{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T18:12:31Z","timestamp":1783793551503,"version":"3.55.0"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732010","type":"print"},{"value":"9783031732027","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73202-7_16","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T14:19:13Z","timestamp":1732112353000},"page":"270-287","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Towards Multimodal Open-Set Domain Generalization and\u00a0Adaptation Through Self-supervision"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8562-1946","authenticated-orcid":false,"given":"Hao","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6870-240X","authenticated-orcid":false,"given":"Eleni","family":"Chatzi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9546-1488","authenticated-orcid":false,"given":"Olga","family":"Fink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"16_CR1","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. In: ICLR (2022)"},{"key":"16_CR2","unstructured":"Bergman, L., Hoshen, Y.: Classification-based anomaly detection for general data. arXiv preprint arXiv:2005.02359 (2020)"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Blum, H., Sarlin, P.E., Nieto, J., Siegwart, R., Cadena, C.: Fishyscapes: a benchmark for safe semantic segmentation in autonomous driving. In: ICCVW (2019)","DOI":"10.1109\/ICCVW.2019.00294"},{"key":"16_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1007\/978-3-030-58517-4_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Bucci","year":"2020","unstructured":"Bucci, S., Loghmani, M.R., Tommasi, T.: On the effectiveness of image rotation for open set domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 422\u2013438. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_25"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Carlucci, F.M., D\u2019Innocente, A., Bucci, S., Caputo, B., Tommasi, T.: Domain generalization by solving jigsaw puzzles. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00233"},{"key":"16_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607 (2020)"},{"key":"16_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1007\/978-3-030-01225-0_44","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Damen","year":"2018","unstructured":"Damen, D., et al.: Scaling egocentric vision: the EPIC-KITCHENS dataset. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 753\u2013771. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_44"},{"key":"16_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"16_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104283","volume":"159","author":"H Dong","year":"2023","unstructured":"Dong, H., Chen, X., S\u00e4rkk\u00e4, S., Stachniss, C.: Online pole segmentation on range images for long-term LiDAR localization in urban environments. Robot. Auton. Syst. 159, 104283 (2023)","journal-title":"Robot. Auton. Syst."},{"key":"16_CR12","unstructured":"Dong, H., Nejjar, I., Sun, H., Chatzi, E., Fink, O.: SimMMDG: a simple and effective framework for multi-modal domain generalization. In: NeurIPS (2023)"},{"key":"16_CR13","unstructured":"Dong, H., et al.: SuperFusion: multilevel LiDAR-camera fusion for long-range HD map generation. arXiv preprint arXiv:2211.15656 (2022)"},{"key":"16_CR14","unstructured":"Dong, H., Zhao, Y., Chatzi, E., Fink, O.: MultiOOD: scaling out-of-distribution detection for multiple modalities. arXiv preprint arXiv:2405.17419 (2024)"},{"key":"16_CR15","unstructured":"Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)"},{"issue":"1","key":"16_CR16","first-page":"1","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 1\u201335 (2016). ISSN: 2096-2030","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR17","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728 (2018)"},{"key":"16_CR18","unstructured":"Golan, I., El-Yaniv, R.: Deep anomaly detection using geometric transformations. In: NeurIPS (2018)"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Gupta, S., Hoffman, J., Malik, J.: Cross modal distillation for supervision transfer. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.309"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"16_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1007\/978-3-030-58536-5_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Huang","year":"2020","unstructured":"Huang, Z., Wang, H., Xing, E.P., Huang, D.: Self-challenging improves cross-domain generalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 124\u2013140. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_8"},{"key":"16_CR23","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Kazakos, E., Nagrani, A., Zisserman, A., Damen, D.: EPIC-Fusion: audio-visual temporal binding for egocentric action recognition. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00559"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Kim, D., et al.: Learning cross-modal contrastive features for video domain adaptation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01336"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Larsson, G., Maire, M., Shakhnarovich, G.: Colorization as a proxy task for visual understanding. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.96"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Deeper, broader and artier domain generalization. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.591"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Learning to generalize: meta-learning for domain generalization. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Li, H., Pan, S.J., Wang, S., Kot, A.C.: Domain generalization with adversarial feature learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00566"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Li, J., Chen, P., He, Z., Yu, S., Liu, S., Jia, J.: Rethinking out-of-distribution (OOD) detection: masked image modeling is all you need. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01114"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, J., Han, B., Yuan, Y.: Adjustment and alignment for unbiased open set domain adaptation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02309"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Liu, H., Cao, Z., Long, M., Wang, J., Yang, Q.: Separate to adapt: open set domain adaptation via progressive separation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00304"},{"issue":"1","key":"16_CR33","first-page":"857","volume":"35","author":"X Liu","year":"2021","unstructured":"Liu, X., et al.: Self-supervised learning: generative or contrastive. IEEE Trans. Knowl. Data Eng. 35(1), 857\u2013876 (2021)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"16_CR34","unstructured":"Lu, W., Wang, J., Sun, X., Chen, Y., Xie, X.: Out-of-distribution representation learning for time series classification. In: ICLR (2023)"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"16_CR36","unstructured":"Muandet, K., Balduzzi, D., Sch\u00f6lkopf, B.: Domain generalization via invariant feature representation. In: ICML (2013)"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Munro, J., Damen, D.: Multi-modal domain adaptation for fine-grained action recognition. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00020"},{"key":"16_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"16_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/978-3-030-01225-0_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Pan","year":"2018","unstructured":"Pan, X., Luo, P., Shi, J., Tang, X.: Two at once: enhancing learning and generalization capacities via IBN-Net. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 484\u2013500. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_29"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Panareda\u00a0Busto, P., Gall, J.: Open set domain adaptation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.88"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"16_CR42","unstructured":"Piratla, V., Netrapalli, P., Sarawagi, S.: Efficient domain generalization via common-specific low-rank decomposition. In: ICML (2020)"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Planamente, M., Plizzari, C., Alberti, E., Caputo, B.: Domain generalization through audio-visual relative norm alignment in first person action recognition. In: WACV (2022)","DOI":"10.1109\/WACV51458.2022.00024"},{"key":"16_CR44","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Saha, A., Subramanya, A., Pirsiavash, H.: Hidden trigger backdoor attacks. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6871"},{"key":"16_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-030-01228-1_10","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K Saito","year":"2018","unstructured":"Saito, K., Yamamoto, S., Ushiku, Y., Harada, T.: Open set domain adaptation by backpropagation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 156\u2013171. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_10"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Shu, Y., Cao, Z., Wang, C., Wang, J., Long, M.: Open domain generalization with domain-augmented meta-learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00950"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: IROS (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"16_CR49","unstructured":"Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: maximizing for domain invariance. arXiv preprint arXiv:1412.3474 (2014)"},{"key":"16_CR50","unstructured":"Wang, D., Shelhamer, E., Liu, S., Olshausen, B., Darrell, T.: Tent: fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726 (2020)"},{"issue":"8","key":"16_CR51","first-page":"8052","volume":"35","author":"J Wang","year":"2022","unstructured":"Wang, J., et al.: Generalizing to unseen domains: a survey on domain generalization. IEEE Trans. Knowl. Data Eng. 35(8), 8052\u20138072 (2022)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, J., Qi, L., Shi, Y.: Generalizable decision boundaries: dualistic meta-learning for open set domain generalization. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01062"},{"key":"16_CR53","doi-asserted-by":"crossref","unstructured":"You, K., Long, M., Cao, Z., Wang, J., Jordan, M.I.: Universal domain adaptation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00283"},{"key":"16_CR54","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: ICLR (2018)"},{"key":"16_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Doughty, H., Shao, L., Snoek, C.G.: Audio-adaptive activity recognition across video domains. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01342"},{"key":"16_CR56","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, Y., Hospedales, T., Xiang, T.: Deep domain-adversarial image generation for domain generalisation. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.7003"},{"key":"16_CR57","unstructured":"Zhu, R., Li, S.: CrossMatch: cross-classifier consistency regularization for open-set single domain generalization. In: ICLR (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73202-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T15:09:32Z","timestamp":1732115372000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73202-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031732010","9783031732027"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73202-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}