{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:35Z","timestamp":1792786895732,"version":"4.5.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFE0203100"],"award-info":[{"award-number":["2024YFE0203100"]}]},{"name":"Scientific Research Innovation Capability Support Project for Young Faculty","award":["ZYGXQNJSKYCXNLZCXM-I28"],"award-info":[{"award-number":["ZYGXQNJSKYCXNLZCXM-I28"]}]},{"name":"National Natural Science Foundation of China","award":["62476293"],"award-info":[{"award-number":["62476293"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"General Embodied AI Center of Sun Yat-sen University"},{"name":"Major Key Project of the PCL","award":["PCL2025A17"],"award-info":[{"award-number":["PCL2025A17"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3689529","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:35:44Z","timestamp":1777923344000},"page":"11370-11381","source":"Crossref","is-referenced-by-count":0,"title":["MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation"],"prefix":"10.1109","volume":"48","author":[{"given":"Kaixin","family":"Cai","sequence":"first","affiliation":[{"name":"Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9965-8088","authenticated-orcid":false,"given":"Pengzhen","family":"Ren","sequence":"additional","affiliation":[{"name":"PengCheng Laboratory","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Han","sequence":"additional","affiliation":[{"name":"Huawei Noah\u2019s Ark Lab.","place":["Montr\u00e9al, QC, Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei Noah\u2019s Ark Lab.","place":["Montr\u00e9al, QC, Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Noah\u2019s Ark Lab.","place":["Montr\u00e9al, QC, Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7960-9382","authenticated-orcid":false,"given":"Jianzhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Noah\u2019s Ark Lab.","place":["Montr\u00e9al, QC, Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3359"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02064"},{"key":"ref6","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref7","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2383"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0819"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"ref17","article-title":"Exploring visual interpretability for contrastive language-image pre-training","author":"Li","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref19","article-title":"Viewco: Discovering text-supervised segmentation masks via multi-view semantic consistency","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00106"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00143"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00116"},{"key":"ref23","first-page":"134","article-title":"Diffusion models for zero-shot open-vocabulary segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Karazija","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00367"},{"key":"ref28","article-title":"Clip surgery for better explainability with enhancement in open-vocabulary tasks","author":"Li","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"ref30","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref31","article-title":"NICE: Non-linear independent components estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dinh","year":"2015"},{"key":"ref32","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Nichol","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref34","article-title":"Synthetic data from diffusion models improves ImageNet classification","author":"Azizi","year":"2023"},{"key":"ref35","article-title":"Leaving reality to imagination: Robust classification via generated datasets","author":"Bansal","year":"2023"},{"key":"ref36","article-title":"Is synthetic data from generative models ready for image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"He","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00774"},{"key":"ref38","article-title":"Effective data augmentation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Trabucco","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547930"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00584"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00262"},{"key":"ref42","article-title":"Imaginarynet: Learning object detectors without real images and annotations","author":"Ni","year":"2022"},{"key":"ref43","article-title":"DALL-E for detection: Language-driven context image synthesis for object detection","author":"Ge","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_28"},{"key":"ref45","article-title":"Guiding text-to-image diffusion model towards grounded generation","author":"Li","year":"2023"},{"key":"ref46","article-title":"DiffusionSeg: Adapting diffusion towards unsupervised object discovery","author":"Ma","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref52","article-title":"From colouring-in to pointillism: Revisiting semantic segmentation supervision","author":"Benenson","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref56","first-page":"33","article-title":"SegCLIP: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"23","author":"Luo","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11503136.pdf?arnumber=11503136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:03:02Z","timestamp":1790265782000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11503136\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":59,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3689529","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":[[2026,10]]}}}