{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T02:36:30Z","timestamp":1784428590692,"version":"3.55.0"},"reference-count":374,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012338","name":"Alan Turing Institute","doi-asserted-by":"publisher","award":["SDCfP2\\100009"],"award-info":[{"award-number":["SDCfP2\\100009"]}],"id":[{"id":"10.13039\/100012338","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Industry Alignment Fund Industry Collaboration Projects"},{"name":"Funding Initiative and Singapore MOE AcRF Tier 1","award":["RG16\/21"],"award-info":[{"award-number":["RG16\/21"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3434373","type":"journal-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T19:32:40Z","timestamp":1722281560000},"page":"10138-10163","source":"Crossref","is-referenced-by-count":184,"title":["Transformer-Based Visual Segmentation: A Survey"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0550-8247","authenticated-orcid":false,"given":"Xiangtai","family":"Li","sequence":"first","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4868-6526","authenticated-orcid":false,"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[{"name":"Institute of Big Data, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9770-7720","authenticated-orcid":false,"given":"Haobo","family":"Yuan","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2748-4514","authenticated-orcid":false,"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6711-9319","authenticated-orcid":false,"given":"Jiangmiao","family":"Pang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8686-9513","authenticated-orcid":false,"given":"Guangliang","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6820-2325","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5345-1591","authenticated-orcid":false,"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011174803800"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref3","first-page":"313","article-title":"Multiclass spectral clustering","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Stella"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.54"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00133570"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00254"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref16","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref25","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3243465"},{"key":"ref35","article-title":"3D vision with transformers: A survey","author":"Lahoud","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3275156"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.118"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225573"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02036"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00412"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00988"},{"key":"ref53","article-title":"STEP: Segmenting and tracking every pixel","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Weber"},{"key":"ref54","article-title":"The 2017 Davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref55","article-title":"YouTube-VOS: A large-scale video object segmentation benchmark","author":"Xu","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00199"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2962685"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.189"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00909"},{"key":"ref62","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878975"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6805"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3099366"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref67","first-page":"254","article-title":"Dual graph convolutional network for semantic segmentation","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Zhang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_45"},{"key":"ref69","article-title":"SFNet: Faster, accurate, and domain agnostic semantic segmentation via semantic flow","author":"Li","year":"2022"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00692"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_26"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01556"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_17"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00904"},{"key":"ref79","article-title":"Semantic instance segmentation with a discriminative loss function","author":"De Brabandere","year":"2017"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01024"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00215"},{"key":"ref86","article-title":"SOLOv2: Dynamic and fast instance segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00902"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00028"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.477"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_69"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00976"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16225"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3211612"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00399"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00813"},{"key":"ref100","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi"},{"key":"ref101","first-page":"5099","article-title":"PointNet: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref102","first-page":"6737","article-title":"Learning object bounding boxes for 3D instance segmentation on point clouds","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00407"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00272"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00166"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01236"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01299"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20197"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01289"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00548"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"ref114","first-page":"350","article-title":"A2-Nets: Double attention networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref115","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3032166"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00720"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01780"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref123","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01797"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_34"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00240"},{"key":"ref130","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"ref134","first-page":"20014","article-title":"XCiT: Cross-covariance image transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ali"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref140","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref142","first-page":"28522","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive Bias","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref144","first-page":"1","article-title":"On the connection between local attention and dynamic depth-wise convolution","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Han"},{"key":"ref145","first-page":"1140","article-title":"SegNeXt: Rethinking convolutional attention design for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref147","article-title":"Demystify transformers & convolutions in modern image deep networks","author":"Dai","year":"2022"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref151","first-page":"14668","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref153","article-title":"Test-time training with masked autoencoders","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gandelsman"},{"key":"ref154","article-title":"Exploring long-sequence masked autoencoders","author":"Hu","year":"2022"},{"key":"ref155","first-page":"35632","article-title":"ConvMAE: Masked convolution meets masked autoencoders","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gao"},{"key":"ref156","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02240"},{"key":"ref158","first-page":"14449","article-title":"SparseR-CNN: End-to-end object detection with learnable proposals","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Sun"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"ref160","article-title":"ISTR: End-to-end instance segmentation via transformers","author":"Hu","year":"2021"},{"key":"ref161","first-page":"21898","article-title":"SOLQ: Segmenting objects by learning queries","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref162","article-title":"BoundarySqueeze: Image segmentation as boundary squeezing","author":"He","year":"2021"},{"key":"ref163","first-page":"10326","article-title":"K-Net: Towards unified image segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref164","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00290"},{"key":"ref169","article-title":"Mask2Former for video instance segmentation","author":"Cheng","year":"2021"},{"key":"ref170","first-page":"13352","article-title":"Video instance segmentation using inter-frame communication transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hwang"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01354"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref175","article-title":"Conditional DETR v2: Efficient detection transformer with box queries","author":"Chen","year":"2022"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref177","first-page":"1","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref179","first-page":"1","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref181","article-title":"Learning equivariant segmentation with instance-unique querying","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"ref183","article-title":"Group DETR: Fast DETR training with group-wise one-to-many assignment","author":"Chen","year":"2022"},{"key":"ref184","article-title":"DETRs with collaborative hybrid assignments training","author":"Zong","year":"2022"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref186","article-title":"TransTrack: Multiple-object tracking with transformer","author":"Sun","year":"2020"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref188","first-page":"31265","article-title":"MinVIS: A minimal video instance segmentation framework without video-based training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_34"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_42"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00168"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_31"},{"key":"ref193","article-title":"Multi-task learning with multi-query transformer for dense prediction","author":"Xu","year":"2022"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_30"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2024.3371348"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref203","first-page":"21984","article-title":"Few-shot segmentation via cycle-consistent transformer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref204","first-page":"2491","article-title":"Associating objects with transformers for video object segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01140"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_36"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3252807"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_35"},{"key":"ref209","article-title":"Mask matching transformer for few-shot segmentation","author":"Jiao","year":"2022"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref211","first-page":"1","article-title":"CycleMLP: A MLP-like architecture for dense prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref212","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tolstikhin"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00090"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref215","first-page":"1","article-title":"Designing BERT for convolutional networks: Sparse and hierarchical masked modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tian"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref217","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00264"},{"key":"ref219","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022"},{"key":"ref220","article-title":"Masked autoencoders as spatiotemporal learners","author":"Feichtenhofer","year":"2022"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20227"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref226","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00259"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00439"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00102"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00529"},{"key":"ref233","first-page":"226","article-title":"End-to-end object detection with adaptive clustering transformer","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Zheng"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"ref235","first-page":"1","article-title":"Sparse DETR: Efficient end-to-end object detection with learnable sparsity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Roh"},{"key":"ref236","first-page":"23109","article-title":"VITA: Video instance segmentation via object token association","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Heo"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_17"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00030"},{"key":"ref240","first-page":"13877","article-title":"Tube-link: A flexible cross tube baseline for universal video segmentation","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Li"},{"key":"ref241","article-title":"Efficient DETR: Improving end-to-end object detector with dense prior","author":"Yao","year":"2021"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01733"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_6"},{"key":"ref244","article-title":"PanopticPartFormer: A unified and decoupled view for panoptic part segmentation","author":"Li","year":"2023"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01868"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01247"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163578"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-024-01539-4"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3155958"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3421340"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref259","article-title":"Point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training","author":"Zhang","year":"2022"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160590"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25335"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00479"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25329"},{"key":"ref264","article-title":"A dataset for semantic segmentation of point cloud sequences","author":"Behley","year":"2019"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref266","first-page":"493","article-title":"Tip-Adapter: Training-free CLIP-adapter for better vision-language modeling","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhang"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref268","first-page":"1","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref274","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01081"},{"key":"ref278","article-title":"Rethinking evaluation metrics of open-vocabulary segmentaion","author":"Zhou","year":"2023"},{"key":"ref279","first-page":"1","article-title":"F-VLM: Open-vocabulary object detection upon frozen vision and language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kuo"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_30"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref282","first-page":"1","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02005"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01242"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00414"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00969"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_22"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01128"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475317"},{"key":"ref295","article-title":"DA-DETR: Domain adaptive detection transformer by hybrid attention","author":"Zhang","year":"2021"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_37"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237740"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00295"},{"key":"ref299","article-title":"The devil is in the labels: Semantic segmentation from sentences","author":"Yin","year":"2022"},{"key":"ref300","first-page":"1","article-title":"LMSeg: Language-guided multi-dataset segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Qiang"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00742"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01097"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3320613"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01911-w"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_26"},{"key":"ref308","first-page":"6582","article-title":"Weakly supervised instance segmentation using the bounding box tightness prior","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hsu"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00339"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00683"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02189"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"ref315","first-page":"310","article-title":"Localizing objects with self-supervised transformers and no labels","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Sim\u00e9oni"},{"key":"ref316","first-page":"1","article-title":"Unsupervised semantic segmentation by distilling feature correspondences","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hamilton"},{"key":"ref317","first-page":"33754","article-title":"ReCo: Retrieve and co-segment for zero-shot transfer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref318","article-title":"Discovering object masks with transformers for unsupervised semantic segmentation","author":"Van Gansbeke","year":"2022"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01378"},{"key":"ref320","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00305"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_1"},{"key":"ref323","first-page":"1","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mehta"},{"key":"ref324","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00134"},{"key":"ref325","first-page":"35462","article-title":"Expediting large-scale vision transformer for dense prediction without fine-tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref326","article-title":"EdgeSAM: Prompt-in-the-loop distillation for on-device deployment of SAM","author":"Zhou","year":"2023"},{"key":"ref327","article-title":"RAP-SAM: Towards real-time all-purpose segment anything","author":"Xu","year":"2024"},{"key":"ref328","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"ref329","first-page":"1","article-title":"SeaFormer: Squeeze-enhanced axial transformer for mobile semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wan"},{"key":"ref330","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00891"},{"key":"ref331","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00437"},{"key":"ref332","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_42"},{"key":"ref333","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02037"},{"key":"ref334","article-title":"SegRefiner: Towards model-agnostic segmentation refinement with discrete diffusion process","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref335","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00305"},{"key":"ref336","first-page":"1","article-title":"PatchDCT: Patch refinement for high quality instance segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wen"},{"key":"ref337","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00861"},{"key":"ref338","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3227513"},{"key":"ref339","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref340","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref341","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00141"},{"key":"ref342","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00225"},{"key":"ref343","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref344","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref345","article-title":"TransUNet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"ref346","first-page":"205","article-title":"Swin-Unet: Unet-like pure transformer for medical image segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis. Workshops","author":"Cao"},{"key":"ref347","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"ref348","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref349","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref350","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2023"},{"key":"ref351","article-title":"Hierarchical open-vocabulary universal image segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref352","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref353","first-page":"20787","article-title":"CLUSTSEG: Clustering for universal segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref354","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00313"},{"key":"ref355","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_30"},{"key":"ref356","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01709"},{"key":"ref357","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00089"},{"key":"ref358","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01405"},{"key":"ref359","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00310"},{"key":"ref360","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_25"},{"key":"ref361","first-page":"1","article-title":"UNIFIED-IO: A unified model for vision, language, and multi-modal tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu"},{"key":"ref362","article-title":"Generalizable entity grounding via assistance of large language model","author":"Qi","year":"2024"},{"key":"ref363","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"ref364","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00689"},{"key":"ref365","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_26"},{"key":"ref366","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00090"},{"key":"ref367","article-title":"Explore in-context segmentation via latent diffusion models","author":"Wang","year":"2024"},{"key":"ref368","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02223-3"},{"key":"ref369","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref370","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref371","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01791"},{"key":"ref372","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_11"},{"key":"ref373","article-title":"4D panoptic scene graph generation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref374","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3442301"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10613466.pdf?arnumber=10613466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:49:59Z","timestamp":1736884199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10613466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":374,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3434373","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":[[2024,12]]}}}