{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T04:30:42Z","timestamp":1783398642623,"version":"3.54.6"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"New Generation of AI","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61922046"],"award-info":[{"award-number":["61922046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alibaba Innovative Research"},{"name":"Alibaba Research Intern Program"},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AME Programmatic Funds","award":["A1892b0026"],"award-info":[{"award-number":["A1892b0026"]}]},{"name":"AME Programmatic Funds","award":["A19E3b0099"],"award-info":[{"award-number":["A19E3b0099"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,11,1]]},"DOI":"10.1109\/tpami.2022.3202765","type":"journal-article","created":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T19:52:51Z","timestamp":1661889171000},"page":"12760-12771","source":"Crossref","is-referenced-by-count":236,"title":["P2T: Pyramid Pooling Transformer for Scene Understanding"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8666-3435","authenticated-orcid":false,"given":"Yu-Huan","family":"Wu","sequence":"first","affiliation":[{"name":"TMCC, College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6143-0264","authenticated-orcid":false,"given":"Yun","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhan","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy, Hangzhou, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-8758","authenticated-orcid":false,"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"TMCC, College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781420010749"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2918284"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref7","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3134684"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref15","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Vaswani"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref17","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00147"},{"key":"ref19","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref24","article-title":"Transformer in convolutional neural networks","author":"Liu","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref28","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Chu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3302"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref33","article-title":"Demystifying local vision transformer: Sparse connectivity, weight sharing, and dynamic weight","author":"Han","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.239"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref38","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09825-6"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.038"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00374"},{"key":"ref47","article-title":"ISTR: End-to-end instance segmentation with transformers","author":"Hu","year":"2021"},{"key":"ref48","first-page":"10347","article-title":"Training data-efficient image transformers  distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref50","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021"},{"key":"ref51","article-title":"Token labeling: Training a 85.5% top-1 accuracy vision transformer with 56M parameters on ImageNet","author":"Jiang","year":"2021"},{"key":"ref52","article-title":"LocalViT: Bringing locality to vision transformers","author":"Li","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_3"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107622"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301274"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_15"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.02.067"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.31"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00567"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3140168"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3065822"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00133"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2920407"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00337"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.433"},{"key":"ref69","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref70","article-title":"Attention is not all you need: Pure attention loses rank doubly exponentially with depth","author":"Dong","year":"2021"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref72","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"ref76","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref77","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref78","article-title":"MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref79","article-title":"MMDetection: Open MMLab detection toolbox and benchmark","author":"Chen","year":"2019"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10269680\/09870559.pdf?arnumber=9870559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:00:04Z","timestamp":1705024804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9870559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":79,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3202765","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,1]]}}}