{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:24:36Z","timestamp":1777656276613,"version":"3.51.4"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729126","type":"print"},{"value":"9783031729133","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-72913-3_19","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:46:23Z","timestamp":1733089583000},"page":"340-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["On the\u00a0Viability of\u00a0Monocular Depth Pre-training for\u00a0Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9308-7085","authenticated-orcid":false,"given":"Dong","family":"Lao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1094-8204","authenticated-orcid":false,"given":"Fengyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5737-4699","authenticated-orcid":false,"given":"Daniel","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0787-2082","authenticated-orcid":false,"given":"Hyoungseob","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4334-1374","authenticated-orcid":false,"given":"Samuel","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3157-6016","authenticated-orcid":false,"given":"Alex","family":"Wong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2902-6362","authenticated-orcid":false,"given":"Stefano","family":"Soatto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 417\u2013424 (2000)","DOI":"10.1145\/344779.344972"},{"key":"19_CR2","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Mairal, J., Joulin, A.: Unsupervised pre-training of image features on non-curated data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00305"},{"key":"19_CR4","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"},{"issue":"4","key":"19_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR6","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"19_CR7","unstructured":"Chen, M., Arti\u00e8res, T., Denoyer, L.: Unsupervised object segmentation by redrawing. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"19_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":"19_CR9","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"19_CR11","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: CVPR09 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"19_CR12","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"2","key":"19_CR13","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vision 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"issue":"2","key":"19_CR14","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1109\/LRA.2019.2896963","volume":"4","author":"X Fei","year":"2019","unstructured":"Fei, X., Wong, A., Soatto, S.: Geo-supervised visual depth prediction. IEEE Rob. Autom. Lett. 4(2), 1661\u20131668 (2019)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth prediction (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"19_CR17","unstructured":"Goldblum, M., et\u00a0al.: Battle of the backbones: a large-scale comparison of pretrained models across computer vision tasks. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u2019ar, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15979\u201315988 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Hoyer, L., Dai, D., Chen, Y., K\u00c3\u00b6ring, A., Saha, S., Van\u00a0Gool, L.: Three ways to improve semantic segmentation with self-supervised depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11130\u201311140 (2021)","DOI":"10.1109\/CVPR46437.2021.01098"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Hoyer, L., Dai, D., Wang, Q., Chen, Y., Van\u00a0Gool, L.: Improving semi-supervised and domain-adaptive semantic segmentation with self-supervised depth estimation. arXiv preprint arXiv:2108.12545 (2021)","DOI":"10.1109\/CVPR46437.2021.01098"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Huang, J., Lee, A.B., Mumford, D.: Statistics of range images. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No. PR00662), vol.\u00a01, pp. 324\u2013331. IEEE (2000)","DOI":"10.1109\/CVPR.2000.855836"},{"key":"19_CR22","unstructured":"Huang, J., Mumford, D.: Statistics of natural images and models. In: Proceedings 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), vol.\u00a01, pp. 541\u2013547. IEEE (1999)"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, H., Larsson, G., Shakhnarovich, M.M.G., Learned-Miller, E.: Self-supervised relative depth learning for urban scene understanding. In: Proceedings of the European Conference on Computer Vision (eccv), pp. 19\u201335 (2018)","DOI":"10.1007\/978-3-030-01252-6_2"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Jin, B., et al.: Exploring spatial-temporal multi-frequency analysis for high-fidelity and temporal-consistency video prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4554\u20134563 (2020)","DOI":"10.1109\/CVPR42600.2020.00461"},{"issue":"3630","key":"19_CR25","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1126\/science.145.3630.356","volume":"145","author":"B Julesz","year":"1964","unstructured":"Julesz, B.: Binocular depth perception without familiarity cues: random-dot stereo images with controlled spatial and temporal properties clarify problems in stereopsis. Science 145(3630), 356\u2013362 (1964)","journal-title":"Science"},{"key":"19_CR26","unstructured":"Julesz, B.: Foundations of cyclopean perception (1971)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"7","key":"19_CR28","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vision 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"19_CR29","unstructured":"Lao, D., Hu, Z., Locatello, F., Yang, Y., Soatto, S.: Divided attention: unsupervised multi-object discovery with contextually separated slots. arXiv preprint arXiv:2304.01430 (2023)"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Lao, D., Sundaramoorthi, G.: Minimum delay moving object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4250\u20134259 (2017)","DOI":"10.1109\/CVPR.2017.511"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Lao, D., Sundaramoorthi, G.: Extending layered models to 3d motion. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 435\u2013451 (2018)","DOI":"10.1007\/978-3-030-01249-6_27"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Lao, D., Zhu, P., Wonka, P., Sundaramoorthi, G.: Flow-guided video inpainting with scene templates. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14599\u201314608 (2021)","DOI":"10.1109\/ICCV48922.2021.01433"},{"key":"19_CR33","unstructured":"Lasinger, K., Ranftl, R., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. arXiv preprint arXiv:1907.01341 (2019)"},{"key":"19_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"19_CR35","doi-asserted-by":"publisher","unstructured":"Liu, T.Y., Agrawal, P., Chen, A., Hong, B.W., Wong, A.: Monitored distillation for positive congruent depth completion. In: European Conference on Computer Vision, pp. 35\u201353. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_3","DOI":"10.1007\/978-3-031-20086-1_3"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Lopez-Rodriguez, A., Busam, B., Mikolajczyk, K.: Project to adapt: domain adaptation for depth completion from noisy and sparse sensor data. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69525-5_20"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Nathan\u00a0Silberman, Derek\u00a0Hoiem, P.K., Fergus, R.: Indoor segmentation and support inference from rgbd images. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"19_CR38","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. Trans. Mach. Learn. Res. (2024). https:\/\/openreview.net\/forum?id=a68SUt6zFt"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Ramirez, P.Z., Tonioni, A., Salti, S., Stefano, L.D.: Learning across tasks and domains. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8110\u20138119 (2019)","DOI":"10.1109\/ICCV.2019.00820"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Saha, S., et al.: Learning to relate depth and semantics for unsupervised domain adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8197\u20138207 (2021)","DOI":"10.1109\/CVPR46437.2021.00810"},{"key":"19_CR43","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":"19_CR44","doi-asserted-by":"crossref","unstructured":"Sundaramoorthi, G., Petersen, P., Varadarajan, V., Soatto, S.: On the set of images modulo viewpoint and contrast changes. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 832\u2013839. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206704"},{"key":"19_CR45","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. arXiv preprint physics\/0004057 (2000)"},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wu, J., Long, M., Tenenbaum, J.B.: Probabilistic video prediction from noisy data with a posterior confidence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10830\u201310839 (2020)","DOI":"10.1109\/CVPR42600.2020.01084"},{"issue":"2","key":"19_CR47","doi-asserted-by":"publisher","first-page":"1495","DOI":"10.1109\/LRA.2021.3058072","volume":"6","author":"A Wong","year":"2021","unstructured":"Wong, A., Cicek, S., Soatto, S.: Learning topology from synthetic data for unsupervised depth completion. IEEE Rob. Autom. Lett. 6(2), 1495\u20131502 (2021)","journal-title":"IEEE Rob. Autom. Lett."},{"issue":"2","key":"19_CR48","doi-asserted-by":"publisher","first-page":"3120","DOI":"10.1109\/LRA.2021.3062602","volume":"6","author":"A Wong","year":"2021","unstructured":"Wong, A., Fei, X., Hong, B.W., Soatto, S.: An adaptive framework for learning unsupervised depth completion. IEEE Rob. Autom. Lett. 6(2), 3120\u20133127 (2021)","journal-title":"IEEE Rob. Autom. Lett."},{"issue":"2","key":"19_CR49","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1109\/LRA.2020.2969938","volume":"5","author":"A Wong","year":"2020","unstructured":"Wong, A., Fei, X., Tsuei, S., Soatto, S.: Unsupervised depth completion from visual inertial odometry. IEEE Rob. Autom. Lett. 5(2), 1899\u20131906 (2020)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Wong, A., Soatto, S.: Bilateral cyclic constraint and adaptive regularization for unsupervised monocular depth prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5644\u20135653 (2019)","DOI":"10.1109\/CVPR.2019.00579"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Wong, A., Soatto, S.: Unsupervised depth completion with calibrated backprojection layers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12747\u201312756 (2021)","DOI":"10.1109\/ICCV48922.2021.01251"},{"key":"19_CR52","doi-asserted-by":"crossref","unstructured":"Wu, Y., Liu, T.Y., Park, H., Soatto, S., Lao, D., Wong, A.: Augundo: scaling up augmentations for monocular depth completion and estimation. In: European Conference on Computer Vision. Springer, Heidelberg (2024)","DOI":"10.1007\/978-3-031-73039-9_16"},{"key":"19_CR53","doi-asserted-by":"crossref","unstructured":"Wu, Y., Gao, R., Park, J., Chen, Q.: Future video synthesis with object motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5539\u20135548 (2020)","DOI":"10.1109\/CVPR42600.2020.00558"},{"key":"19_CR54","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. arXiv preprint arXiv:2401.10891 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"19_CR55","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"19_CR56","doi-asserted-by":"crossref","unstructured":"Yang, Y., Wong, A., Soatto, S.: Dense depth posterior (ddp) from single image and sparse range. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3353\u20133362 (2019)","DOI":"10.1109\/CVPR.2019.00347"},{"key":"19_CR57","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: disentangling task transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3712\u20133722 (2018)","DOI":"10.1109\/CVPR.2018.00391"},{"key":"19_CR58","doi-asserted-by":"crossref","unstructured":"Zeng, Z., et al.: Wordepth: variational language prior for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9708\u20139719 (2024)","DOI":"10.1109\/CVPR52733.2024.00927"},{"key":"19_CR59","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"}],"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\/978-3-031-72913-3_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:25:29Z","timestamp":1733095529000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72913-3_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031729126","9783031729133"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72913-3_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 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"}}]}}