@inproceedings{d3c89c9c9e8143f2897ec4ea42ddaa0c,
title = "CycDA: Unsupervised Cycle Domain Adaptation to Learn from Image to Video",
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 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. ",
author = "Wei Lin and Anna Kukleva and Kunyang Sun and Horst Possegger and Hilde Kuehne and Horst Bischof",
year = "2022",
doi = "10.1007/978-3-031-20062-5_40",
language = "English",
isbn = "978-3-031-20061-8",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "698--715",
booktitle = "Computer Vision – ECCV 2022",
note = "2022 European Conference on Computer Vision : ECCV 2022, ECCV 2022 ; Conference date: 23-10-2022 Through 27-10-2022",
}