Abstract
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. We leverage the joint spatial information in images and videos on the one hand and, on the other hand, train 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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: CVPR, pp. 6299–6308 (2017)
Chen, J., Wu, X., Hu, Y., Luo, J.: Spatial-temporal causal inference for partial image-to-video adaptation. In: AAAI, vol. 35, pp. 1027–1035 (2021)
Chen, M.H., Kira, Z., AlRegib, G., Yoo, J., Chen, R., Zheng, J.: Temporal attentive alignment for large-scale video domain adaptation. In: ICCV, pp. 6321–6330 (2019)
Chen, M.H., Li, B., Bao, Y., AlRegib, G., Kira, Z.: Action segmentation with joint self-supervised temporal domain adaptation. In: CVPR, pp. 9454–9463 (2020)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597–1607. PMLR (2020)
Choi, J., Sharma, G., Chandraker, M., Huang, J.B.: Unsupervised and semi-supervised domain adaptation for action recognition from drones. In: WACV, pp. 1717–1726 (2020)
Choi, J., Sharma, G., Schulter, S., Huang, J.-B.: Shuffle and attend: video domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 678–695. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58610-2_40
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248–255. IEEE (2009)
Duan, H., Zhao, Y., Xiong, Y., Liu, W., Lin, D.: Omni-sourced webly-supervised learning for video recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 670–688. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58555-6_40
Feichtenhofer, C.: X3d: expanding architectures for efficient video recognition. In: CVPR (2020)
Gan, C., Sun, C., Duan, L., Gong, B.: Webly-supervised video recognition by mutually voting for relevant web images and web video frames. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 849–866. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_52
Gan, C., Sun, C., Nevatia, R.: Deck: discovering event composition knowledge from web images for zero-shot event detection and recounting in videos. In: AAAI, vol. 31 (2017)
Gan, C., Yao, T., Yang, K., Yang, Y., Mei, T.: You lead, we exceed: labor-free video concept learning by jointly exploiting web videos and images. In: CVPR, pp. 923–932 (2016)
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML, pp. 1180–1189. PMLR (2015)
Ganin, Y., et al.: Domain-adversarial training of neural networks. JMLR 17(1), 2030–2096 (2016)
Guo, S., et al.: Curriculumnet: weakly supervised learning from large-scale web images. In: ECCV, pp. 135–150 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Jamal, A., Namboodiri, V.P., Deodhare, D., Venkatesh, K.: Deep domain adaptation in action space. In: BMVC, vol. 2, p. 5 (2018)
Kae, A., Song, Y.: Image to video domain adaptation using web supervision. In: WACV, pp. 567–575 (2020)
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR, pp. 1725–1732 (2014)
Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)
Kim, D., et al.: Learning cross-modal contrastive features for video domain adaptation. In: ICCV, pp. 13618–13627 (2021)
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: a large video database for human motion recognition. In: ICCV, pp. 2556–2563. IEEE (2011)
Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.S.: Attention transfer from web images for video recognition. In: ACM Multimedia, pp. 1–9 (2017)
Li, Y., Wang, N., Shi, J., Hou, X., Liu, J.: Adaptive batch normalization for practical domain adaptation. Pattern Recogn. 80, 109–117 (2018)
Liu, H., Wang, J., Long, M.: Cycle self-training for domain adaptation. arXiv preprint arXiv:2103.03571 (2021)
Liu, Y., Lu, Z., Li, J., Yang, T., Yao, C.: Deep image-to-video adaptation and fusion networks for action recognition. TIP 29, 3168–3182 (2019)
Luo, Y., Huang, Z., Wang, Z., Zhang, Z., Baktashmotlagh, M.: Adversarial bipartite graph learning for video domain adaptation. In: ACM Multimedia, pp. 19–27 (2020)
Ma, S., Bargal, S.A., Zhang, J., Sigal, L., Sclaroff, S.: Do less and achieve more: training cnns for action recognition utilizing action images from the web. Pattern Recogn. 68, 334–345 (2017)
Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. JMLR 9(11) (2008)
Munro, J., Damen, D.: Multi-modal domain adaptation for fine-grained action recognition. In: CVPR, pp. 122–132 (2020)
Pan, B., Cao, Z., Adeli, E., Niebles, J.C.: Adversarial cross-domain action recognition with co-attention. In: AAAI, vol. 34, pp. 11815–11822 (2020)
Sahoo, A., Shah, R., Panda, R., Saenko, K., Das, A.: Contrast and mix: temporal contrastive video domain adaptation with background mixing. In: NeurIPS (2021)
Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR, pp. 3723–3732 (2018)
Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)
Sun, C., Shetty, S., Sukthankar, R., Nevatia, R.: Temporal localization of fine-grained actions in videos by domain transfer from web images. In: ACM Multimedia, pp. 371–380 (2015)
Tanisik, G., Zalluhoglu, C., Ikizler-Cinbis, N.: Facial descriptors for human interaction recognition in still images. Pattern Recogn. Lett. 73, 44–51 (2016)
Wang, L., Xiong, Y., Lin, D., Van Gool, L.: Untrimmednets for weakly supervised action recognition and detection. In: CVPR, pp. 4325–4334 (2017)
Wang, Z., She, Q., Smolic, A.: Action-net: multipath excitation for action recognition. In: CVPR (2021)
Yang, C., Xu, Y., Shi, J., Dai, B., Zhou, B.: Temporal pyramid network for action recognition. In: CVPR (2020)
Yang, J., Sun, X., Lai, Y.K., Zheng, L., Cheng, M.M.: Recognition from web data: a progressive filtering approach. TIP 27(11), 5303–5315 (2018)
Yao, B., Jiang, X., Khosla, A., Lin, A.L., Guibas, L., Fei-Fei, L.: Human action recognition by learning bases of action attributes and parts. In: ICCV, pp. 1331–1338. IEEE (2011)
Yu, F., Wu, X., Chen, J., Duan, L.: Exploiting images for video recognition: heterogeneous feature augmentation via symmetric adversarial learning. TIP 28(11), 5308–5321 (2019)
Yu, F., Wu, X., Sun, Y., Duan, L.: Exploiting images for video recognition with hierarchical generative adversarial networks. In: IJCAI (2018)
Zhang, J., Han, Y., Tang, J., Hu, Q., Jiang, J.: Semi-supervised image-to-video adaptation for video action recognition. IEEE Trans. Cybern. 47(4), 960–973 (2016)
Zhang, Y., Deng, B., Jia, K., Zhang, L.: Label propagation with augmented anchors: a simple semi-supervised learning baseline for unsupervised domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 781–797. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58548-8_45
Zhuang, B., Liu, L., Li, Y., Shen, C., Reid, I.: Attend in groups: a weakly-supervised deep learning framework for learning from web data. In: CVPR, pp. 1878–1887 (2017)
Zou, Y., Yu, Z., Kumar, B., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: ECCV, pp. 289–305 (2018)
Zou, Y., Yu, Z., Liu, X., Kumar, B., Wang, J.: Confidence regularized self-training. In: ICCV, pp. 5982–5991 (2019)
Acknowledgements
This work was partially funded by the Austrian Research Promotion Agency (FFG) project 874065 and by the Christian Doppler Laboratory for Semantic 3D Computer Vision, funded in part by Qualcomm Inc.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, W., Kukleva, A., Sun, K., Possegger, H., Kuehne, H., Bischof, H. (2022). CycDA: Unsupervised Cycle Domain Adaptation to Learn from Image to Video. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13663. Springer, Cham. https://doi.org/10.1007/978-3-031-20062-5_40
Download citation
DOI: https://doi.org/10.1007/978-3-031-20062-5_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20061-8
Online ISBN: 978-3-031-20062-5
eBook Packages: Computer ScienceComputer Science (R0)