{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T05:27:38Z","timestamp":1750138058846,"version":"3.37.3"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0101501"],"award-info":[{"award-number":["2018AAA0101501"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2022.3226624","type":"journal-article","created":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T18:37:13Z","timestamp":1670524633000},"page":"190-202","source":"Crossref","is-referenced-by-count":3,"title":["One-Stage Visual Relationship Referring With Transformers and Adaptive Message Passing"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9876-8285","authenticated-orcid":false,"given":"Hang","family":"Wang","sequence":"first","affiliation":[{"name":"Ministry of Education Key Laboratory for Intelligent Networks and Network Security, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1714-3433","authenticated-orcid":false,"given":"Youtian","family":"Du","sequence":"additional","affiliation":[{"name":"Ministry of Education Key Laboratory for Intelligent Networks and Network Security, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"}]},{"given":"Yabin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0760-5267","authenticated-orcid":false,"given":"Shuai","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2078-4215","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref38","first-page":"1","article-title":"Translating embeddings for modeling multi-relational data","volume":"26","author":"bordes","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref29","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"chen","year":"2018","journal-title":"arXiv 1812 03426"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3062543"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00244"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00482"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref21","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref50","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref11","article-title":"Scene graph reasoning for visual question answering","author":"hildebrandt","year":"2020","journal-title":"arXiv 2007 01072"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.469"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097180"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3128322"},{"key":"ref14","first-page":"347","article-title":"Variational context: Exploiting visual and textual context for grounding referring expressions","volume":"43","author":"niu","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2979010"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00718"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3079278"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093297"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3043084"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2908774"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038354"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923287"},{"key":"ref49","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963957"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.23.5.1380"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587799"},{"key":"ref42","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref41","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref43","first-page":"1","article-title":"An image is worth 16&#x00D7;16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"Proc Int Conf Learn Represent"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/09976944.pdf?arnumber=9976944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T19:30:14Z","timestamp":1674502214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9976944\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3226624","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2023]]}}}