{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:20:05Z","timestamp":1790274005337,"version":"4.1.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726699","type":"print"},{"value":"9783031726705","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72670-5_4","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"57-74","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Formula-Supervised Visual-Geometric Pre-training"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2154-8230","authenticated-orcid":false,"given":"Ryosuke","family":"Yamada","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6463-7738","authenticated-orcid":false,"given":"Kensho","family":"Hara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8844-165X","authenticated-orcid":false,"given":"Hirokatsu","family":"Kataoka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4145-7595","authenticated-orcid":false,"given":"Koshi","family":"Makihara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9761-4142","authenticated-orcid":false,"given":"Nakamasa","family":"Inoue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7573-7873","authenticated-orcid":false,"given":"Rio","family":"Yokota","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0638-0855","authenticated-orcid":false,"given":"Yutaka","family":"Satoh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Afham, M., Dissanayake, I., Dissanayake, D., Dharmasiri, A., Thilakarathna, K., Rodrigo, R.: Crosspoint: self-supervised cross-modal contrastive learning for 3D point cloud understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9902\u20139912 (2022)","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"4_CR2","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 (ICCV), pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"4_CR3","unstructured":"Chang, A.X., et\u00a0al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"4_CR5","unstructured":"Dehghani, M., et\u00a0al.: Scaling vision transformers to 22 billion parameters. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 7480\u20137512 (2023)"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse-XL: a universe of 10m+ 3D objects. In: Proceedings of the Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"4_CR7","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"4_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of the International Conference on Learning Representation (ICLR) (2021)"},{"issue":"1","key":"4_CR9","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. (IJCV) 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"4_CR10","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 (CVPR), pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Hou, J., Xie, S., Graham, B., Dai, A., Nie\u00dfner, M.: Pri3D: can 3D priors help 2D representation learning? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 5693\u20135702 (2021)","DOI":"10.1109\/ICCV48922.2021.00564"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Inoue, N., Yamagata, E., Kataoka, H.: Initialization using Perlin noise for training networks with a limited amount of data. In: Proceedings of the International Conference on Pattern Recognition (ICPR), pp. 1023\u20131028 (2021)","DOI":"10.1109\/ICPR48806.2021.9412955"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Jain, A., et al.: Odin: a single model for 2D and 3D segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3564\u20133574 (2024)","DOI":"10.1109\/CVPR52733.2024.00342"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Kataoka, H., Hara, K., Hayashi, R., Yamagata, E., Inoue, N.: Spatiotemporal initialization for 3D CNNs with generated motion patterns. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1279\u20131288 (2022)","DOI":"10.1109\/WACV51458.2022.00081"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Kataoka, H., et al.: Replacing labeled real-image datasets with auto-generated contours. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21232\u201321241 (2022)","DOI":"10.1109\/CVPR52688.2022.02055"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Kataoka, H., et al.: Pre-training without natural images. In: Proceedings of the Asian Conference on Computer Vision (ACCV) (2020)","DOI":"10.1007\/978-3-030-69544-6_35"},{"key":"4_CR17","unstructured":"Kirillov, A., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the International IEEE Workshop on 3D Representation and Recognition (3DRR-13), pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"4_CR19","unstructured":"Krizhevsky, A., Hinton, G.: Learning Multiple Layers of Features from Tiny Images. Technical report, University of Toronto (2009)"},{"key":"4_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1007\/978-3-030-58586-0_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Kundu","year":"2020","unstructured":"Kundu, A., et al.: Virtual multi-view fusion for 3D semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 518\u2013535. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_31"},{"key":"4_CR21","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1007\/978-3-031-20086-1_38","volume-title":"ECCV 2022","author":"H Liu","year":"2022","unstructured":"Liu, H., Cai, M., Lee, Y.J.: Masked discrimination for self-supervised learning on point clouds. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 657\u2013675. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_38"},{"key":"4_CR22","unstructured":"Liu, Y.C., et al.: Learning from 2D: contrastive pixel-to-point knowledge transfer for 3D pretraining. arXiv preprint arXiv:2104.04687 (2021)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Qi, X., Fu, C.W.: 3D-to-2D distillation for indoor scene parsing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4464\u20134474 (2021)","DOI":"10.1109\/CVPR46437.2021.00444"},{"key":"4_CR24","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2906\u20132917 (2021)","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Nakashima, K., Kataoka, H., Satoh, Y.: Does formula-driven supervised learning work on small datasets? IEEE Access (2023)","DOI":"10.1109\/ACCESS.2023.3320639"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing, pp. 722\u2013729 (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"4_CR28","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1007\/978-3-031-20086-1_35","volume-title":"ECCV 2022","author":"Y Pang","year":"2022","unstructured":"Pang, Y., Wang, W., Tay, F.E., Liu, W., Tian, Y., Yuan, L.: Masked autoencoders for point cloud self-supervised learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13662, pp. 604\u2013621. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_35"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep Hough voting for 3D object detection in point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Robert, D., Vallet, B., Landrieu, L.: Learning multi-view aggregation in the wild for large-scale 3d semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5575\u20135584 (2022)","DOI":"10.1109\/CVPR52688.2022.00549"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 843\u2013852 (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Takashima, S., Hayamizu, R., Inoue, N., Kataoka, H., Yokota, R.: Visual atoms: pre-training vision transformers with sinusoidal waves. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18579\u201318588 (2023)","DOI":"10.1109\/CVPR52729.2023.01782"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Tang, P., Xu, H.M., Ma, C.: Prototransfer: cross-modal prototype transfer for point cloud segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3337\u20133347 (2023)","DOI":"10.1109\/ICCV51070.2023.00309"},{"key":"4_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":"4_CR35","doi-asserted-by":"crossref","unstructured":"Uy, M.A., Pham, Q.H., Hua, B.S., Nguyen, T., Yeung, S.K.: Revisiting point cloud classification: a new benchmark dataset and classification model on real-world data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1588\u20131597 (2019)","DOI":"10.1109\/ICCV.2019.00167"},{"key":"4_CR36","unstructured":"Wang, Z., Yu, X., Rao, Y., Zhou, J., Lu, J.: P2p: tuning pre-trained image models for point cloud analysis with point-to-pixel prompting. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), pp. 14388\u201314402 (2022)"},{"key":"4_CR37","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J.: 3D shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1912\u20131920 (2015)"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Yamada, R., Kataoka, H., Chiba, N., Domae, Y., Ogata, T.: Point cloud pre-training with natural 3D structures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21283\u201321293 (2022)","DOI":"10.1109\/CVPR52688.2022.02060"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Yamada, R., et al.: Mv-FractaLDB: formula-driven supervised learning for multi-view image recognition. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2076\u20132083 (2021)","DOI":"10.1109\/IROS51168.2021.9635946"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Yi, X., Deng, J., Sun, Q., Hua, X.S., Lim, J.H., Zhang, H.: Invariant training 2D-3D joint hard samples for few-shot point cloud recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 14463\u201314474 (2023)","DOI":"10.1109\/ICCV51070.2023.01330"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Yu, X., Tang, L., Rao, Y., Huang, T., Zhou, J., Lu, J.: Point-Bert: pre-training 3D point cloud transformers with masked point modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19313\u201319322 (2022)","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 16259\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"issue":"6","key":"4_CR43","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2017","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 40(6), 1452\u20131464 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"}],"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\/978-3-031-72670-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:16:05Z","timestamp":1727594165000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72670-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726699","9783031726705"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72670-5_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}