{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T08:40:39Z","timestamp":1776847239048,"version":"3.51.2"},"reference-count":56,"publisher":"World Scientific Pub Co Pte Ltd","issue":"07","funder":[{"name":"Key Research and Development Program of Henan Province","award":["231111212000"],"award-info":[{"award-number":["231111212000"]}]},{"name":"Zhengzhou University of Aeronautics","award":["2025CX117"],"award-info":[{"award-number":["2025CX117"]}]},{"name":"Henan Province Higher Education Key Research Project","award":["25CY039"],"award-info":[{"award-number":["25CY039"]}]},{"name":"Cost Estimation System for Aerospace Forgings Based on VC6.0","award":["22029014"],"award-info":[{"award-number":["22029014"]}]},{"name":"Composite Material Production Cost Accounting System for Aerospace Components","award":["22029040"],"award-info":[{"award-number":["22029040"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2026,6,15]]},"abstract":"<jats:p>Weakly Supervised Semantic Segmentation (WSSS) reduces annotation costs but often suffers from incomplete target activation. To address this, we propose Cross-Attentive Multimodal Enhancement for Weakly-Supervised Referring Image Semantic Segmentation (CAME). CAME introduces CrossModalityAttnFusion (CMAF) to guide language features using visual cues, thereby improving semantic alignment. A Positional Encoding 2D (PED) module enhances structural perception through coordinate encoding. Structure-Aware Consistency Loss (SACL) enforces boundary alignment via edge constraints. Additionally, Entropy Constraint Loss and Focal Loss V2 suppress low-confidence noise and emphasize difficult regions. This joint optimization improves pseudo mask quality, resulting in sharper boundaries and enhanced regional consistency. Experiments show that CAME achieves mIoU scores of 54.96%, 57.08%, and 53.01% on the validation and test sets of RefCOCO, 48.25%, 46.37%, and 45.09% on RefCOCO[Formula: see text], and 54.89% on the validation set of RefCOCOg, significantly outperforming existing weakly supervised methods. These results confirm the effectiveness and strong generalization ability of the proposed approach.<\/jats:p>","DOI":"10.1142\/s0218001426550025","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T03:03:46Z","timestamp":1770174226000},"source":"Crossref","is-referenced-by-count":0,"title":["Cross-Attentive Multimodal Enhancement for Weakly Supervised Referring Image Semantic Segmentation"],"prefix":"10.1142","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6236-9850","authenticated-orcid":false,"given":"Yong","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science, Zhengzhou University of Aeronautics, Zhengzhou 450046, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4447-2337","authenticated-orcid":false,"given":"Menglu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Zhengzhou University of Aeronautics, Zhengzhou 450046, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0249-3656","authenticated-orcid":false,"given":"Tianci","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Computer Science, Zhengzhou University of Aeronautics, Zhengzhou 450046, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"key":"S0218001426550025BIB001","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"S0218001426550025BIB002","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00182"},{"issue":"2","key":"S0218001426550025BIB003","first-page":"3615","volume":"82","author":"Chen Z.","year":"2025","journal-title":"Comput. Mater. Contin."},{"key":"S0218001426550025BIB004","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00104"},{"key":"S0218001426550025BIB005","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01301"},{"key":"S0218001426550025BIB006","unstructured":"L. Deng, M. Yang, T. Li, Y. He and C. Wang, RFBNet: Deep multimodal networks with residual fusion blocks for RGB-D semantic segmentation, preprint (2019), arXiv:1907.00135."},{"key":"S0218001426550025BIB007","unstructured":"A. Dosovitskiy\n                      et al.\n                      , An image is worth 16\u00d716 words: Transformers for image recognition at scale, preprint (2020), arXiv:2010.11929."},{"key":"S0218001426550025BIB008","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00428"},{"key":"S0218001426550025BIB009","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3201372"},{"key":"S0218001426550025BIB010","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"S0218001426550025BIB011","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3581781"},{"key":"S0218001426550025BIB012","doi-asserted-by":"publisher","DOI":"10.1145\/3653021"},{"key":"S0218001426550025BIB013","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01078"},{"key":"S0218001426550025BIB014","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"S0218001426550025BIB015","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"S0218001426550025BIB016","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"S0218001426550025BIB017","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010002"},{"key":"S0218001426550025BIB018","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01638"},{"key":"S0218001426550025BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746641"},{"key":"S0218001426550025BIB020","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16269"},{"key":"S0218001426550025BIB021","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01425"},{"key":"S0218001426550025BIB022","doi-asserted-by":"crossref","unstructured":"M. Kimura, R. Shimizu, Y. Hirakawa, R. Goto and Y. Saito, On permutation-invariant neural networks, preprint (2024), arXiv:2403.17410.","DOI":"10.2139\/ssrn.4814691"},{"key":"S0218001426550025BIB023","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"S0218001426550025BIB024","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01999"},{"key":"S0218001426550025BIB025","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00429"},{"key":"S0218001426550025BIB026","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00545"},{"key":"S0218001426550025BIB027","first-page":"9694","volume":"34","author":"Li J.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0218001426550025BIB028","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"S0218001426550025BIB029","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"S0218001426550025BIB030","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02022"},{"key":"S0218001426550025BIB031","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"S0218001426550025BIB032","first-page":"2117","volume":"36","author":"Qin J.","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"S0218001426550025BIB033","first-page":"8748","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford A.","year":"2021"},{"key":"S0218001426550025BIB034","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01875"},{"key":"S0218001426550025BIB035","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/136"},{"key":"S0218001426550025BIB036","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"S0218001426550025BIB037","first-page":"100671","volume":"20","author":"Sakurai K.","year":"2025","journal-title":"Mach. Learn. Appl."},{"key":"S0218001426550025BIB038","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2046"},{"key":"S0218001426550025BIB039","unstructured":"R. Strudel, I. Laptev and C. Schmid, Weakly-supervised segmentation of referring expressions, preprint (2022), arXiv:2205.04725."},{"key":"S0218001426550025BIB040","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00719"},{"key":"S0218001426550025BIB041","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"S0218001426550025BIB042","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"S0218001426550025BIB043","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01649"},{"key":"S0218001426550025BIB044","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"S0218001426550025BIB045","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"S0218001426550025BIB046","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00690"},{"key":"S0218001426550025BIB047","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"S0218001426550025BIB048","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"S0218001426550025BIB049","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"S0218001426550025BIB050","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00715"},{"key":"S0218001426550025BIB051","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"S0218001426550025BIB052","first-page":"336","volume-title":"Proc. 14th Int. Conf. Computer Vision Theory Appl. (VISAPP)","author":"Zhang Y.","year":"2019"},{"key":"S0218001426550025BIB053","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"S0218001426550025BIB054","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"S0218001426550025BIB055","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00426"},{"key":"S0218001426550025BIB056","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001426550025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T07:44:03Z","timestamp":1776843843000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218001426550025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":56,"journal-issue":{"issue":"07","published-print":{"date-parts":[[2026,6,15]]}},"alternative-id":["10.1142\/S0218001426550025"],"URL":"https:\/\/doi.org\/10.1142\/s0218001426550025","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"value":"0218-0014","type":"print"},{"value":"1793-6381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,20]]},"article-number":"2655002"}}