{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:25:22Z","timestamp":1783643122069,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China Project","award":["2022ZD0161100"],"award-info":[{"award-number":["2022ZD0161100"]}]},{"name":"General Research Fund of Hong Kong RGC","award":["14204021"],"award-info":[{"award-number":["14204021"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3396281","type":"journal-article","created":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T18:12:50Z","timestamp":1716919970000},"page":"9630-9643","source":"Crossref","is-referenced-by-count":17,"title":["Pyramid Fusion Transformer for Semantic Segmentation"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7907-3832","authenticated-orcid":false,"given":"Zipeng","family":"Qin","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4392-1056","authenticated-orcid":false,"given":"Jianbo","family":"Liu","sequence":"additional","affiliation":[{"name":"SenseTime Research, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7303-5712","authenticated-orcid":false,"given":"Xiaolin","family":"Zhang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2438-4072","authenticated-orcid":false,"given":"Maoqing","family":"Tian","sequence":"additional","affiliation":[{"name":"SenseTime Research, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4742-8624","authenticated-orcid":false,"given":"Aojun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1253-6633","authenticated-orcid":false,"given":"Shuai","family":"Yi","sequence":"additional","affiliation":[{"name":"SenseTime Research, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2664-7975","authenticated-orcid":false,"given":"Hongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"Multimedia Laboratory, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_1"},{"key":"ref4","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035231"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2798282"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074273"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120873"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref14","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00301"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref17","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3114541"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3198318"},{"key":"ref25","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146714"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3202765"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref32","article-title":"Hierarchical multi-scale attention for semantic segmentation","author":"Tao","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3086618"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01060"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3328478"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3157995"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01633"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_21"},{"key":"ref46","first-page":"272","article-title":"Co-attention dictionary network for weakly-supervised semantic segmentation","volume-title":"Neurocomputing","volume":"486","author":"Wan","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16300"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_29"},{"key":"ref49","first-page":"4353","article-title":"Large kernel mattersimprove semantic segmentation by global convolutional network","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Peng","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141231"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref55","article-title":"MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref59","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01555"},{"key":"ref62","article-title":"BEit: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00083"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10540365.pdf?arnumber=10540365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T07:19:22Z","timestamp":1726730362000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10540365\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3396281","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}