{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:15:49Z","timestamp":1777889749108,"version":"3.51.4"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02111","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22738-22747","source":"Crossref","is-referenced-by-count":0,"title":["Bridging Local Inductive Bias and Long-Range Dependencies With Pixel-Mamba for End-To-End Whole Slide Image Analysis"],"prefix":"10.1109","author":[{"given":"Zhongwei","family":"Qiu","sequence":"first","affiliation":[{"name":"Zhejiang University"}]},{"given":"Hanqing","family":"Chao","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}]},{"given":"Tiancheng","family":"Lin","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}]},{"given":"Wanxing","family":"Chang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}]},{"given":"Zijiang","family":"Yang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}]},{"given":"Wenpei","family":"Jiao","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}]},{"given":"Yixuan","family":"Shen","sequence":"additional","affiliation":[{"name":"Shanghai Institution of Pancreatic Disease"}]},{"given":"Yunshuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Institution of Pancreatic Disease,Department of Pathology"}]},{"given":"Yelin","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Institution of Pancreatic Disease,Department of Pathology"}]},{"given":"Wenbin","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Institution of Pancreatic Disease"}]},{"given":"Hui","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Institution of Pancreatic Disease,Department of Pathology"}]},{"given":"Yun","family":"Bian","sequence":"additional","affiliation":[{"name":"Shanghai Institution of Pancreatic Disease"}]},{"given":"Ke","family":"Yan","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}]},{"given":"Dakai","family":"Jin","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}]},{"given":"Le","family":"Lu","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Alexey","year":"2021","journal-title":"ICLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0256907"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02857-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-18-2013"},{"key":"ref7","article-title":"Transformers are ssms: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","article-title":"Longnet: Scaling transformers to 1,000,000,000 tokens","author":"Ding","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_57"},{"key":"ref11","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00391"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19976"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02504-3"},{"key":"ref17","first-page":"2127","article-title":"Attention-based deep multiple instance learning","author":"Ilse","year":"2018","journal-title":"In ICML"},{"key":"ref18","article-title":"Hest-1k: A dataset for spatial transcriptomics and histology image analysis","author":"Jaume","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01409"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01076"},{"key":"ref21","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-020-00682-w"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02856-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00683"},{"key":"ref26","first-page":"2846","article-title":"S4nd: Modeling images and videos as multidimensional signals with state spaces","volume":"35","author":"Nguyen","year":"2022","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_15"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02036"},{"key":"ref29","article-title":"End-to-end multi-source visual prompt tuning for survival analysis in whole slide images","author":"Qiu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2018.03.086"},{"key":"ref31","first-page":"2136","article-title":"Transmil: Transformer based correlated multiple instance learning for whole slide image classification","volume":"34","author":"Shao","year":"2021","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01099"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01288"},{"key":"ref34","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021","journal-title":"In ICML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-023-00421-7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3404549"},{"key":"ref37","article-title":"When an image is worth $1,024 \\times 1,024$ words: A case study in computational pathology","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87237-3_18"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07894-z"},{"key":"ref40","article-title":"Exploring low-rank property in multiple instance learning for whole slide image classification","author":"Xiang","year":"2023","journal-title":"In ICLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07441-w"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07441-w"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72083-3_28"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2979450"},{"key":"ref46","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446302.pdf?arnumber=11446302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:16:34Z","timestamp":1777612594000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02111","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}