{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:14:25Z","timestamp":1771956865192,"version":"3.50.1"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726323","type":"print"},{"value":"9783031726330","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-72633-0_27","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T07:56:25Z","timestamp":1732175785000},"page":"478-496","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["TIP: Tabular-Image Pre-training for\u00a0Multimodal Classification with\u00a0Incomplete Data"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9961-4533","authenticated-orcid":false,"given":"Siyi","family":"Du","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5628-4311","authenticated-orcid":false,"given":"Shaoming","family":"Zheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7288-4227","authenticated-orcid":false,"given":"Yinsong","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2943-7698","authenticated-orcid":false,"given":"Wenjia","family":"Bai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0691-0270","authenticated-orcid":false,"given":"Declan P.","family":"O\u2019Regan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3417-3092","authenticated-orcid":false,"given":"Chen","family":"Qin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"issue":"9","key":"27_CR1","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","volume":"28","author":"JN Acosta","year":"2022","unstructured":"Acosta, J.N., Falcone, G.J., Rajpurkar, P., Topol, E.J.: Multimodal biomedical AI. Nat. Med. 28(9), 1773\u20131784 (2022)","journal-title":"Nat. Med."},{"key":"27_CR2","unstructured":"Antelmi, L., Ayache, N., Robert, P., Ribaldi, F., Garibotto, V., Frisoni, G.B., Lorenzi, M.: Combining multi-task learning and multi-channel variational auto-encoders to exploit datasets with missing observations-application to multi-modal neuroimaging studies in dementia. hal preprint hal-03114888v2 (2021)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Assran, M., Duval, Q., Misra, I., et\u00a0al.: Self-supervised learning from images with a joint-embedding predictive architecture. In: CVPR, pp. 15619\u201315629 (2023)","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"27_CR4","unstructured":"Bahri, D., Jiang, H., Tay, Y., Metzler, D.: SCARF: self-supervised contrastive learning using random feature corruption. In: ICLR (2022)"},{"issue":"10","key":"27_CR5","doi-asserted-by":"publisher","first-page":"1654","DOI":"10.1038\/s41591-020-1009-y","volume":"26","author":"W Bai","year":"2020","unstructured":"Bai, W., Suzuki, H., Huang, J., Francis, C., Wang, S., Tarroni, G., et al.: A population-based phenome-wide association study of cardiac and aortic structure and function. Nat. Med. 26(10), 1654\u20131662 (2020)","journal-title":"Nat. Med."},{"issue":"2","key":"27_CR6","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.P.: Multimodal machine learning: a survey and taxonomy. IEEE TPAMI 41(2), 423\u2013443 (2018)","journal-title":"IEEE TPAMI"},{"issue":"1","key":"27_CR7","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1177\/096228029900800103","volume":"8","author":"J Barnard","year":"1999","unstructured":"Barnard, J., Meng, X.L.: Applications of multiple imputation in medical studies: from AIDS to NHANES. Stat. Methods Med. Res. 8(1), 17\u201336 (1999)","journal-title":"Stat. Methods Med. Res."},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Bayasi, N., Hamarneh, G., Garbi, R.: Continual-Zoo: Leveraging zoo models for continual classification of medical images. In: CVPRW, pp. 4128\u20134138 (2024)","DOI":"10.1109\/CVPRW63382.2024.00416"},{"issue":"8","key":"27_CR9","doi-asserted-by":"publisher","first-page":"2939","DOI":"10.1007\/s00371-021-02166-7","volume":"38","author":"K Bayoudh","year":"2022","unstructured":"Bayoudh, K., Knani, R., Hamdaoui, F., Mtibaa, A.: A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Vis. Comput. 38(8), 2939\u20132970 (2022)","journal-title":"Vis. Comput."},{"key":"27_CR10","doi-asserted-by":"publisher","first-page":"7499","DOI":"10.1109\/TNNLS.2022.3229161","volume":"35","author":"V Borisov","year":"2022","unstructured":"Borisov, V., Leemann, T., Se\u00dfler, K., Haug, J., Pawelczyk, M., Kasneci, G.: Deep neural networks and tabular data: a survey. IEEE Trans. Neural Netw.Learn. Syst. 35, 7499\u20137519 (2022)","journal-title":"IEEE Trans. Neural Netw.Learn. Syst."},{"key":"27_CR11","doi-asserted-by":"publisher","first-page":"102719","DOI":"10.1016\/j.artmed.2023.102719","volume":"147","author":"B Borsos","year":"2024","unstructured":"Borsos, B., Allaart, C.G., van Halteren, A.: Predicting stroke outcome: a case for multimodal deep learning methods with tabular and CT perfusion data. Artif. Intell. Med. 147, 102719 (2024)","journal-title":"Artif. Intell. Med."},{"key":"27_CR12","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., et al.: Language models are few-shot learners. NIPS 33, 1877\u20131901 (2020)","journal-title":"NIPS"},{"issue":"3","key":"27_CR13","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1377\/hlthaff.2011.0178","volume":"30","author":"MB Buntin","year":"2011","unstructured":"Buntin, M.B., Burke, M.F., Hoaglin, M.C., Blumenthal, D.: The benefits of health information technology: a review of the recent literature shows predominantly positive results. Health Aff. 30(3), 464\u2013471 (2011)","journal-title":"Health Aff."},{"issue":"7726","key":"27_CR14","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41586-018-0579-z","volume":"562","author":"C Bycroft","year":"2018","unstructured":"Bycroft, C., Freeman, C., Petkova, D., et al.: The UK Biobank resource with deep phenotyping and genomic data. Nature 562(7726), 203\u2013209 (2018)","journal-title":"Nature"},{"key":"27_CR15","doi-asserted-by":"publisher","first-page":"133583","DOI":"10.1109\/ACCESS.2019.2941419","volume":"7","author":"Q Cai","year":"2019","unstructured":"Cai, Q., Wang, H., et al.: A survey on multimodal data-driven smart healthcare systems: approaches and applications. IEEE Access 7, 133583\u2013133599 (2019)","journal-title":"IEEE Access"},{"issue":"10","key":"27_CR16","doi-asserted-by":"publisher","first-page":"742","DOI":"10.7326\/0003-4819-144-10-200605160-00125","volume":"144","author":"B Chaudhry","year":"2006","unstructured":"Chaudhry, B., Wang, J., Wu, S., Maglione, M., Mojica, W., Roth, E., et al.: Systematic review: impact of health information technology on quality, efficiency, and costs of medical care. Ann. Intern. Med. 144(10), 742\u2013752 (2006)","journal-title":"Ann. Intern. Med."},{"issue":"1","key":"27_CR17","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s11633-022-1369-5","volume":"20","author":"FL Chen","year":"2023","unstructured":"Chen, F.L., Zhang, D.Z., Han, M.L., Chen, X.Y., et al.: VLP: a survey on vision-language pre-training. Mach. Intell. Res. 20(1), 38\u201356 (2023)","journal-title":"Mach. Intell. Res."},{"key":"27_CR18","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":"27_CR19","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: CVPR, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"27_CR20","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: ACL, pp. 4171\u20134186 (2019)"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Dong, H., et al.: Table pre-training: a survey on model architectures, pre-training objectives, and downstream tasks. arXiv preprint arXiv:2201.09745 (2022)","DOI":"10.24963\/ijcai.2022\/761"},{"key":"27_CR22","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s11704-019-8208-z","volume":"14","author":"X Dong","year":"2020","unstructured":"Dong, X., Yu, Z., Cao, W., Shi, Y., Ma, Q.: A survey on ensemble learning. Front. Comp. Sci. 14, 241\u2013258 (2020)","journal-title":"Front. Comp. Sci."},{"key":"27_CR23","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"27_CR24","doi-asserted-by":"publisher","unstructured":"Duanmu, H., et al.: Prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer using deep learning with integrative imaging, Molecular and demographic data. In: Martel, A.L., et al. (ed.) Medical Image Computing and Computer Assisted Intervention - MICCAI 2020, MICCAI 2020, LNCS, vol. 12262, pp 242\u2013252. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59713-9_24","DOI":"10.1007\/978-3-030-59713-9_24"},{"key":"27_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105151","volume":"115","author":"MA Ganaie","year":"2022","unstructured":"Ganaie, M.A., Hu, M., Malik, A., et al.: Ensemble deep learning: a review. Eng. Appl. Artif. Intell. 115, 105151 (2022)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Ghorbani, A., Zou, J.Y.: Embedding for informative missingness: Deep learning with incomplete data. In: 2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp. 437\u2013445. IEEE (2018)","DOI":"10.1109\/ALLERTON.2018.8636008"},{"key":"27_CR27","first-page":"18932","volume":"34","author":"Y Gorishniy","year":"2021","unstructured":"Gorishniy, Y., Rubachev, I., Khrulkov, V., Babenko, A.: Revisiting deep learning models for tabular data. NIPS 34, 18932\u201318943 (2021)","journal-title":"NIPS"},{"key":"27_CR28","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. NIPS 33, 21271\u201321284 (2020)","journal-title":"NIPS"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Hager, P., Menten, M.J., Rueckert, D.: Best of both worlds: multimodal contrastive learning with tabular and imaging data. In: CVPR, pp. 23924\u201323935 (2023)","DOI":"10.1109\/CVPR52729.2023.02291"},{"key":"27_CR30","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.neucom.2022.09.136","volume":"515","author":"X Han","year":"2023","unstructured":"Han, X., Wang, Y.T., Feng, J.L., Deng, C., et al.: A survey of transformer-based multimodal pre-trained modals. Neurocomputing 515, 89\u2013106 (2023)","journal-title":"Neurocomputing"},{"issue":"7","key":"27_CR31","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1080\/j.1440-1614.2005.01630.x","volume":"39","author":"G Hawthorne","year":"2005","unstructured":"Hawthorne, G., Hawthorne, G., Elliott, P.: Imputing cross-sectional missing data: comparison of common techniques. Australian New Zealand J. Psychiatry 39(7), 583\u2013590 (2005)","journal-title":"Australian New Zealand J. Psychiatry"},{"key":"27_CR32","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, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"27_CR33","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":"27_CR34","doi-asserted-by":"crossref","unstructured":"He, R., McAuley, J.: Ups and downs: modeling the visual evolution of fashion trends with one-class collaborative filtering. In: WWW, pp. 507\u2013517 (2016)","DOI":"10.1145\/2872427.2883037"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Heiliger, L., Sekuboyina, A., Menze, B., et\u00a0al.: Beyond medical imaging-a review of multimodal deep learning in radiology. Authorea Preprints (2023)","DOI":"10.36227\/techrxiv.19103432.v1"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Huang, J., Chen, B., Luo, L., et\u00a0al.: DVM-CAR: a large-scale automotive dataset for visual marketing research and applications. In: 2022 IEEE International Conference on Big Data (Big Data), pp. 4140\u20134147. IEEE (2022)","DOI":"10.1109\/BigData55660.2022.10020634"},{"issue":"1","key":"27_CR37","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41746-020-00341-z","volume":"3","author":"SC Huang","year":"2020","unstructured":"Huang, S.C., Pareek, A., Seyyedi, S., Banerjee, I., Lungren, M.P.: Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines. NPJ Digit. Med. 3(1), 136 (2020)","journal-title":"NPJ Digit. Med."},{"key":"27_CR38","unstructured":"Huang, X., Khetan, A., Cvitkovic, M., Karnin, Z.: TabTransformer: tabular data modeling using contextual embeddings. arXiv preprint arXiv:2012.06678 (2020)"},{"key":"27_CR39","unstructured":"Jarrett, D., Cebere, B.C., Liu, T., Curth, A., van\u00a0der Schaar, M.: HyperImpute: Generalized iterative imputation with automatic model selection. In: ICML, pp. 9916\u20139937. PMLR (2022)"},{"key":"27_CR40","unstructured":"Jiang, J.P., Ye, H.J., Wang, L., Yang, Y., Jiang, Y., Zhan, D.C.: On transferring expert knowledge from tabular data to images. In: NIPSW (2023)"},{"issue":"11","key":"27_CR41","doi-asserted-by":"publisher","first-page":"4037","DOI":"10.1109\/TPAMI.2020.2992393","volume":"43","author":"L Jing","year":"2020","unstructured":"Jing, L., Tian, Y.: Self-supervised visual feature learning with deep neural networks: a survey. IEEE TPAMI 43(11), 4037\u20134058 (2020)","journal-title":"IEEE TPAMI"},{"key":"27_CR42","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: MIMIC-III, a freely accessible critical care database. Sci. Data 3(1), 1\u20139 (2016)","DOI":"10.1038\/sdata.2016.35"},{"key":"27_CR43","doi-asserted-by":"publisher","first-page":"103982","DOI":"10.1016\/j.jbi.2021.103982","volume":"126","author":"KS Kalyan","year":"2022","unstructured":"Kalyan, K.S., Rajasekharan, A., Sangeetha, S.: AMMU: a survey of transformer-based biomedical pretrained language models. J. Biomed. Inform. 126, 103982 (2022)","journal-title":"J. Biomed. Inform."},{"issue":"9","key":"27_CR44","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.1109\/TMI.2022.3162870","volume":"41","author":"W Ko","year":"2022","unstructured":"Ko, W., Jung, W., Jeon, E., Suk, H.I.: A deep generative-discriminative learning for multimodal representation in imaging genetics. IEEE Trans. Med. Imaging 41(9), 2348\u20132359 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"27_CR45","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, pp. 12888\u201312900. PMLR (2022)"},{"key":"27_CR46","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., et al.: Align before fuse: vision and language representation learning with momentum distillation. NIPS 34, 9694\u20139705 (2021)","journal-title":"NIPS"},{"issue":"3","key":"27_CR47","first-page":"18","volume":"2","author":"A Liaw","year":"2002","unstructured":"Liaw, A., Wiener, M., et al.: Classification and regression by randomforest. R News 2(3), 18\u201322 (2002)","journal-title":"R News"},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Littlejohns, T.J., Holliday, J., Gibson, L.M., Garratt, S., et\u00a0al.: The UK Biobank imaging enhancement of 100,000 participants: rationale, data collection, management and future directions. Nat. Commun. 11(1), 2624 (2020)","DOI":"10.1038\/s41467-020-15948-9"},{"issue":"6","key":"27_CR49","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1111\/j.1365-2796.2010.02274.x","volume":"268","author":"A Mackinnon","year":"2010","unstructured":"Mackinnon, A.: The use and reporting of multiple imputation in medical research-a review. J. Intern. Med. 268(6), 586\u2013593 (2010)","journal-title":"J. Intern. Med."},{"key":"27_CR50","unstructured":"Majmundar, K.A., Goyal, S., Netrapalli, P., Jain, P.: MET: masked encoding for tabular data. In: NIPSW (2022)"},{"key":"27_CR51","unstructured":"Mattei, P.A., Frellsen, J.: MIWAE: deep generative modelling and imputation of incomplete data sets. In: ICML, pp. 4413\u20134423. PMLR (2019)"},{"issue":"7","key":"27_CR52","first-page":"6630","volume":"35","author":"X Miao","year":"2022","unstructured":"Miao, X., Wu, Y., et al.: An experimental survey of missing data imputation algorithms. IEEE Trans. Knowl. Data Eng. 35(7), 6630\u20136650 (2022)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"2","key":"27_CR53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3605943","volume":"56","author":"B Min","year":"2023","unstructured":"Min, B., Ross, H., Sulem, E., Veyseh, A.P.B., Nguyen, T.H., et al.: Recent advances in natural language processing via large pre-trained language models: a survey. ACM Comput. Surv. 56(2), 1\u201340 (2023)","journal-title":"ACM Comput. Surv."},{"key":"27_CR54","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. NIPS 35, 27730\u201327744 (2022)","journal-title":"NIPS"},{"key":"27_CR55","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"27_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1007\/978-3-030-87240-3_66","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"S P\u00f6lsterl","year":"2021","unstructured":"P\u00f6lsterl, S., Wolf, T.N., Wachinger, C.: Combining 3D image and tabular data via the dynamic affine feature map transform. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 688\u2013698. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_66"},{"key":"27_CR57","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"issue":"1","key":"27_CR58","first-page":"85","volume":"27","author":"TE Raghunathan","year":"2001","unstructured":"Raghunathan, T.E., Lepkowski, J.M., Van Hoewyk, J., Solenberger, P., et al.: A multivariate technique for multiply imputing missing values using a sequence of regression models. Surv. Pract. 27(1), 85\u201396 (2001)","journal-title":"Surv. Pract."},{"key":"27_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v045.i04","volume":"45","author":"P Royston","year":"2011","unstructured":"Royston, P., White, I.R.: Multiple imputation by chained equations (MICE): implementation in stata. J. Stat. Softw. 45, 1\u201320 (2011)","journal-title":"J. Stat. Softw."},{"issue":"2","key":"27_CR60","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1037\/1082-989X.7.2.147","volume":"7","author":"JL Schafer","year":"2002","unstructured":"Schafer, J.L., Graham, J.W.: Missing data: our view of the state of the art. Psychol. Methods 7(2), 147 (2002)","journal-title":"Psychol. Methods"},{"key":"27_CR61","unstructured":"Somepalli, G., Goldblum, M., Schwarzschild, A., Bruss, C.B., Goldstein, T.: SAINT: improved neural networks for tabular data via row attention and contrastive pre-training. arXiv preprint arXiv:2106.01342 (2021)"},{"key":"27_CR62","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1016\/j.neuroimage.2019.01.031","volume":"189","author":"S Spasov","year":"2019","unstructured":"Spasov, S., Passamonti, L., Duggento, A., Lio, P., Toschi, N., et al.: A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to alzheimer\u2019s disease. Neuroimage 189, 276\u2013287 (2019)","journal-title":"Neuroimage"},{"issue":"1","key":"27_CR63","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","volume":"28","author":"DJ Stekhoven","year":"2012","unstructured":"Stekhoven, D.J., B\u00fchlmann, P.: MissForest\u2013non-parametric missing value imputation for mixed-type data. Bioinformatics 28(1), 112\u2013118 (2012)","journal-title":"Bioinformatics"},{"key":"27_CR64","doi-asserted-by":"publisher","unstructured":"Sun, K., Luo, X., Luo, M.Y.: A survey of pretrained language models. In: Memmi, G., Yang, B., Kong, L., Zhang, T., Qiu, M. (eds.) Knowledge Science, Engineering and Management, KSEM 2022, LNCS, vol. 13369, pp. 442\u2013456 Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-10986-7_36","DOI":"10.1007\/978-3-031-10986-7_36"},{"key":"27_CR65","first-page":"18853","volume":"34","author":"T Ucar","year":"2021","unstructured":"Ucar, T., Hajiramezanali, E., Edwards, L.: SubTab: Subsetting features of tabular data for self-supervised representation learning. NIPS 34, 18853\u201318865 (2021)","journal-title":"NIPS"},{"issue":"1","key":"27_CR66","doi-asserted-by":"publisher","first-page":"13505","DOI":"10.1038\/s41598-021-92799-4","volume":"11","author":"LA Vale-Silva","year":"2021","unstructured":"Vale-Silva, L.A., Rohr, K.: Long-term cancer survival prediction using multimodal deep learning. Sci. Rep. 11(1), 13505 (2021)","journal-title":"Sci. Rep."},{"key":"27_CR67","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, vol. 30 (2017)"},{"key":"27_CR68","first-page":"2902","volume":"35","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Sun, J.: TransTab: learning transferable tabular transformers across tables. NIPS 35, 2902\u20132915 (2022)","journal-title":"NIPS"},{"key":"27_CR69","doi-asserted-by":"publisher","first-page":"119505","DOI":"10.1016\/j.neuroimage.2022.119505","volume":"260","author":"TN Wolf","year":"2022","unstructured":"Wolf, T.N., P\u00f6lsterl, S., et al.: DAFT: a universal module to interweave tabular data and 3D images in CNNs. Neuroimage 260, 119505 (2022)","journal-title":"Neuroimage"},{"key":"27_CR70","doi-asserted-by":"crossref","unstructured":"Yang, J., Gupta, A., Upadhyay, S., He, L., Goel, R., Paul, S.: TableFormer: robust transformer modeling for table-text encoding. In: ACL, pp. 528\u2013537 (2022)","DOI":"10.18653\/v1\/2022.acl-long.40"},{"key":"27_CR71","unstructured":"Ye, C., Lu, G., Wang, H., et\u00a0al.: CT-BERT: learning better tabular representations through cross-table pre-training. arXiv preprint arXiv:2307.04308 (2023)"},{"key":"27_CR72","unstructured":"Yoon, J., Jordon, J., Schaar, M.: Gain: missing data imputation using generative adversarial nets. In: ICML, pp. 5689\u20135698. PMLR (2018)"},{"key":"27_CR73","first-page":"11033","volume":"33","author":"J Yoon","year":"2020","unstructured":"Yoon, J., Zhang, Y., et al.: VIME: extending the success of self-and semi-supervised learning to tabular domain. NIPS 33, 11033\u201311043 (2020)","journal-title":"NIPS"},{"key":"27_CR74","unstructured":"Yu, J., Wang, Z., Vasudevan, V., et\u00a0al.: Coca: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"27_CR75","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. In: ICML, pp. 12310\u201312320. PMLR (2021)"},{"key":"27_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, C., Zhang, C., Song, J., Yi, J.S.K., Kweon, I.S.: A survey on masked autoencoder for visual self-supervised learning. In: IJCAI, pp. 6805\u20136813 (2023)","DOI":"10.24963\/ijcai.2023\/762"},{"key":"27_CR77","doi-asserted-by":"publisher","unstructured":"Zheng, H., et al.: Multi-transSP: multimodal transformer for survival prediction of nasopharyngeal carcinoma patients. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention - MICCAI 2022, MICCAI 2022, LNCS, vol. 13437. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16449-1_23","DOI":"10.1007\/978-3-031-16449-1_23"}],"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\/978-3-031-72633-0_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T08:16:36Z","timestamp":1732176996000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72633-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031726323","9783031726330"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72633-0_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 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"}}]}}