{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T05:59:15Z","timestamp":1790315955342,"version":"4.1.0"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Foundation of China","award":["62622604"],"award-info":[{"award-number":["62622604"]}]},{"name":"Shandong Provincial Natural Science Foundation","award":["ZR2024YQ004"],"award-info":[{"award-number":["ZR2024YQ004"]}]},{"name":"Taishan Scholars Youth Expert Program of Shandong Province","award":["tsqn202312109"],"award-info":[{"award-number":["tsqn202312109"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3729490","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:04:01Z","timestamp":1788807841000},"page":"10109-10122","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Textual Noise in Multimodal FGVC via Hierarchical Semantic Purification and Multi-Stage Alignment"],"prefix":"10.1109","volume":"35","author":[{"given":"Menghuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Ocean University of China","place":["Qingdao, China"],"department":["Department of Information Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8320-6156","authenticated-orcid":false,"given":"Qing","family":"Cai","sequence":"additional","affiliation":[{"name":"Hefei University of Technology","place":["Hefei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2478-4722","authenticated-orcid":false,"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University","place":["Hong Kong, China"],"department":["Department of Health Technology and Informatics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyu","family":"Dong","sequence":"additional","affiliation":[{"name":"Ocean University of China","place":["Qingdao, China"],"department":["Department of Information Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5027-5286","authenticated-orcid":false,"given":"David","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen","place":["Shenzhen, Guangdong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6882-600X","authenticated-orcid":false,"given":"Sheng","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Southampton","place":["Southampton, U.K."]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"issue":"1","key":"ref3","first-page":"1","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR Workshop Fine-Grained Vis. Categorization","volume":"2","author":"Khosla"},{"key":"ref4","volume-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref5","article-title":"The iNaturalist species classification and detection dataset","author":"Van Horn","year":"2017","journal-title":"arXiv:1707.06642"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13133300"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103432","article-title":"Expert knowledge-guided multi-granularity multi-scale fusion for weakly-supervised histological segmentation","volume":"125","author":"Hu","year":"2026","journal-title":"Inf. Fusion"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3469962"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110426","article-title":"Cross co-teaching for semi-supervised medical image segmentation","volume":"152","author":"Zhang","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10770-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2026.113456"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/rs13040747"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2023.112614"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-021-06592-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2933510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2021.3055617"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2921876"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28034"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00725"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00670"},{"key":"ref22","article-title":"An image is worth $16\\times 16$\n words: Transformers for image recognition at scale","volume-title":"Proc. Comput. Vis. Pattern Recognit. (ICLR)","author":"Dosovitskiy"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3244340"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.192"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.775"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093373"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00407"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.13"},{"key":"ref29","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref30","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref32","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref33","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00320-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00156"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3377540"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291819"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref45","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref48","article-title":"An image is worth $16\\times 16$\n words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref50","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref52","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3227737"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3546951"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126668"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3607828.3617797"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238548"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3441813"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3535818"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3114622"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2026.3671661"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01067"},{"key":"ref67","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref68","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2026.114765","article-title":"Soft-label guided multi-granularity prompts learning for human-object interaction detection","volume":"192","author":"Han","year":"2026","journal-title":"Appl. Soft Comput."},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3612592"},{"issue":"12","key":"ref71","doi-asserted-by":"crossref","first-page":"10319","DOI":"10.1109\/TPAMI.2024.3438154","article-title":"Gradient harmonization in unsupervised domain adaptation","volume":"46","author":"Huang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02614-0"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222624"},{"key":"ref74","first-page":"40","article-title":"Stop words for processing software engineering documents: Do they matter?","volume-title":"Proc. IEEE\/ACM 2nd Int. Workshop Natural Language-Based Softw. Eng. (NLBSE)","author":"Fan"},{"key":"ref75","first-page":"2639","article-title":"Accelerating text mining using domain-specific stop word lists","volume-title":"Proc. IEEE Int. Conf. Big Data (Big Data)","author":"Alshanik"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_26"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1902.03368"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref82","article-title":"MiniCPM-V: A GPT-4 V level MLLM on your phone","author":"Yao","year":"2024","journal-title":"arXiv:2408.01800"},{"key":"ref83","first-page":"11162","article-title":"Vit-Net: Interpretable vision transformers with neural tree decoder","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2978115"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108248"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3243048"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0304"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.09450"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105534"},{"key":"ref92","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11683333.pdf?arnumber=11683333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T05:10:06Z","timestamp":1790313006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11683333\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3729490","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}