{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:57:26Z","timestamp":1763621846881,"version":"3.41.2"},"reference-count":94,"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":[{"name":"Shenzhen Medical Research Funds in China","award":["B2302037"],"award-info":[{"award-number":["B2302037"]}]},{"name":"National Key R&D Program of China","award":["2022ZD0118201"],"award-info":[{"award-number":["2022ZD0118201"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972217","32071459","62176249","62006133","62271465"],"award-info":[{"award-number":["61972217","32071459","62176249","62006133","62271465"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AI for Science (AI4S)-Preferred Program"},{"DOI":"10.13039\/501100004791","name":"Shenzhen Graduate School, Peking University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004791","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.2025.3535294","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T13:44:24Z","timestamp":1738071864000},"page":"4029-4042","source":"Crossref","is-referenced-by-count":3,"title":["Dual-Level Masked Semantic Inference for Semi-Supervised Semantic Segmentation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5353-2467","authenticated-orcid":false,"given":"Qiankun","family":"Ma","sequence":"first","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0046-6105","authenticated-orcid":false,"given":"Ziyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9292-2744","authenticated-orcid":false,"given":"Pengchong","family":"Qiao","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Media Analytics and Computing Laboratory, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6747-0646","authenticated-orcid":false,"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9765-4523","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2980426"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3232572"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref4","first-page":"1140","article-title":"SegNeXt: Rethinking convolutional attention design for semantic segmentation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Guo","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"article-title":"Rethinking atrous convolution for semantic image segmentation","year":"2017","author":"Chen","key":"ref11"},{"article-title":"High-resolution representations for labeling pixels and regions","year":"2019","author":"Sun","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref14","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","volume-title":"Proc. 17th Int. Conf. Neural Inf. Process. Syst.","author":"Grandvalet","year":"2004"},{"key":"ref15","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop","author":"Lee","year":"2013"},{"key":"ref16","first-page":"3833","article-title":"Rethinking pre-training and self-training","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Zoph","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01139"},{"article-title":"SoftMatch: Addressing the quantity-quality trade-off in semi-supervised learning","year":"2023","author":"Chen","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01500"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00558"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367416"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00405"},{"key":"ref23","first-page":"25731","article-title":"Class-distribution-aware pseudo-labeling for semi-supervised multi-label learning","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Xie","year":"2024"},{"article-title":"Temporal ensembling for semi-supervised learning","year":"2016","author":"Laine","key":"ref24"},{"key":"ref25","first-page":"1171","article-title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Sajjadi","year":"2016"},{"key":"ref26","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Tarvainen","year":"2017"},{"key":"ref27","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Xie","year":"2020"},{"key":"ref28","first-page":"10759","article-title":"Consistency-based semi-supervised learning for object detection","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Jeong","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2837502"},{"key":"ref31","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Caron","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01347"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00934"},{"key":"ref34","first-page":"21960","article-title":"Can semi-supervised learning use all the data effectively? A lower bound perspective","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Tifrea","year":"2024"},{"key":"ref35","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Sohn","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01071"},{"key":"ref37","first-page":"11525","article-title":"Dash: Semi-supervised learning with dynamic thresholding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2021"},{"key":"ref38","first-page":"18408","article-title":"FlexMatch: Boosting semi-supervised learning with curriculum pseudo labeling","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Zhang","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_40"},{"article-title":"Semi-supervised semantic segmentation via dynamic self-training and classbalanced curriculum","year":"2020","author":"Feng","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01273"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_9"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2960224"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3138337"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5244\/c.34.154"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_26"},{"article-title":"Structured consistency loss for semi-supervised semantic segmentation","year":"2020","author":"Kim","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01092"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01876"},{"article-title":"Masked supervised learning for semantic segmentation","year":"2022","author":"Zunair","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2723841"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877127"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3228167"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3324132"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3241539"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3458936"},{"key":"ref58","first-page":"9984","article-title":"Rethinking semi-supervised medical image segmentation: A variance-reduction perspective","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"You","year":"2024"},{"key":"ref59","first-page":"61792","article-title":"Daw: Exploring the better weighting function for semi-supervised semantic segmentation","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Sun","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103111"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103011"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01484"},{"key":"ref63","first-page":"22106","article-title":"Semi-supervised semantic segmentation via adaptive equalization learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Hu","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00699"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02270"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"article-title":"Uniform masking: Enabling mae pre-training for pyramid-based vision transformers with locality","year":"2022","author":"Li","key":"ref67"},{"article-title":"MixMIM: Mixed and masked image modeling for efficient visual representation learning","year":"2022","author":"Liu","key":"ref68"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01000"},{"key":"ref71","article-title":"Contextual image masking modeling via synergized contrasting without view augmentation for faster and better visual pretraining","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2022"},{"article-title":"PixMIM: Rethinking pixel reconstruction in masked image modeling","year":"2023","author":"Liu","key":"ref72"},{"article-title":"BEiT: BERT pre-training of image transformers","year":"2021","author":"Bao","key":"ref73"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_14"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25252"},{"article-title":"Masked frequency modeling for self-supervised visual pre-training","year":"2022","author":"Xie","key":"ref78"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00126"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00423"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00422"},{"article-title":"Semi-supervised semantic segmentation via marginal contextual information","year":"2023","author":"Kimhi","key":"ref82"},{"article-title":"Semi-supervised semantic segmentation meets masked modeling: Fine-grained locality learning matters in consistency regularization","year":"2023","author":"Pan","key":"ref83"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.544"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00421"},{"key":"ref90","article-title":"PseudoSeg: Designing pseudo labels for semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zou","year":"2021"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.59275\/j.melba.2021-g79f"},{"article-title":"Explaining and harnessing adversarial examples","year":"2014","author":"Goodfellow","key":"ref93"},{"article-title":"Adversarial machine learning at scale","year":"2016","author":"Kurakin","key":"ref94"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10856422.pdf?arnumber=10856422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:48:45Z","timestamp":1752169725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10856422\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535294","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}