{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:40:52Z","timestamp":1778258452882,"version":"3.51.4"},"reference-count":69,"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":[{"name":"National Key R&D Program of China","award":["2023YFB4502804"],"award-info":[{"award-number":["2023YFB4502804"]}]},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2051"],"award-info":[{"award-number":["U22B2051"]}],"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":["62302411"],"award-info":[{"award-number":["62302411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2021J06003"],"award-info":[{"award-number":["2021J06003"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M732948"],"award-info":[{"award-number":["2023M732948"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"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.2025.3583795","type":"journal-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T13:45:46Z","timestamp":1751031946000},"page":"8990-9004","source":"Crossref","is-referenced-by-count":4,"title":["NICE: Improving Panoptic Narrative Detection and Segmentation With Cascading Collaborative Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0289-9672","authenticated-orcid":false,"given":"Haowei","family":"Wang","sequence":"first","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-6308","authenticated-orcid":false,"given":"Jiayi","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Guo","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2595-7883","authenticated-orcid":false,"given":"Yilong","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-9306","authenticated-orcid":false,"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01276"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_16"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413846"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17602"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00140"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548086"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413902"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref11","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref13","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Karpathy","year":"2014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25350"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref20","first-page":"10326","article-title":"K-Net: Towards unified image segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.303"},{"key":"ref22","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01871-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079993"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01647-z"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.520"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.333"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref37","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1174"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3090426"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00438"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3286760"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/99"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27969"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3686836"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref56","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref57","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"ref68","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kendall","year":"2018"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00667"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11163533\/11053686.pdf?arnumber=11053686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T13:11:38Z","timestamp":1758028298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11053686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":69,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3583795","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]]}}}