{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T12:06:31Z","timestamp":1782389191741,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":54,"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"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176030"],"award-info":[{"award-number":["62176030"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2023CDJYGRH-YB18"],"award-info":[{"award-number":["2023CDJYGRH-YB18"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681534","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"6083-6092","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["SAM-MIL: A Spatial Contextual Aware Multiple Instance Learning Approach for Whole Slide Image Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7518-2351","authenticated-orcid":false,"given":"Heng","family":"Fang","sequence":"first","affiliation":[{"name":"School of Big Data & Software Engineering, Chongqing University, Chongqing, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5610-0826","authenticated-orcid":false,"given":"Sheng","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Big Data & Software Engineering, Chongqing University, Chongqing, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8835-9215","authenticated-orcid":false,"given":"Wenhao","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Big Data & Software Engineering, Chongqing University, Chongqing, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3926-7901","authenticated-orcid":false,"given":"Luwen","family":"Huangfu","sequence":"additional","affiliation":[{"name":"Fowler College of Business, San Diego State University, San Diego, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8678-2271","authenticated-orcid":false,"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_36"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.14585"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0508-1"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01503"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"e_1_3_2_2_6_1","volume-title":"Guillaume Jaume, Andrew H Song, Bowen Chen, Andrew Zhang, Daniel Shao, Muhammad Shaban, et al.","author":"Chen Richard J","year":"2024","unstructured":"Richard J Chen, Tong Ding, Ming Y Lu, Drew FK Williamson, Guillaume Jaume, Andrew H Song, Bowen Chen, Andrew Zhang, Daniel Shao, Muhammad Shaban, et al. 2024. Towards a general-purpose foundation model for computational pathology. Nature Medicine (2024), 1--13."},{"key":"e_1_3_2_2_7_1","volume-title":"Drew FK Williamson, and Faisal Mahmood","author":"Chen Richard J","year":"2021","unstructured":"Richard J Chen, Ming Y Lu, Muhammad Shaban, Chengkuan Chen, Tiffany Y Chen, Drew FK Williamson, and Faisal Mahmood. 2021. Whole slide images are 2d point clouds: Context-aware survival prediction using patch-based graph convolutional networks. In Medical Image Computing and Computer Assisted Intervention--MICCAI 2021: 24th International Conference, Strasbourg, France, September 27--October 1, 2021, Proceedings, Part VIII 24. Springer, 339--349."},{"key":"e_1_3_2_2_8_1","volume-title":"Segment and track anything. arXiv preprint arXiv:2305.06558","author":"Cheng Yangming","year":"2023","unstructured":"Yangming Cheng, Liulei Li, Yuanyou Xu, Xiaodi Li, Zongxin Yang, Wenguan Wang, and Yi Yang. 2023. Segment and track anything. arXiv preprint arXiv:2305.06558 (2023)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102105"},{"key":"e_1_3_2_2_10_1","unstructured":"Ruining Deng Can Cui Quan Liu Tianyuan Yao Lucas W Remedios Shunxing Bao Bennett A Landman Lee E Wheless Lori A Coburn Keith T Wilson et al. 2023. Segment anything model (sam) for digital pathology: Assess zero-shot segmentation on whole slide imaging. arXiv preprint arXiv:2304.04155 (2023)."},{"key":"e_1_3_2_2_11_1","volume-title":"Solving the multiple instance problem with axis-parallel rectangles. Artificial intelligence","author":"Dietterich Thomas G","year":"1997","unstructured":"Thomas G Dietterich, Richard H Lathrop, and Tom\u00e1s Lozano-P\u00e9rez. 1997. Solving the multiple instance problem with axis-parallel rectangles. Artificial intelligence, Vol. 89, 1--2 (1997), 31--71."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10890"},{"key":"e_1_3_2_2_13_1","volume-title":"Scalable mask annotation for video text spotting. arXiv preprint arXiv:2305.01443","author":"He Haibin","year":"2023","unstructured":"Haibin He, Jing Zhang, Mengyang Xu, Juhua Liu, Bo Du, and Dacheng Tao. 2023. Scalable mask annotation for video text spotting. arXiv preprint arXiv:2305.01443 (2023)."},{"key":"e_1_3_2_2_14_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Le Hou Dimitris Samaras Tahsin M Kurc Yi Gao James E Davis and Joel H Saltz. 2016. Patch-based convolutional neural network for whole slide tissue image classification. In CVPR. 2424--2433.","DOI":"10.1109\/CVPR.2016.266"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19976"},{"key":"e_1_3_2_2_17_1","volume-title":"When sam meets medical images: An investigation of segment anything model (sam) on multi-phase liver tumor segmentation. arXiv preprint arXiv:2304.08506","author":"Hu Chuanfei","year":"2023","unstructured":"Chuanfei Hu and Xinde Li. 2023. When sam meets medical images: An investigation of segment anything model (sam) on multi-phase liver tumor segmentation. arXiv preprint arXiv:2304.08506 (2023)."},{"key":"e_1_3_2_2_18_1","volume-title":"A visual--language foundation model for pathology image analysis using medical twitter. Nature Medicine","author":"Huang Zhi","year":"2023","unstructured":"Zhi Huang, Federico Bianchi, Mert Yuksekgonul, Thomas J Montine, and James Zou. 2023. A visual--language foundation model for pathology image analysis using medical twitter. Nature Medicine (2023), 1--10."},{"key":"e_1_3_2_2_19_1","unstructured":"Maximilian Ilse Jakub Tomczak and Max Welling. 2018. Attention-based deep multiple instance learning. In ICML. PMLR 2127--2136."},{"key":"e_1_3_2_2_20_1","first-page":"36722","article-title":"Amos: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation","volume":"35","author":"Ji Yuanfeng","year":"2022","unstructured":"Yuanfeng Ji, Haotian Bai, Chongjian Ge, Jie Yang, Ye Zhu, Ruimao Zhang, Zhen Li, Lingyan Zhanng, Wanling Ma, Xiang Wan, et al. 2022. Amos: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36722--36732.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_2_22_1","volume-title":"Sohee Oh, Kyoungseob Shin, Jiyu Sun, Minsun Jung, Cheol Lee, Hyojin Kim, Jin-Haeng Chung, Kyung Chul Moon, et al.","author":"Lee Yongju","year":"2022","unstructured":"Yongju Lee, Jeong Hwan Park, Sohee Oh, Kyoungseob Shin, Jiyu Sun, Minsun Jung, Cheol Lee, Hyojin Kim, Jin-Haeng Chung, Kyung Chul Moon, et al. 2022. Derivation of prognostic contextual histopathological features from whole-slide images of tumours via graph deep learning. Nature Biomedical Engineering (2022), 1--15."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Bin Li Yin Li and Kevin W Eliceiri. 2021. Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning. In CVPR. 14318--14328.","DOI":"10.1109\/CVPR46437.2021.01409"},{"key":"e_1_3_2_2_24_1","volume-title":"DT-MIL: Deformable Transformer for Multi-instance Learning on Histopathological Image. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 206--216","author":"Li Hang","year":"2021","unstructured":"Hang Li, Fan Yang, Yu Zhao, Xiaohan Xing, Jun Zhang, Mingxuan Gao, Junzhou Huang, Liansheng Wang, and Jianhua Yao. 2021. DT-MIL: Deformable Transformer for Multi-instance Learning on Histopathological Image. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 206--216."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01076"},{"key":"e_1_3_2_2_26_1","volume-title":"Foundations and Recent Trends in Multimodal Machine Learning: Principles. Challenges, and Open Questions. arXiv","author":"Liang PP","year":"2022","unstructured":"PP Liang, A Zadeh, and LP Morency. 2022. Foundations and Recent Trends in Multimodal Machine Learning: Principles. Challenges, and Open Questions. arXiv, Vol. 2209 (2022)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01899"},{"key":"e_1_3_2_2_28_1","volume-title":"Richard J Chen, Ivy Liang, Tong Ding, Guillaume Jaume, Igor Odintsov, Long Phi Le, Georg Gerber, et al.","author":"Lu Ming Y","year":"2024","unstructured":"Ming Y Lu, Bowen Chen, Drew FK Williamson, Richard J Chen, Ivy Liang, Tong Ding, Guillaume Jaume, Igor Odintsov, Long Phi Le, Georg Gerber, et al. 2024. A visual-language foundation model for computational pathology. Nature Medicine (2024), 1--12."},{"key":"e_1_3_2_2_29_1","volume-title":"Melissa Zhao, Maha Shady, Jana Lipkova, and Faisal Mahmood.","author":"Lu Ming Y","year":"2021","unstructured":"Ming Y Lu, Tiffany Y Chen, Drew FK Williamson, Melissa Zhao, Maha Shady, Jana Lipkova, and Faisal Mahmood. 2021. AI-based pathology predicts origins for cancers of unknown primary. Nature, Vol. 594, 7861 (2021), 106--110."},{"key":"e_1_3_2_2_30_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_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-020-00682-w"},{"key":"e_1_3_2_2_32_1","volume-title":"Can sam boost video super-resolution? arXiv preprint arXiv:2305.06524","author":"Lu Zhihe","year":"2023","unstructured":"Zhihe Lu, Zeyu Xiao, Jiawang Bai, Zhiwei Xiong, and Xinchao Wang. 2023. Can sam boost video super-resolution? arXiv preprint arXiv:2305.06524 (2023)."},{"key":"e_1_3_2_2_33_1","volume-title":"A framework for multiple-instance learning. Advances in neural information processing systems","author":"Maron Oded","year":"1997","unstructured":"Oded Maron and Tom\u00e1s Lozano-P\u00e9rez. 1997. A framework for multiple-instance learning. Advances in neural information processing systems, Vol. 10 (1997)."},{"key":"e_1_3_2_2_34_1","volume-title":"Sam vs bet: A comparative study for brain extraction and segmentation of magnetic resonance images using deep learning. arXiv preprint arXiv:2304.04739","author":"Mohapatra Sovesh","year":"2023","unstructured":"Sovesh Mohapatra, Advait Gosai, and Gottfried Schlaug. 2023. Sam vs bet: A comparative study for brain extraction and segmentation of magnetic resonance images using deep learning. arXiv preprint arXiv:2304.04739, Vol. 2 (2023), 4."},{"key":"e_1_3_2_2_35_1","volume-title":"Bram Van Ginneken, and Geert Litjens","author":"Pinckaers Hans","year":"2020","unstructured":"Hans Pinckaers, Bram Van Ginneken, and Geert Litjens. 2020. Streaming convolutional neural networks for end-to-end learning with multi-megapixel images. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 3 (2020), 1581--1590."},{"key":"e_1_3_2_2_36_1","volume-title":"md: Zero-shot medical image segmentation capabilities of the segment anything model. arXiv preprint arXiv:2304.05396","author":"Roy Saikat","year":"2023","unstructured":"Saikat Roy, Tassilo Wald, Gregor Koehler, Maximilian R Rokuss, Nico Disch, Julius Holzschuh, David Zimmerer, and Klaus H Maier-Hein. 2023. Sam. md: Zero-shot medical image segmentation capabilities of the segment anything model. arXiv preprint arXiv:2304.05396 (2023)."},{"key":"e_1_3_2_2_37_1","volume-title":"Self supervised learning improves dMMR\/MSI detection from histology slides across multiple cancers. arXiv preprint arXiv:2109.05819","author":"Saillard Charlie","year":"2021","unstructured":"Charlie Saillard, Olivier Dehaene, Tanguy Marchand, Olivier Moindrot, Aur\u00e9lie Kamoun, Benoit Schmauch, and Simon Jegou. 2021. Self supervised learning improves dMMR\/MSI detection from histology slides across multiple cancers. arXiv preprint arXiv:2109.05819 (2021)."},{"key":"e_1_3_2_2_38_1","volume-title":"NeurIPS","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. NeurIPS, Vol. 34 (2021)."},{"key":"e_1_3_2_2_39_1","volume-title":"Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification. arXiv preprint arXiv:2103.10626","author":"Sharma Yash","year":"2021","unstructured":"Yash Sharma, Aman Shrivastava, Lubaina Ehsan, Christopher A Moskaluk, Sana Syed, and Donald E Brown. 2021. Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification. arXiv preprint arXiv:2103.10626 (2021)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101813"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00377"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47401-9_23"},{"key":"e_1_3_2_2_43_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Di","year":"2024","unstructured":"Di Wang, Jing Zhang, Bo Du, Minqiang Xu, Lin Liu, Dacheng Tao, and Liangpei Zhang. 2024. Samrs: Scaling-up remote sensing segmentation dataset with segment anything model. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"e_1_3_2_2_45_1","volume-title":"Weakly supervised deep learning for whole slide lung cancer image analysis","author":"Wang Xi","year":"2019","unstructured":"Xi Wang, Hao Chen, Caixia Gan, Huangjing Lin, Qi Dou, Efstratios Tsougenis, Qitao Huang, Muyan Cai, and Pheng-Ann Heng. 2019. Weakly supervised deep learning for whole slide lung cancer image analysis. IEEE transactions on cybernetics, Vol. 50, 9 (2019), 3950--3962."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.08.026"},{"key":"e_1_3_2_2_47_1","volume-title":"Combining Attention-based Multiple Instance Learning and Gaussian Processes for CT Hemorrhage Detection","author":"Wu Yunan","unstructured":"Yunan Wu, Arne Schmidt, Enrique Hern\u00e1ndez-S\u00e1nchez, Rafael Molina, and Aggelos K Katsaggelos. 2021. Combining Attention-based Multiple Instance Learning and Gaussian Processes for CT Hemorrhage Detection. In MICCAI. Springer, 582--591."},{"key":"e_1_3_2_2_48_1","volume-title":"Camel: A weakly supervised learning framework for histopathology image segmentation. In CVPR. 10682--10691.","author":"Xu Gang","year":"2019","unstructured":"Gang Xu, Zhigang Song, Zhuo Sun, Calvin Ku, Zhe Yang, Cancheng Liu, Shuhao Wang, Jianpeng Ma, and Wei Xu. 2019. Camel: A weakly supervised learning framework for histopathology image segmentation. In CVPR. 10682--10691."},{"key":"e_1_3_2_2_49_1","volume-title":"Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968","author":"Yang Jinyu","year":"2023","unstructured":"Jinyu Yang, Mingqi Gao, Zhe Li, Shang Gao, Fangjing Wang, and Feng Zheng. 2023. Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968 (2023)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01824"},{"key":"e_1_3_2_2_51_1","volume-title":"Segment anything model for brain tumor segmentation. arXiv preprint arXiv:2309.08434","author":"Zhang Peng","year":"2023","unstructured":"Peng Zhang and Yaping Wang. 2023. Segment anything model for brain tumor segmentation. arXiv preprint arXiv:2309.08434 (2023)."},{"key":"e_1_3_2_2_52_1","volume-title":"Segment anything model for medical image segmentation: Current applications and future directions. Computers in Biology and Medicine","author":"Zhang Yichi","year":"2024","unstructured":"Yichi Zhang, Zhenrong Shen, and Rushi Jiao. 2024. Segment anything model for medical image segmentation: Current applications and future directions. Computers in Biology and Medicine (2024), 108238."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16434-7_7"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"crossref","unstructured":"Yu Zhao Fan Yang Yuqi Fang Hailing Liu et al. 2020. Predicting lymph node metastasis using histopathological images based on multiple instance learning with deep graph convolution. In CVPR. 4837--4846.","DOI":"10.1109\/CVPR42600.2020.00489"}],"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\/3664647.3681534","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:48Z","timestamp":1750294668000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681534"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":54,"alternative-id":["10.1145\/3664647.3681534","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681534","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"}}]}}