# CycDA: Unsupervised Cycle Domain Adaptation from Image to Video

arXiv: https://arxiv.org/abs/2203.16244 · HTML: https://mlsanity.com/paper/2203.16244/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [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)
- [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)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Temporal Pyramid Network for Action Recognition](https://mlsanity.com/paper/2004.03548/) (2020)
- [UntrimmedNets for Weakly Supervised Action Recognition and Detection](https://mlsanity.com/paper/1703.03329/) (2017)
- [CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images](https://mlsanity.com/paper/1808.01097/) (2018)
- [Cycle Self-Training for Domain Adaptation](https://mlsanity.com/paper/2103.03571/) (2021)
- [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)
- [Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation](https://mlsanity.com/paper/2003.02824/) (2020)
- [ACTION-Net: Multipath Excitation for Action Recognition](https://mlsanity.com/paper/2103.07372/) (2021)
- [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)
- [Omni-sourced Webly-supervised Learning for Video Recognition](https://mlsanity.com/paper/2003.13042/) (2020)
- [Learning Cross-modal Contrastive Features for Video Domain Adaptation](https://mlsanity.com/paper/2108.11974/) (2021)
- [Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2007.07695/) (2020)
- [Adversarial Bipartite Graph Learning for Video Domain Adaptation](https://mlsanity.com/paper/2007.15829/) (2020)
- [Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition](https://mlsanity.com/paper/1911.10751/) (2019)
- [Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images](https://mlsanity.com/paper/1504.00983/) (2015)
- [Attend in groups: a weakly-supervised deep learning framework for learning from web data](https://mlsanity.com/paper/1611.09960/) (2016)
- [Facial Descriptors for Human Interaction Recognition In Still Images](https://mlsanity.com/paper/1509.05366/) (2015)
- [Do Less and Achieve More: Training CNNs for Action Recognition Utilizing Action Images from the Web](https://mlsanity.com/paper/1512.07155/) (2015)
- [Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks](https://mlsanity.com/paper/1805.04384/) (2018)
- [Image to Video Domain Adaptation Using Web Supervision](https://mlsanity.com/paper/1908.01449/) (2019)

## Built on by (most cited first, 6 of 6)

- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective](https://mlsanity.com/paper/2208.07365/) (2022)
- [Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2211.10412/) (2022)
- [Site-Level Fine-Tuning with Progressive Layer Freezing: Towards Robust Prediction of Bronchopulmonary Dysplasia from Day-1 Chest Radiographs in Extremely Preterm Infants](https://mlsanity.com/paper/2507.12269/) (2025)
- [Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptation](https://mlsanity.com/paper/2511.18711/) (2025)
- [Return of Frustratingly Easy Unsupervised Video Domain Adaptation](https://mlsanity.com/paper/2605.19510/) (2026)

## Abstract (arXiv)

Although action recognition has achieved impressive results over recent years, both collection and annotation of video training data are still time-consuming and cost intensive. Therefore, image-to-video adaptation has been proposed to exploit labeling-free web image source for adapting on unlabeled target videos. This poses two major challenges: (1) spatial domain shift between web images and video frames; (2) modality gap between image and video data. To address these challenges, we propose Cycle Domain Adaptation (CycDA), a cycle-based approach for unsupervised image-to-video domain adaptation by leveraging the joint spatial information in images and videos on the one hand and, on the other hand, training an independent spatio-temporal model to bridge the modality gap. We alternate between the spatial and spatio-temporal learning with knowledge transfer between the two in each cycle. We evaluate our approach on benchmark datasets for image-to-video as well as for mixed-source domain adaptation achieving state-of-the-art results and demonstrating the benefits of our cyclic adaptation. Code is available at urlhttps://github.com/wlin-at/CycDA.