{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:27:09Z","timestamp":1781022429745,"version":"3.54.1"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2108085UD12"],"award-info":[{"award-number":["2108085UD12"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176155"],"award-info":[{"award-number":["62176155"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tpami.2025.3536481","type":"journal-article","created":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T19:17:19Z","timestamp":1738264639000},"page":"3639-3656","source":"Crossref","is-referenced-by-count":12,"title":["Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7561-9789","authenticated-orcid":false,"given":"Deyi","family":"Ji","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6767-8105","authenticated-orcid":false,"given":"Feng","family":"Zhao","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2300-3039","authenticated-orcid":false,"given":"Hongtao","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7266-5579","authenticated-orcid":false,"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8662-5818","authenticated-orcid":false,"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshops","author":"Hinton"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00692"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_26"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01556"},{"key":"ref7","volume-title":"","author":"Gonzalez","year":"2002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00913"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1117\/12.2522940"},{"key":"ref12","first-page":"21719","article-title":"Discrete latent perspective learning for segmentation and detection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ji"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00296"},{"key":"ref14","article-title":"IBD: Alleviating hallucinations in large vision-language models via image-biased decoding","author":"Zhu","year":"2024","journal-title":"arXiv:2402.18476"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3096333"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3110682"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16257"},{"key":"ref20","article-title":"Reasoning3D\u2013grounding and reasoning in 3D: Fine-grained zero-shot open-vocabulary 3D reasoning part segmentation via large vision-language models","author":"Chen","year":"2024","journal-title":"arXiv:2405.19326"},{"key":"ref21","article-title":"XLSTM-UNet can be an effective 2D & 3D medical image segmentation backbone with vision-LSTM (ViL) better than its Mamba counterpart","author":"Chen","year":"2024","journal-title":"arXiv:2407.01530"},{"key":"ref22","article-title":"View-centric multi-object tracking with homographic matching in moving UAV","author":"Ji","year":"2024","journal-title":"arXiv:2403.10830"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/102"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/99"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446592"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00716"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00432"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02262"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01235"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3257546"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_21"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/34.41363"},{"key":"ref36","article-title":"Surface perception from local analysis of texture and contour","author":"Stevens","year":"1979"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1049\/ip-vis:19981688"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/83.799885"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2326059"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WiSPNET.2016.7566368"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007032"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1049\/ip-vis:20045030"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2007.09.011"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30497-5_180"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/11559573_5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/11821045_51"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CCCM.2009.5267510"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859376"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1080\/net.12.3.371.393"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3007412"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1983.1095851"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/78.127960"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/S0734-189X(87)80186-X"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"ref55","article-title":"Adaptive histogram equalization","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/BHI.2019.8834585"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2963177"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.1995.8746010"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2012.2206398"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3001940"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","first-page":"1","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref70","first-page":"1","article-title":"ENet: A deep neural network architecture for real-time semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Paszke"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3032166"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.776"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00031"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2017.8127684"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01243"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_4"},{"key":"ref85","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"},{"key":"ref86","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"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00132"},{"key":"ref90","article-title":"How to train your ViT? Data, augmentation, and regularization in vision transformers","author":"Steiner","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref91","first-page":"1","article-title":"ImageNet-21k pretraining for the masses","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ridnik"},{"key":"ref92","first-page":"1","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00891"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01637"},{"key":"ref96","first-page":"1","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10958761\/10858405.pdf?arnumber=10858405","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T17:13:39Z","timestamp":1744305219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10858405\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":96,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3536481","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":[[2025,5]]}}}