{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:58Z","timestamp":1740132898893,"version":"3.37.3"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["K22RC00010"],"award-info":[{"award-number":["K22RC00010"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3311909","type":"journal-article","created":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T17:52:35Z","timestamp":1693936355000},"page":"3481-3490","source":"Crossref","is-referenced-by-count":0,"title":["DropQueries: A Simple Way to Discover Comprehensive Segment Representations"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0746-4376","authenticated-orcid":false,"given":"Haojie","family":"Ding","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network and Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5625-2966","authenticated-orcid":false,"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1978-2025","authenticated-orcid":false,"given":"Guoliang","family":"Kang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1838-9176","authenticated-orcid":false,"given":"Weijia","family":"Li","sequence":"additional","affiliation":[{"name":"School of Geospatial Engineering and Science, Sun Yat-sen University, Zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8697-695X","authenticated-orcid":false,"given":"Conghui","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network and Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2812-8781","authenticated-orcid":false,"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Advanced Information Science and Network and Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"article-title":"Rethinking atrous convolution for semantic image segmentation","year":"2017","author":"Chen","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref5","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","year":"2021"},{"key":"ref6","first-page":"10326","article-title":"K-Net: Towards unified image segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/508"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3262973"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01089"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01308"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3151145"},{"key":"ref22","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120873"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref26","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","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2971175"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_20"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3260631"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","year":"2022","author":"Zhang","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1604.01685"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.2983686"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref53","first-page":"31360","article-title":"GMMSeg: Gaussian mixture based generative semantic segmentation models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liang","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw60793.2023.00083"},{"key":"ref56","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Chen","year":"2023"},{"key":"ref57","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref58","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2021"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10239324.pdf?arnumber=10239324","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T23:44:18Z","timestamp":1709336658000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10239324\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3311909","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2024]]}}}