{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T01:17:10Z","timestamp":1772759830498,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125109"],"award-info":[{"award-number":["62125109"]}],"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":["61931023"],"award-info":[{"award-number":["61931023"]}],"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":["61932022"],"award-info":[{"award-number":["61932022"]}],"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":["62371288"],"award-info":[{"award-number":["62371288"]}],"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":["62320106003"],"award-info":[{"award-number":["62320106003"]}],"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":["62120106007"],"award-info":[{"award-number":["62120106007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521851","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:32:25Z","timestamp":1735155145000},"page":"2127-2140","source":"Crossref","is-referenced-by-count":1,"title":["MENSA: Multi-Dataset Harmonized Pretraining for Semantic Segmentation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9169-7055","authenticated-orcid":false,"given":"Bowen","family":"Shi","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6337-5748","authenticated-orcid":false,"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0026-4247","authenticated-orcid":false,"given":"Yaoming","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2522-5778","authenticated-orcid":false,"given":"Wenrui","family":"Dai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9694-9880","authenticated-orcid":false,"given":"Junni","family":"Zou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4552-0029","authenticated-orcid":false,"given":"Hongkai","family":"Xiong","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2890360"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3198314"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3151145"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref9","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01045"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref18","first-page":"2022","article-title":"Language-driven semantic segmentation","volume-title":"Proc. 10th Int. Conf. Learn. Representation","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02060-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref22","first-page":"2022","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. 10th Int. Conf. Learn. Representation","author":"Bao"},{"key":"ref23","first-page":"552","article-title":"PeCo: Perceptual codebook for BERT pre-training of vision transformers","volume-title":"Proc. 37th AAAI Conf. Artif. Intell.","author":"Dong","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00295"},{"key":"ref26","first-page":"2487","article-title":"Cross-dataset collaborative learning for semantic segmentation","volume-title":"Proc. 36th AAAI Conf. Artif. Intell.","author":"Wang","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00085"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_2"},{"key":"ref29","article-title":"Democratizing contrastive language-image pre-training: A CLIP benchmark of data, model, and supervision","volume-title":"Proc. ICML Pre-Training Workshop","author":"Cui","year":"2022"},{"key":"ref30","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01436"},{"key":"ref34","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. 10th Int. Conf. Learn. Representation","author":"Gu","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref39","first-page":"736","article-title":"A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model","volume-title":"Proc. 17th Eur. Conf. Comput. Vis.","author":"Xu","year":"2022"},{"key":"ref40","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. 32rd Int. Conf. Mach. Learn.","author":"Ganin","year":"2015"},{"key":"ref41","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume-title":"Proc. 32rd Int. Conf. Mach. Learn.","author":"Long","year":"2015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"ref43","first-page":"6450","article-title":"Domain generalization via model-agnostic learning of semantic features","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Dou","year":"2019"},{"key":"ref44","first-page":"998","article-title":"MetaReg: Towards domain generalization using meta-regularization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Balaji","year":"2018"},{"key":"ref45","first-page":"5542","article-title":"Deeper, broader and artier domain generalization","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Li","year":"2017"},{"key":"ref46","first-page":"5715","article-title":"Unified deep supervised domain adaptation and generalization","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Motiian","year":"2017"},{"key":"ref47","first-page":"6023","article-title":"CutMix: Regularization strategy to train strong classifiers with localizable features","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Yun","year":"2019"},{"key":"ref48","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. 6th Int. Conf. Learn. Representation","author":"Zhang","year":"2018"},{"issue":"1","key":"ref49","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","article-title":"The PASCAL visual object classes challenge: A retrospective","volume":"111","author":"Everingham","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref57","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. 5th Int. Conf. Learn. Representation","author":"Loshchilov","year":"2017"},{"key":"ref58","first-page":"2023","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proc. 11th Int. Conf. Learn. Representation","author":"Chen"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_36"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10814086.pdf?arnumber=10814086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T21:56:22Z","timestamp":1744062982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10814086\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521851","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}