# Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition

arXiv: https://arxiv.org/abs/2203.04559 · HTML: https://mlsanity.com/paper/2203.04559/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 50 references that are in the map.
- First posted on arXiv 9 Mar 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [Temporal Relational Reasoning in Videos](https://mlsanity.com/paper/1711.08496/) (2017)
- [Moments in Time Dataset: one million videos for event understanding](https://mlsanity.com/paper/1801.03150/) (2018)
- [Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition](https://mlsanity.com/paper/1708.07632/) (2017)
- [Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer](https://mlsanity.com/paper/2012.07297/) (2020)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [Temporal Attentive Alignment for Large-Scale Video Domain Adaptation](https://mlsanity.com/paper/1907.12743/) (2019)
- [Domain Impression: A Source Data Free Domain Adaptation Method](https://mlsanity.com/paper/2102.09003/) (2021)
- [Domain Adaptation without Source Data](https://mlsanity.com/paper/2007.01524/) (2020)
- [Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation](https://mlsanity.com/paper/2003.02824/) (2020)
- [Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2003.04614/) (2020)
- [Adversarial Cross-Domain Action Recognition with Co-Attention](https://mlsanity.com/paper/1912.10405/) (2019)
- [ARID: A New Dataset for Recognizing Action in the Dark](https://mlsanity.com/paper/2006.03876/) (2020)
- [Semantic Concentration for Domain Adaptation](https://mlsanity.com/paper/2108.05720/) (2021)

## Built on by (most cited first, 28 of 28)

- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Domain Adaptation for Time Series Under Feature and Label Shifts](https://mlsanity.com/paper/2302.03133/) (2023)
- [Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2303.10457/) (2023)
- [Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors](https://mlsanity.com/paper/2205.14467/) (2022)
- [Test-Time Zero-Shot Temporal Action Localization](https://mlsanity.com/paper/2404.05426/) (2024)
- [The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation](https://mlsanity.com/paper/2308.09139/) (2023)
- [XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition](https://mlsanity.com/paper/2403.01560/) (2024)
- [Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training](https://mlsanity.com/paper/2312.02914/) (2023)
- [Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos](https://mlsanity.com/paper/2311.16444/) (2023)
- [Human-Centric Transformer for Domain Adaptive Action Recognition](https://mlsanity.com/paper/2407.10860/) (2024)
- [Leveraging Endo- and Exo-Temporal Regularization for Black-box Video Domain Adaptation](https://mlsanity.com/paper/2208.05187/) (2022)
- [Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation](https://mlsanity.com/paper/2303.10451/) (2023)
- [Source-free Video Domain Adaptation by Learning from Noisy Labels](https://mlsanity.com/paper/2311.18572/) (2023)
- [Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains](https://mlsanity.com/paper/2305.08420/) (2023)
- [Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions](https://mlsanity.com/paper/2404.15252/) (2024)
- [Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation](https://mlsanity.com/paper/2504.11669/) (2025)
- [Temporal Restoration and Spatial Rewiring for Source-Free Multivariate Time Series Domain Adaptation](https://mlsanity.com/paper/2505.21525/) (2025)
- [Day2Dark: Pseudo-Supervised Activity Recognition beyond Silent Daylight](https://mlsanity.com/paper/2212.02053/) (2022)
- [Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptation](https://mlsanity.com/paper/2303.10452/) (2023)
- [GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap](https://mlsanity.com/paper/2311.12467/) (2023)
- [Merlin L48 Spectrogram Dataset](https://mlsanity.com/paper/2511.00252/) (2025)
- [Multi-modal Instance Refinement for Cross-domain Action Recognition](https://mlsanity.com/paper/2311.14281/) (2023)
- [Domain Generalization for Improved Human Activity Recognition in Office Space Videos Using Adaptive Pre-processing](https://mlsanity.com/paper/2503.12678/) (2025)
- [Hierarchical Bayesian Framework for Multisource Domain Adaptation](https://mlsanity.com/paper/2512.18553/) (2025)
- [Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation](https://mlsanity.com/paper/2604.09955/) (2026)
- [EV-CLIP: Efficient Visual Prompt Adaptation for CLIP in Few-shot Action Recognition under Visual Challenges](https://mlsanity.com/paper/2604.22595/) (2026)
- [Return of Frustratingly Easy Unsupervised Video Domain Adaptation](https://mlsanity.com/paper/2605.19510/) (2026)
- [Test-Time Adaptation via Dual Distillation for Videos Under Severe Distribution Shifts](https://mlsanity.com/paper/2607.24611/) (2026)

## Abstract (arXiv)

Video-based Unsupervised Domain Adaptation (VUDA) methods improve the robustness of video models, enabling them to be applied to action recognition tasks across different environments. However, these methods require constant access to source data during the adaptation process. Yet in many real-world applications, subjects and scenes in the source video domain should be irrelevant to those in the target video domain. With the increasing emphasis on data privacy, such methods that require source data access would raise serious privacy issues. Therefore, to cope with such concern, a more practical domain adaptation scenario is formulated as the Source-Free Video-based Domain Adaptation (SFVDA). Though there are a few methods for Source-Free Domain Adaptation (SFDA) on image data, these methods yield degenerating performance in SFVDA due to the multi-modality nature of videos, with the existence of additional temporal features. In this paper, we propose a novel Attentive Temporal Consistent Network (ATCoN) to address SFVDA by learning temporal consistency, guaranteed by two novel consistency objectives, namely feature consistency and source prediction consistency, performed across local temporal features. ATCoN further constructs effective overall temporal features by attending to local temporal features based on prediction confidence. Empirical results demonstrate the state-of-the-art performance of ATCoN across various cross-domain action recognition benchmarks.