{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T02:11:52Z","timestamp":1762827112020,"version":"build-2065373602"},"reference-count":20,"publisher":"World Scientific Pub Co Pte Ltd","issue":"15","funder":[{"name":"E-commerce Performance Evaluation and Analysis Service jointly carried out by Suzhou University and Shanghai Huacalyx Xianghui Culture Communication","award":["2022xhx322"],"award-info":[{"award-number":["2022xhx322"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2025,12,15]]},"abstract":"<jats:p>This paper introduces a multimodal item retrieval and matching framework based on a visual-semantic joint embedding architecture. The proposed model leverages a dual-encoder structure\u00a0\u2014 comprising a ResNet-50 visual encoder and a DistilBERT text encoder\u00a0\u2014 followed by modality-specific projection heads to map features into a shared embedding space. Training is driven by a symmetric contrastive loss enhanced with hard negative mining and semantic regularization, fostering strong intra-class cohesion and inter-class separability. Evaluations on MS-COCO and Flickr30K demonstrate the model\u2019s superior retrieval performance. Specifically, it achieves Recall@1 scores of 80.5 (I2T) and 68.4 (T2I) on MS-COCO, and 69.8 (I2T) and 55.7 (T2I) on Flickr30K, outperforming baselines such as UNITER, CLIP, and SCAN. The model also shows high stability and efficiency, converging faster than alternatives and requiring less training time. Ablation studies confirm the effectiveness of contrastive loss, projection heads, and semantic regularization, while sensitivity analysis identifies an optimal temperature parameter ([Formula: see text]). Training loss and ranking distribution analyses further validate the model\u2019s robustness and fine-grained alignment capabilities. Overall, the proposed method offers a scalable, interpretable, and efficient solution for cross-modal retrieval tasks, with strong potential for deployment in real-world applications involving fine-grained and domain-specific queries.<\/jats:p>","DOI":"10.1142\/s0218001425500272","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T03:26:38Z","timestamp":1755055598000},"source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Item Retrieval and Matching Algorithm Based on Visual-Semantic Joint Embedding"],"prefix":"10.1142","volume":"39","author":[{"given":"Xu","family":"Xu","sequence":"first","affiliation":[{"name":"Business School, Suzhou University, Suzhou 234000, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaojiao","family":"Sun","sequence":"additional","affiliation":[{"name":"Business School, Suzhou University, Suzhou 234000, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2025,9,30]]},"reference":[{"key":"S0218001425500272BIB001","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107036"},{"key":"S0218001425500272BIB002","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475347"},{"key":"S0218001425500272BIB003","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"S0218001425500272BIB004","first-page":"1597","volume-title":"Int. Conf. Machine Learning","author":"Chen T.","year":"2020"},{"key":"S0218001425500272BIB005","first-page":"8765","volume":"33","author":"Chuang C.-Y.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0218001425500272BIB006","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"S0218001425500272BIB007","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3326921"},{"key":"S0218001425500272BIB008","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331213"},{"key":"S0218001425500272BIB009","first-page":"2891","volume-title":"Int. Conf. Machine Learning","author":"Huang C.","year":"2019"},{"key":"S0218001425500272BIB010","first-page":"29406","volume":"34","author":"Huang Z.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0218001425500272BIB011","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"S0218001425500272BIB012","first-page":"18661","volume":"33","author":"Khosla P.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0218001425500272BIB013","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00330"},{"key":"S0218001425500272BIB014","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3079850"},{"key":"S0218001425500272BIB015","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"S0218001425500272BIB016","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-41636-w"},{"key":"S0218001425500272BIB017","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_41"},{"key":"S0218001425500272BIB018","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00590"},{"key":"S0218001425500272BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911065"},{"key":"S0218001425500272BIB020","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029181"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001425500272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T02:05:34Z","timestamp":1762826734000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218001425500272"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":20,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2025,12,15]]}},"alternative-id":["10.1142\/S0218001425500272"],"URL":"https:\/\/doi.org\/10.1142\/s0218001425500272","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"type":"print","value":"0218-0014"},{"type":"electronic","value":"1793-6381"}],"subject":[],"published":{"date-parts":[[2025,9,30]]},"article-number":"2550027"}}