{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T07:31:00Z","timestamp":1767079860175,"version":"3.48.0"},"reference-count":43,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3635675","type":"journal-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T18:44:20Z","timestamp":1763750660000},"page":"215940-215954","source":"Crossref","is-referenced-by-count":0,"title":["NutriChildNet: Deep Learning With Context-Aware Attention for Intelligent Childhood Nutrition Surveillance"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3946-5265","authenticated-orcid":false,"given":"Wang","family":"Yuan","sequence":"first","affiliation":[{"name":"Children’s Health Management Center, Handan First Hospital, Handan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Rongrong","sequence":"additional","affiliation":[{"name":"Children’s Health Management Center, Handan First Hospital, Handan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhaoxin","sequence":"additional","affiliation":[{"name":"Children’s Health Management Center, Handan First Hospital, Handan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gao","family":"Hui","sequence":"additional","affiliation":[{"name":"Children’s Health Management Center, Handan First Hospital, Handan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Jing","sequence":"additional","affiliation":[{"name":"Children’s Health Management Center, Handan First Hospital, Handan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang","family":"Zhitao","sequence":"additional","affiliation":[{"name":"Handan Maternal and Child Health Care Hospital, Handan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Public Health","year":"2012","author":"Turnock","key":"ref1"},{"volume-title":"Understanding Nutrition","year":"2019","author":"Whitney","key":"ref2"},{"article-title":"Zero-shot ECG classification with multimodal learning and test-time clinical knowledge enhancement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","key":"ref3"},{"key":"ref4","article-title":"Dictionary learning for integrative, multimodal and scalable single-cell analysis","author":"Hao","year":"2022","journal-title":"bioRxiv"},{"article-title":"MMPareto: Boosting multimodal learning with innocent unimodal assistance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00031"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102795"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3352602"},{"article-title":"Large multilingual models pivot zero-shot multimodal learning across languages","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02013"},{"key":"ref12","article-title":"A unified industrial large knowledge model framework in Industry 4.0 and smart manufacturing","author":"Lee","year":"2023","journal-title":"arXiv:2312.14428"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3429301"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.01919","article-title":"MMANet: Margin-aware distillation and modality-aware regularization for incomplete multimodal learning","volume-title":"Proc. Comput. Vis. Pattern Recognit.","author":"Wei"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1186\/s41239-022-00377-z"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.121","article-title":"Multimodal diffusion transformer: Learning versatile behavior from multimodal goals","author":"Reuss","year":"2024","journal-title":"Robot., Sci. Syst."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592517"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/bjet.13320"},{"issue":"4","key":"ref20","doi-asserted-by":"crossref","DOI":"10.1115\/1.4056669","article-title":"Attention-enhanced multimodal learning for conceptual design evaluations","volume":"145","author":"Song","year":"2023","journal-title":"J. Mech. Design"},{"article-title":"Calibrating multimodal learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612468"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3622784"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3233\/IDT-230727"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3576050.3576076"},{"article-title":"A theory of multimodal learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Zhou","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02166-7"},{"article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Shi","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_11"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00633-5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-023-01045-x"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2023.3284671","article-title":"Extended vision transformer (ExViT) for land use and land cover classification: A multimodal deep learning framework","volume":"61","author":"Yao","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s00394-024-03545-1"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-024-20931-w"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/nu15183893"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/nu16162685"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263181"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01918"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1458"},{"article-title":"What makes multimodal learning better than single (provably)","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Huang","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00624-6"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11263829.pdf?arnumber=11263829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T07:27:05Z","timestamp":1767079625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11263829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3635675","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}