{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:22:43Z","timestamp":1778613763888,"version":"3.51.4"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000964","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000964","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Prime Minister's Office, Singapore"},{"name":"CREATE program, Singapore-MIT Alliance for Research"},{"name":"Future Urban Mobility"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/lra.2021.3086419","type":"journal-article","created":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T21:39:06Z","timestamp":1636407546000},"page":"5889-5896","source":"Crossref","is-referenced-by-count":8,"title":["Multi-Scale Feature Aggregation by Cross-Scale Pixel-to-Region Relation Operation for Semantic Segmentation"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5114-4192","authenticated-orcid":false,"given":"Yechao","family":"Bai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4544-0427","authenticated-orcid":false,"given":"Ziyuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7435-5072","authenticated-orcid":false,"given":"Lyuyu","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9836-3090","authenticated-orcid":false,"given":"Hongliang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8277-6408","authenticated-orcid":false,"given":"Marcelo H. Ang","family":"Jr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5473-3566","authenticated-orcid":false,"given":"Daniela","family":"Rus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","author":"zheng","year":"0"},{"key":"ref32","first-page":"267","article-title":"PSANet: Point-wise spatial attention network for scene parsing","author":"zhao","year":"0","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref31","author":"girshick","year":"0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00591"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref11","article-title":"Relational inductive biases, deep learning, and graph networks","author":"battaglia","year":"0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref18","first-page":"68","article-title":"Stand-alone self-attention in vision models","author":"parmar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref28","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"goyal","year":"0"},{"key":"ref4","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"0","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref6","article-title":"Object-contextual representations for semantic segmentation","volume":"12351","author":"yuan","year":"0","journal-title":"Comput Vision ECCV 2020 Lecture Notes in Comput Sci"},{"key":"ref29","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00690"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00909"},{"key":"ref7","article-title":"Hierarchical multi-scale attention for semantic segmentation","author":"tao","year":"0"},{"key":"ref2","article-title":"ParseNet: Looking wider to see better","author":"liu","year":"0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref1","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"0"},{"key":"ref20","article-title":"Feature pyramid transformer","volume":"12373","author":"zhang","year":"0","journal-title":"Comput Vision ECCV 2020 Lecture Notes in Comput Sci"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref21","first-page":"352","article-title":"${A}^2$-Nets: Double attention networks","author":"chen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref26","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9399748\/09447231.pdf?arnumber=9447231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:02Z","timestamp":1652194442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9447231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":33,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3086419","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}