{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:30:01Z","timestamp":1776889801462,"version":"3.51.2"},"reference-count":122,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62431004"],"award-info":[{"award-number":["62431004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276046"],"award-info":[{"award-number":["62276046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Dalian Science and Technology Innovation Foundation","award":["2023JJ12GX015"],"award-info":[{"award-number":["2023JJ12GX015"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tpami.2025.3578494","type":"journal-article","created":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T13:34:30Z","timestamp":1749476070000},"page":"8613-8629","source":"Crossref","is-referenced-by-count":4,"title":["ComPtr: Toward Diverse Bi-Source Dense Prediction Tasks via a Simple Yet General Complementary Transformer"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3950-0956","authenticated-orcid":false,"given":"Youwei","family":"Pang","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7734-5128","authenticated-orcid":false,"given":"Xiaoqi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9241-1688","authenticated-orcid":false,"given":"Lihe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3085870"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00479"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-020-0199-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0149-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3051099"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996406"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3171688"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3127149"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3234702"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202563"},{"key":"ref15","article-title":"DFormer: Rethinking RGBD representation learning for semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yin"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/rs15235459"},{"key":"ref19","first-page":"1","article-title":"RGB-T multi-modal crowd counting based on transformer","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Liu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451652"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.07.003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2988032"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3106697"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.06.003"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3095166"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3168331"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883686"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/igarss53475.2024.10640593"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3241257"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3203385"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS48785.2022.9937583"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859777"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_15"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3077058"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475601"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00468"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.556"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049332"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00700"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_33"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3161852"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00756"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref45","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00116"},{"key":"ref48","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.189"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref52","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01276"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01390"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01781"},{"key":"ref56","first-page":"1595","article-title":"Distribution matching for crowd counting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref58","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00464"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref62","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3056416"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2959609"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3131993"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/VRHCIAI57205.2022.00036"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26284-5_5"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3327253"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00120"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00624"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00372"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01901"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3262978"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.533"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref81","first-page":"4835","article-title":"Deep multimodal fusion by channel exchanging","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3066071"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref84","first-page":"1","article-title":"Deep feature selection-and-fusion for RGB-D semantic segmentation","volume-title":"Proc. IEEE Int. Conf. Multimedia Expo","author":"Su"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3174338"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892852"},{"key":"ref87","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191977"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00735"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2015.07.002"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_7"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247708"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3073689"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16191"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00935"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00146"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00430"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062689"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3077767"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140606"},{"key":"ref106","first-page":"7281","article-title":"HRFormer: High-resolution transformer for dense prediction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-1702-6_36"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924578"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2019.00032"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102268"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00941"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3087412"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3099120"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19390-8_48"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/97"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.39"},{"key":"ref120","article-title":"DPFormer: Learning differentially private transformer on long-tailed data","author":"Yin","year":"2024"},{"key":"ref121","article-title":"Parsenet: Looking wider to see better","author":"Liu","year":"2015"},{"key":"ref122","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11163533\/11029181.pdf?arnumber=11029181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T13:11:20Z","timestamp":1758028280000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11029181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":122,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3578494","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":[[2025,10]]}}}