{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:29:41Z","timestamp":1742912981949,"version":"3.40.3"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031200618"},{"type":"electronic","value":"9783031200625"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20062-5_40","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T10:31:55Z","timestamp":1668076315000},"page":"698-715","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CycDA: Unsupervised Cycle Domain Adaptation to\u00a0Learn from\u00a0Image to\u00a0Video"],"prefix":"10.1007","author":[{"given":"Wei","family":"Lin","sequence":"first","affiliation":[]},{"given":"Anna","family":"Kukleva","sequence":"additional","affiliation":[]},{"given":"Kunyang","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Horst","family":"Possegger","sequence":"additional","affiliation":[]},{"given":"Hilde","family":"Kuehne","sequence":"additional","affiliation":[]},{"given":"Horst","family":"Bischof","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"40_CR1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., Wu, X., Hu, Y., Luo, J.: Spatial-temporal causal inference for partial image-to-video adaptation. In: AAAI, vol. 35, pp. 1027\u20131035 (2021)","DOI":"10.1609\/aaai.v35i2.16187"},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"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\u20136330 (2019)","DOI":"10.1109\/ICCV.2019.00642"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Chen, M.H., Li, B., Bao, Y., AlRegib, G., Kira, Z.: Action segmentation with joint self-supervised temporal domain adaptation. In: CVPR, pp. 9454\u20139463 (2020)","DOI":"10.1109\/CVPR42600.2020.00947"},{"key":"40_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607. PMLR (2020)"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Choi, J., Sharma, G., Chandraker, M., Huang, J.B.: Unsupervised and semi-supervised domain adaptation for action recognition from drones. In: WACV, pp. 1717\u20131726 (2020)","DOI":"10.1109\/WACV45572.2020.9093511"},{"key":"40_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1007\/978-3-030-58610-2_40","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Choi","year":"2020","unstructured":"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\u2013695. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_40"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"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\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"40_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1007\/978-3-030-58555-6_40","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Duan","year":"2020","unstructured":"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\u2013688. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_40"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3d: expanding architectures for efficient video recognition. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"40_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1007\/978-3-319-46487-9_52","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Gan","year":"2016","unstructured":"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\u2013866. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_52"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"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)","DOI":"10.1609\/aaai.v31i1.11222"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"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\u2013932 (2016)","DOI":"10.1109\/CVPR.2016.106"},{"key":"40_CR14","unstructured":"Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML, pp. 1180\u20131189. PMLR (2015)"},{"issue":"1","key":"40_CR15","first-page":"2030","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. JMLR 17(1), 2030\u20132096 (2016)","journal-title":"JMLR"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Guo, S., et al.: Curriculumnet: weakly supervised learning from large-scale web images. In: ECCV, pp. 135\u2013150 (2018)","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"40_CR18","unstructured":"Jamal, A., Namboodiri, V.P., Deodhare, D., Venkatesh, K.: Deep domain adaptation in action space. In: BMVC, vol. 2, p. 5 (2018)"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Kae, A., Song, Y.: Image to video domain adaptation using web supervision. In: WACV, pp. 567\u2013575 (2020)","DOI":"10.1109\/WACV45572.2020.9093645"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"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\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"40_CR21","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Kim, D., et al.: Learning cross-modal contrastive features for video domain adaptation. In: ICCV, pp. 13618\u201313627 (2021)","DOI":"10.1109\/ICCV48922.2021.01336"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: a large video database for human motion recognition. In: ICCV, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.S.: Attention transfer from web images for video recognition. In: ACM Multimedia, pp. 1\u20139 (2017)","DOI":"10.1145\/3123266.3123432"},{"key":"40_CR25","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2018.03.005","volume":"80","author":"Y Li","year":"2018","unstructured":"Li, Y., Wang, N., Shi, J., Hou, X., Liu, J.: Adaptive batch normalization for practical domain adaptation. Pattern Recogn. 80, 109\u2013117 (2018)","journal-title":"Pattern Recogn."},{"key":"40_CR26","unstructured":"Liu, H., Wang, J., Long, M.: Cycle self-training for domain adaptation. arXiv preprint arXiv:2103.03571 (2021)"},{"key":"40_CR27","first-page":"3168","volume":"29","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Lu, Z., Li, J., Yang, T., Yao, C.: Deep image-to-video adaptation and fusion networks for action recognition. TIP 29, 3168\u20133182 (2019)","journal-title":"TIP"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Luo, Y., Huang, Z., Wang, Z., Zhang, Z., Baktashmotlagh, M.: Adversarial bipartite graph learning for video domain adaptation. In: ACM Multimedia, pp. 19\u201327 (2020)","DOI":"10.1145\/3394171.3413897"},{"key":"40_CR29","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1016\/j.patcog.2017.01.027","volume":"68","author":"S Ma","year":"2017","unstructured":"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\u2013345 (2017)","journal-title":"Pattern Recogn."},{"key":"40_CR30","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. JMLR 9(11) (2008)"},{"key":"40_CR31","doi-asserted-by":"crossref","unstructured":"Munro, J., Damen, D.: Multi-modal domain adaptation for fine-grained action recognition. In: CVPR, pp. 122\u2013132 (2020)","DOI":"10.1109\/CVPR42600.2020.00020"},{"key":"40_CR32","doi-asserted-by":"crossref","unstructured":"Pan, B., Cao, Z., Adeli, E., Niebles, J.C.: Adversarial cross-domain action recognition with co-attention. In: AAAI, vol. 34, pp. 11815\u201311822 (2020)","DOI":"10.1609\/aaai.v34i07.6854"},{"key":"40_CR33","unstructured":"Sahoo, A., Shah, R., Panda, R., Saenko, K., Das, A.: Contrast and mix: temporal contrastive video domain adaptation with background mixing. In: NeurIPS (2021)"},{"key":"40_CR34","doi-asserted-by":"crossref","unstructured":"Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR, pp. 3723\u20133732 (2018)","DOI":"10.1109\/CVPR.2018.00392"},{"key":"40_CR35","unstructured":"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)"},{"key":"40_CR36","doi-asserted-by":"crossref","unstructured":"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\u2013380 (2015)","DOI":"10.1145\/2733373.2806226"},{"key":"40_CR37","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.patrec.2016.01.002","volume":"73","author":"G Tanisik","year":"2016","unstructured":"Tanisik, G., Zalluhoglu, C., Ikizler-Cinbis, N.: Facial descriptors for human interaction recognition in still images. Pattern Recogn. Lett. 73, 44\u201351 (2016)","journal-title":"Pattern Recogn. Lett."},{"key":"40_CR38","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., Van Gool, L.: Untrimmednets for weakly supervised action recognition and detection. In: CVPR, pp. 4325\u20134334 (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"40_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Z., She, Q., Smolic, A.: Action-net: multipath excitation for action recognition. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"40_CR40","doi-asserted-by":"crossref","unstructured":"Yang, C., Xu, Y., Shi, J., Dai, B., Zhou, B.: Temporal pyramid network for action recognition. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00067"},{"issue":"11","key":"40_CR41","first-page":"5303","volume":"27","author":"J Yang","year":"2018","unstructured":"Yang, J., Sun, X., Lai, Y.K., Zheng, L., Cheng, M.M.: Recognition from web data: a progressive filtering approach. TIP 27(11), 5303\u20135315 (2018)","journal-title":"TIP"},{"key":"40_CR42","doi-asserted-by":"crossref","unstructured":"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\u20131338. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126386"},{"issue":"11","key":"40_CR43","first-page":"5308","volume":"28","author":"F Yu","year":"2019","unstructured":"Yu, F., Wu, X., Chen, J., Duan, L.: Exploiting images for video recognition: heterogeneous feature augmentation via symmetric adversarial learning. TIP 28(11), 5308\u20135321 (2019)","journal-title":"TIP"},{"key":"40_CR44","doi-asserted-by":"crossref","unstructured":"Yu, F., Wu, X., Sun, Y., Duan, L.: Exploiting images for video recognition with hierarchical generative adversarial networks. In: IJCAI (2018)","DOI":"10.24963\/ijcai.2018\/154"},{"issue":"4","key":"40_CR45","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1109\/TCYB.2016.2535122","volume":"47","author":"J Zhang","year":"2016","unstructured":"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\u2013973 (2016)","journal-title":"IEEE Trans. Cybern."},{"key":"40_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1007\/978-3-030-58548-8_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zhang","year":"2020","unstructured":"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\u2013797. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_45"},{"key":"40_CR47","doi-asserted-by":"crossref","unstructured":"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\u20131887 (2017)","DOI":"10.1109\/CVPR.2017.311"},{"key":"40_CR48","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yu, Z., Kumar, B., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: ECCV, pp. 289\u2013305 (2018)","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"40_CR49","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yu, Z., Liu, X., Kumar, B., Wang, J.: Confidence regularized self-training. In: ICCV, pp. 5982\u20135991 (2019)","DOI":"10.1109\/ICCV.2019.00608"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20062-5_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:23:26Z","timestamp":1668126206000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20062-5_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200618","9783031200625"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20062-5_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}