set Video Domain Adaptation](https://mlsanity.com/paper/2109.00522/) (2021)
- [Human-Centric Transformer for Domain Adaptive Action Recognition](https://mlsanity.com/paper/2407.10860/) (2024)
- [Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognition](https://mlsanity.com/paper/2112.12175/) (2021)
- [Leveraging Endo- and Exo-Temporal Regularization for Black-box Video Domain Adaptation](https://mlsanity.com/paper/2208.05187/) (2022)
- [CycDA: Unsupervised Cycle Domain Adaptation from Image to Video](https://mlsanity.com/paper/2203.16244/) (2022)
- [Source-free Video Domain Adaptation by Learning from Noisy Labels](https://mlsanity.com/paper/2311.18572/) (2023)
- [Meta Co-Training: Two Views are Better than One](https://mlsanity.com/paper/2311.18083/) (2023)

## Abstract (arXiv)

Unsupervised video domain adaptation (UVDA) is a practical but under-explored problem. In this paper, we propose a frustratingly easy UVDA method, called MetaTrans. Specifically, MetaTrans adopts a concise learning objective that contains only two fundamental loss terms. Despite the simplicity of the learning objective, MetaTrans embodies an advanced UVDA idea, that is, handling the spatial and temporal divergence of cross-domain videos separately, through a subtle model architecture design. By implementing a temporal-static subtraction module, MetaTrans effectively removes spatial and temporal divergence. Extensive empirical evaluations, particularly on various cross-domain action recognition tasks, show substantial absolute adaptation performance enhancement and significantly superior relative performance gain compared with state-of-the-art UVDA baselines.