{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:53:31Z","timestamp":1777654411212,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680882","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"10804-10813","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi-modal Denoising Diffusion Pre-training for Whole-Slide Image Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2071-4081","authenticated-orcid":false,"given":"Wei","family":"Lou","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen & Shenzhen Research Institute of Big Data, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2486-2890","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2324-6527","authenticated-orcid":false,"given":"Xiang","family":"Wan","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data & Guangdong Provincial Key Laboratory of Big Data Computing, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9120-9843","authenticated-orcid":false,"given":"Haofeng","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.7606"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"e_1_3_2_2_5_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_2_6_1","volume-title":"Deconstructing denoising diffusion models for self-supervised learning. arXiv preprint arXiv:2401.14404","author":"Chen Xinlei","year":"2024","unstructured":"Xinlei Chen, Zhuang Liu, Saining Xie, and Kaiming He. 2024. Deconstructing denoising diffusion models for self-supervised learning. arXiv preprint arXiv:2401.14404 (2024)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.lungcan.2022.01.005"},{"key":"e_1_3_2_2_8_1","volume-title":"Heounjeong Go, and Sang Hyun Park.","author":"Chikontwe Philip","year":"2020","unstructured":"Philip Chikontwe, Meejeong Kim, Soo Jeong Nam, Heounjeong Go, and Sang Hyun Park. 2020. Multiple instance learning with center embeddings for histopathology classification. In Medical Image Computing and Computer Assisted Intervention--MICCAI 2020: 23rd International Conference, Lima, Peru, October 4--8, 2020, Proceedings, Part V 23. Springer International Publishing, 519--528."},{"key":"e_1_3_2_2_9_1","volume-title":"Radu Tudor Ionescu, and Mubarak Shah","author":"Croitoru Florinel-Alin","year":"2023","unstructured":"Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, and Mubarak Shah. 2023. Diffusion models in vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.21769\/BioProtoc.3465"},{"key":"e_1_3_2_2_11_1","volume-title":"Kuang-Yu Jen, Alexander Nobori, Sofia Liou, Sarah Zhang, et al.","author":"de Haan Kevin","year":"2021","unstructured":"Kevin de Haan, Yijie Zhang, Jonathan E Zuckerman, Tairan Liu, Anthony E Sisk, Miguel FP Diaz, Kuang-Yu Jen, Alexander Nobori, Sofia Liou, Sarah Zhang, et al. 2021. Deep learning-based transformation of H&E stained tissues into special stains. Nature communications, Vol. 12, 1 (2021), 1--13."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01628"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.022"},{"key":"e_1_3_2_2_15_1","volume-title":"International Conference on Learning Representations.","author":"Gidaris Spyros","year":"2018","unstructured":"Spyros Gidaris, Praveer Singh, and Nikos Komodakis. 2018. Unsupervised Representation Learning by Predicting Image Rotations. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00391"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_20_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_20"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"e_1_3_2_2_23_1","volume-title":"International conference on machine learning. PMLR, 2127--2136","author":"Ilse Maximilian","year":"2018","unstructured":"Maximilian Ilse, Jakub Tomczak, and Max Welling. 2018. Attention-based deep multiple instance learning. In International conference on machine learning. PMLR, 2127--2136."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101757"},{"key":"e_1_3_2_2_26_1","volume-title":"Immunohistochemistry staining methods. Education Guide Immunohistochemical Staining Methods","author":"Key Marc","year":"2006","unstructured":"Marc Key. 2006. Immunohistochemistry staining methods. Education Guide Immunohistochemical Staining Methods Fourth Edition (2006), 47."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2559.1987.tb01874.x"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01409"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00194"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43987-2_61"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2865036"},{"key":"e_1_3_2_2_32_1","volume-title":"Self-Supervised Alignment Learning for Medical Image Segmentation. In IEEE International Symposium on Biomedical Imaging.","author":"Li Haofeng","year":"2024","unstructured":"Haofeng Li, Yiming Ouyang, and Xiang Wan. 2024. Self-Supervised Alignment Learning for Medical Image Segmentation. In IEEE International Symposium on Biomedical Imaging."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01899"},{"key":"e_1_3_2_2_34_1","volume-title":"Oscar Geessink, Maschenka Balkenhol, Peter Bult, Altuna Halilovic, Meyke Hermsen, Rob Van de Loo, Rob Vogels, et al.","author":"Litjens Geert","year":"2018","unstructured":"Geert Litjens, Peter Bandi, Babak Ehteshami Bejnordi, Oscar Geessink, Maschenka Balkenhol, Peter Bult, Altuna Halilovic, Meyke Hermsen, Rob Van de Loo, Rob Vogels, et al. 2018. 1399 H&E-stained sentinel lymph node sections of breast cancer patients: the CAMELYON dataset. GigaScience, Vol. 7, 6 (2018), giy065."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00198"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3221666"},{"key":"e_1_3_2_2_37_1","volume-title":"Tiffany Y Chen, Richard J Chen, Matteo Barbieri, and Faisal Mahmood.","author":"Lu Ming Y","year":"2021","unstructured":"Ming Y Lu, Drew FK Williamson, Tiffany Y Chen, Richard J Chen, Matteo Barbieri, and Faisal Mahmood. 2021. Data-efficient and weakly supervised computational pathology on whole-slide images. Nature biomedical engineering, Vol. 5, 6 (2021), 555--570."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_2_2_39_1","volume-title":"International Conference on Machine Learning. PMLR, 24963--24982","author":"Mittal Sarthak","year":"2023","unstructured":"Sarthak Mittal, Korbinian Abstreiter, Stefan Bauer, Bernhard Sch\u00f6lkopf, and Arash Mehrjou. 2023. Diffusion based representation learning. In International Conference on Machine Learning. PMLR, 24963--24982."},{"key":"e_1_3_2_2_40_1","volume-title":"DINOv2: Learning Robust Visual Features without Supervision. Transactions on Machine Learning Research","author":"Oquab Maxime","year":"2024","unstructured":"Maxime Oquab, Timoth\u00e9e Darcet, Th\u00e9o Moutakanni, Huy V. Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel HAZIZA, Francisco Massa, Alaaeldin El-Nouby, Mido Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Herve Jegou, Julien Mairal, Patrick Labatut, Armand Joulin, and Piotr Bojanowski. 2024. DINOv2: Learning Robust Visual Features without Supervision. Transactions on Machine Learning Research (2024). https:\/\/openreview.net\/forum?id=a68SUt6zFt"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_3_2_2_42_1","unstructured":"Nathan Heath Patterson. [n. d.]. Multi-modal whole slide image registration. https:\/\/github.com\/NHPatterson\/wsireg."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-18576-2_12"},{"key":"e_1_3_2_2_44_1","volume-title":"International Conference on Machine Learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1136\/jclinpath-2017-204979"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_48_1","first-page":"2136","article-title":"Transmil: Transformer based correlated multiple instance learning for whole slide image classification","volume":"34","author":"Shao Zhuchen","year":"2021","unstructured":"Zhuchen Shao, Hao Bian, Yang Chen, Yifeng Wang, Jian Zhang, Xiangyang Ji, et al. 2021. Transmil: Transformer based correlated multiple instance learning for whole slide image classification. Advances in Neural Information Processing Systems, Vol. 34 (2021), 2136--2147.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01965"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2017.06.001"},{"key":"e_1_3_2_2_51_1","unstructured":"TCGA. [n. d.]. The Cancer Genome Atlas Database. https:\/\/www.cancer.gov\/tcga.."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01492"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-19112-9"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01448"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/176"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01736"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43993-3_57"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475627"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16434-7_23"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01824"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00742"},{"key":"e_1_3_2_2_65_1","volume-title":"Image BERT Pre-training with Online Tokenizer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ydopy-e6Dg","author":"Zhou Jinghao","year":"2022","unstructured":"Jinghao Zhou, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille, and Tao Kong. 2022. Image BERT Pre-training with Online Tokenizer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ydopy-e6Dg"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_3_2_2_67_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Zhu Jun-Yan","year":"2017","unstructured":"Jun-Yan Zhu, Richard Zhang, Deepak Pathak, Trevor Darrell, Alexei A Efros, Oliver Wang, and Eli Shechtman. 2017. Toward multimodal image-to-image translation. Advances in Neural Information Processing Systems, Vol. 30 (2017)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680882","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:33Z","timestamp":1750295853000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680882"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":67,"alternative-id":["10.1145\/3664647.3680882","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680882","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}