{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:48:49Z","timestamp":1772552929685,"version":"3.50.1"},"reference-count":104,"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\/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":["U21B2037"],"award-info":[{"award-number":["U21B2037"]}],"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":["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":["U23A20383"],"award-info":[{"award-number":["U23A20383"]}],"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":["62072387"],"award-info":[{"award-number":["62072387"]}],"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":["62176222"],"award-info":[{"award-number":["62176222"]}],"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":["62176223"],"award-info":[{"award-number":["62176223"]}],"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":["62176226"],"award-info":[{"award-number":["62176226"]}],"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":["62072386"],"award-info":[{"award-number":["62072386"]}],"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":["62072389"],"award-info":[{"award-number":["62072389"]}],"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":["62002305"],"award-info":[{"award-number":["62002305"]}],"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":["62272401"],"award-info":[{"award-number":["62272401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2022J06001"],"award-info":[{"award-number":["2022J06001"]}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2021J06003"],"award-info":[{"award-number":["2021J06003"]}]}],"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.2025.3576857","type":"journal-article","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T13:41:51Z","timestamp":1749217311000},"page":"8550-8562","source":"Crossref","is-referenced-by-count":3,"title":["Universal Image Segmentation With Efficiency"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3187-1656","authenticated-orcid":false,"given":"Jie","family":"Hu","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\/0000-0002-7645-9606","authenticated-orcid":false,"given":"Liujuan","family":"Cao","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":"Xiaofeng","family":"Jin","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\/0000-0002-0800-0609","authenticated-orcid":false,"given":"Shengchuan","family":"Zhang","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","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref3","first-page":"10326","article-title":"K-Net: Towards unified image segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref4","article-title":"Hierarchical open-vocabulary universal image segmentation","author":"Wang","year":"2023","journal-title":"arXiv:2307.00764"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref6","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2023","journal-title":"arXiv:2304.06718"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969919"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01647"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00855"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01709"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref22","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv: 1810.04805"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00028"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00902"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304836"},{"key":"ref27","article-title":"PanoNet: Real-time panoptic segmentation through position-sensitive feature embedding","author":"Chen","year":"2020","journal-title":"arXiv: 2008.00192"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/s22030783"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC51774.2021.00170"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01445-z"},{"key":"ref31","article-title":"Deeperlab: Single-shot image parser","author":"Yang","year":"2019","journal-title":"arXiv: 1902.05093"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3145407"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3014297"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00856"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00722"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref41","first-page":"17721","article-title":"Solov2: Dynamic and fast instance segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00439"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref44","article-title":"ENet: A deep neural network architecture for real-time semantic segmentation","author":"Paszke","year":"2016","journal-title":"arXiv:1606.02147"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_34"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00941"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01515-2"},{"key":"ref50","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref54","article-title":"DFormer: Diffusion-guided transformer for universal image segmentation","author":"Wang","year":"2023","journal-title":"arXiv:2306.03437"},{"key":"ref55","article-title":"Reformer: The efficient transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kitaev"},{"key":"ref56","article-title":"Rethinking attention with performers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choromanski"},{"key":"ref57","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv: 2006.04768"},{"key":"ref58","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref59","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zaheer"},{"key":"ref60","article-title":"Pay less attention with lightweight and dynamic convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref61","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv: 1704.04861"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00910"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00847"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00745"},{"key":"ref70","article-title":"ISTR: End-to-end instance segmentation with transformers","author":"Hu","year":"2021","journal-title":"arXiv:2105.00637"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00860"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01024"},{"key":"ref74","article-title":"POLY-YOLO: Higher speed, more precise detection and instance segmentation for YOLOV3","author":"Hurtik","year":"2020","journal-title":"arXiv: 2005.13243"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500621"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00333"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CRV60082.2023.00027"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00096"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02603-z"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00915"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref84","article-title":"Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes","author":"Hong","year":"2021","journal-title":"arXiv:2101.06085"},{"key":"ref85","first-page":"7423","article-title":"RTFormer: Efficient design for real-time semantic segmentation with transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref86","first-page":"1","article-title":"Speeding up semantic segmentation for autonomous driving","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Treml","year":"2016"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2987816"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506485"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3154443"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01587-1"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2750080"},{"key":"ref93","article-title":"Feature pyramid encoding network for real-time semantic segmentation","author":"Liu","year":"2019","journal-title":"arXiv: 1909.08599"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803154"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3157995"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2962094"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3098355"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3248089"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3129418"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref102","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hwang"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11163533\/11027444.pdf?arnumber=11027444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T13:11:43Z","timestamp":1758028303000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11027444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":104,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3576857","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]]}}}