{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T18:05:49Z","timestamp":1793901949666,"version":"4.8.0"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733963","type":"print"},{"value":"9783031733970","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-73397-0_17","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T15:08:15Z","timestamp":1730560095000},"page":"286-303","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["Decoupling Common and\u00a0Unique Representations for\u00a0Multimodal Self-supervised Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3096-6610","authenticated-orcid":false,"given":"Yi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2422-7289","authenticated-orcid":false,"given":"Conrad M.","family":"Albrecht","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3346-3373","authenticated-orcid":false,"given":"Nassim Ait Ali","family":"Braham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9172-3586","authenticated-orcid":false,"given":"Chenying","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3953-585X","authenticated-orcid":false,"given":"Zhitong","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5530-3613","authenticated-orcid":false,"given":"Xiao Xiang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"17_CR1","unstructured":"Akbari, H., et al.: VATT: transformers for multimodal self-supervised learning from raw video, audio and text. In: Advances in Neural Information Processing Systems, vol. 34, pp. 24206\u201324221 (2021)"},{"key":"17_CR2","doi-asserted-by":"publisher","unstructured":"Baier, G., Deschemps, A., Schmitt, M., Yokoya, N.: GeoNRW (2020). https:\/\/doi.org\/10.21227\/s5xq-b822","DOI":"10.21227\/s5xq-b822"},{"key":"17_CR3","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: VICReg: variance-invariance-covariance regularization for self-supervised learning. arXiv preprint arXiv:2105.04906 (2021)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Cao, J., Leng, H., Lischinski, D., Cohen-Or, D., Tu, C., Li, Y.: ShapeConv: shape-aware convolutional layer for indoor RGB-D semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7088\u20137097 (2021)","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"17_CR5","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9912\u20139924 (2020)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"17_CR7","doi-asserted-by":"publisher","first-page":"2313","DOI":"10.1109\/TIP.2021.3049332","volume":"30","author":"LZ Chen","year":"2021","unstructured":"Chen, L.Z., Lin, Z., Wang, Z., Yang, Y.L., Cheng, M.M.: Spatial information guided convolution for real-time RGBD semantic segmentation. IEEE Trans. Image Process. 30, 2313\u20132324 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR8","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"17_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-030-58621-8_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Chen","year":"2020","unstructured":"Chen, X., et al.: Bi-directional cross-modality feature propagation with separation-and-aggregation gate for RGB-D semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 561\u2013577. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_33"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"17_CR11","unstructured":"Cong, Y., et al.: SatMAE: pre-training transformers for temporal and multi-spectral satellite imagery. In: Advances in Neural Information Processing Systems, vol. 35, pp. 197\u2013211 (2022)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Dunteman, G.H.: Principal Components Analysis, vol.\u00a069. Sage (1989)","DOI":"10.4135\/9781412985475"},{"issue":"3","key":"17_CR13","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/MSP.2021.3134634","volume":"39","author":"L Ericsson","year":"2022","unstructured":"Ericsson, L., Gouk, H., Loy, C.C., Hospedales, T.M.: Self-supervised representation learning: introduction, advances, and challenges. IEEE Signal Process. Mag. 39(3), 42\u201362 (2022)","journal-title":"IEEE Signal Process. Mag."},{"key":"17_CR14","unstructured":"Fuller, A., Millard, K., Green, J.: Croma: remote sensing representations with contrastive radar-optical masked autoencoders. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"17_CR15","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728 (2018)"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: ImageBind: one embedding space to bind them all. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15180\u201315190, June 2023","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Singh, M., Ravi, N., van\u00a0der Maaten, L., Joulin, A., Misra, I.: OMNIVORE: a single model for many visual modalities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16102\u201316112, June 2022","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"17_CR18","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21271\u201321284 (2020)"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Guo, X., et\u00a0al.: SkySense: a multi-modal remote sensing foundation model towards universal interpretation for earth observation imagery. arXiv preprint arXiv:2312.10115 (2023)","DOI":"10.1109\/CVPR52733.2024.02613"},{"key":"17_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-319-10584-0_23","volume-title":"Computer Vision \u2013 ECCV 2014","author":"S Gupta","year":"2014","unstructured":"Gupta, S., Girshick, R., Arbel\u00e1ez, P., Malik, J.: Learning rich features from RGB-D images for object detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 345\u2013360. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_23"},{"key":"17_CR21","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR24","unstructured":"Hong, D., et\u00a0al.: SpectralGPT: spectral foundation model. arXiv preprint arXiv:2311.07113 (2023)"},{"issue":"12","key":"17_CR25","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1038\/s41551-022-00914-1","volume":"6","author":"R Krishnan","year":"2022","unstructured":"Krishnan, R., Rajpurkar, P., Topol, E.J.: Self-supervised learning in medicine and healthcare. Nat. Biomed. Eng. 6(12), 1346\u20131352 (2022)","journal-title":"Nat. Biomed. Eng."},{"key":"17_CR26","unstructured":"Liang, P.P., Deng, Z., Ma, M.Q., Zou, J.Y., Morency, L.P., Salakhutdinov, R.: Factorized contrastive learning: going beyond multi-view redundancy. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"17_CR28","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Manas, O., Lacoste, A., Gir\u00f3-i Nieto, X., Vazquez, D., Rodriguez, P.: Seasonal contrast: unsupervised pre-training from uncurated remote sensing data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9414\u20139423 (2021)","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Mendieta, M., Han, B., Shi, X., Zhu, Y., Chen, C.: Towards geospatial foundation models via continual pretraining. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16806\u201316816 (2023)","DOI":"10.1109\/ICCV51070.2023.01541"},{"key":"17_CR31","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-3-031-19809-0_30","volume-title":"ECCV 2022","author":"N Mu","year":"2022","unstructured":"Mu, N., Kirillov, A., Wagner, D., Xie, S.: SLIP: self-supervision meets language-image pre-training. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13686, pp. 529\u2013544. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_30"},{"key":"17_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"17_CR33","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Peng, X., Wei, Y., Deng, A., Wang, D., Hu, D.: Balanced multimodal learning via on-the-fly gradient modulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8238\u20138247 (2022)","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"17_CR35","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Scheibenreif, L., Hanna, J., Mommert, M., Borth, D.: Self-supervised vision transformers for land-cover segmentation and classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1422\u20131431 (2022)","DOI":"10.1109\/CVPRW56347.2022.00148"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"issue":"3","key":"17_CR39","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1109\/MGRS.2021.3089174","volume":"9","author":"G Sumbul","year":"2021","unstructured":"Sumbul, G., et al.: BigEarthNet-MM: a large-scale, multimodal, multilabel benchmark archive for remote sensing image classification and retrieval [software and data sets]. IEEE Geosci. Remote Sens. Mag. 9(3), 174\u2013180 (2021)","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"17_CR40","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319\u20133328. PMLR (2017)"},{"key":"17_CR41","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A., Bottou, L.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11(12) (2010)"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Wang, L., Luc, P., Recasens, A., Alayrac, J.B., Oord, A.V.D.: Multimodal self-supervised learning of general audio representations. arXiv preprint arXiv:2104.12807 (2021)","DOI":"10.1109\/ICASSP43922.2022.9746790"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Y., Albrecht, C.M., Braham, N.A.A., Mou, L., Zhu, X.X.: Self-supervised learning in remote sensing: a review. arXiv preprint arXiv:2206.13188 (2022)","DOI":"10.1109\/MGRS.2022.3198244"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Y., Albrecht, C.M., Zhu, X.X.: Self-supervised vision transformers for joint SAR-optical representation learning. In: IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium, pp. 139\u2013142. IEEE (2022)","DOI":"10.1109\/IGARSS46834.2022.9883983"},{"key":"17_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Y., Braham, N.A.A., Xiong, Z., Liu, C., Albrecht, C.M., Zhu, X.X.: SSL4EO-S12: a large-scale multi-modal, multi-temporal dataset for self-supervised learning in earth observation. arXiv preprint arXiv:2211.07044 (2022)","DOI":"10.1109\/MGRS.2023.3281651"},{"issue":"3","key":"17_CR46","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/MGRS.2023.3281651","volume":"11","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Braham, N.A.A., Xiong, Z., Liu, C., Albrecht, C.M., Zhu, X.X.: SSL4EO-S12: a large-scale multimodal, multitemporal dataset for self-supervised learning in earth observation [software and data sets]. IEEE Geosci. Remote Sens. Mag. 11(3), 98\u2013106 (2023)","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"17_CR47","unstructured":"Wang, Y., Hern\u00e1ndez, H.H., Albrecht, C.M., Zhu, X.X.: Feature guided masked autoencoder for self-supervised learning in remote sensing. arXiv preprint arXiv:2310.18653 (2023)"},{"key":"17_CR48","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/978-3-031-20056-4_20","volume-title":"ECCV 2022","author":"L Wei","year":"2022","unstructured":"Wei, L., Xie, L., Zhou, W., Li, H., Tian, Q.: MVP: multimodality-guided visual pre-training. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13690, pp. 337\u2013353. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_20"},{"key":"17_CR49","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4794\u20134803 (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: DAT++: spatially dynamic vision transformer with deformable attention. arXiv preprint arXiv:2309.01430 (2023)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"17_CR51","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 12077\u201312090 (2021)"},{"key":"17_CR52","unstructured":"Xiong, Z., et al.: Neural plasticity-inspired foundation model for observing the earth crossing modalities. arXiv preprint arXiv:2403.15356 (2024)"},{"key":"17_CR53","doi-asserted-by":"crossref","unstructured":"Xiong, Z., Wang, Y., Zhang, F., Zhu, X.X.: One for all: toward unified foundation models for earth vision. arXiv preprint arXiv:2401.07527 (2024)","DOI":"10.1109\/IGARSS53475.2024.10641637"},{"key":"17_CR54","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.neucom.2019.09.066","volume":"373","author":"Z Xiong","year":"2020","unstructured":"Xiong, Z., Yuan, Y., Wang, Q.: MSN: modality separation networks for RGB-D scene recognition. Neurocomputing 373, 81\u201389 (2020)","journal-title":"Neurocomputing"},{"key":"17_CR55","doi-asserted-by":"publisher","first-page":"2722","DOI":"10.1109\/TIP.2021.3053459","volume":"30","author":"Z Xiong","year":"2021","unstructured":"Xiong, Z., Yuan, Y., Wang, Q.: ASK: adaptively selecting key local features for RGB-D scene recognition. IEEE Trans. Image Process. 30, 2722\u20132733 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR56","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Vision-language pre-training with triple contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15671\u201315680 (2022)","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"17_CR57","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow Twins: self-supervised learning via redundancy reduction. In: International Conference on Machine Learning, pp. 12310\u201312320. PMLR (2021)"},{"key":"17_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, J., Liu, H., Yang, K., Hu, X., Liu, R., Stiefelhagen, R.: CMX: cross-modal fusion for RGB-X semantic segmentation with transformers. arXiv preprint arXiv:2203.04838 (2022)","DOI":"10.1109\/TITS.2023.3300537"},{"key":"17_CR59","doi-asserted-by":"crossref","unstructured":"Zhou, J., Yu, Q., Luo, C., Zhang, J.: Feature decomposition for reducing negative transfer: a novel multi-task learning method for recommender system. arXiv preprint arXiv:2302.05031 (2023)","DOI":"10.1609\/aaai.v37i13.27055"}],"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\/978-3-031-73397-0_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T15:20:06Z","timestamp":1730560806000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73397-0_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733963","9783031733970"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73397-0_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 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"}}]}}