{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T03:56:44Z","timestamp":1790567804189,"version":"4.1.0"},"reference-count":38,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T00:00:00Z","timestamp":1788480000000},"content-version":"vor","delay-in-days":3,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ift.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Food Science"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:label\/>\n                    <jats:p>The rapid diversification of food products, frequent packaging updates, and seasonal variations pose significant challenges for vision\u2010based food inspection and dietary monitoring in real\u2010world food systems. To address the need for scalable and flexible food analysis, this study proposes a domain\u2010adaptive open\u2010vocabulary food object detection (OVFD) framework that enables the identification of both existing and previously unseen food categories without category\u2010specific box annotations for new items. By leveraging open\u2010vocabulary representations, the framework allows dynamic expansion of detectable food categories as new items emerge, supporting continuous adaptation to evolving products, recipes, and dietary patterns while reducing manual annotation requirements. The proposed method integrates a dynamic prompt distribution network (DPDN) to improve region\u2010text alignment, along with a density\u2010aware multiple instance learning (DA\u2010MIL) strategy that uses weakly supervised image\u2010level tags to improve generalization and suppress background\u2010driven detections. To reduce semantic leakage, Food2K labels are filtered by normalized matching, synonym auditing, and overlap\u2010based rules before training. The framework was evaluated on multiple benchmark food datasets under open\u2010vocabulary settings, demonstrating consistent improvements in detection performance for both Base (seen) and Novel (unseen) food categories, with Novel\u2010category gains also observed under AP75 (average precision at intersection\u2010over\u2010union = 0.75) and COCO\u2010style AP. Repeated\u2010run reporting, error analysis, and limited external evaluation support stability and practical plausibility. By enabling dynamic category expansion with reduced annotation overhead, the proposed approach provides an assistive localization module for downstream dietary assessment, sorting review, and quality\u2010inspection workflows, while task\u2010specific validation and human verification remain necessary before operational food\u2010safety or production\u2010line use.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Practical Applications<\/jats:title>\n                    <jats:p>This study provides an OVFD approach that can be adapted to new food items with reduced category\u2010specific box annotation. Bounding\u2010box localization can support upstream perception for portion estimation, ingredient\u2010level dietary logging, assisted sorting review, and quality\u2010inspection workflows by identifying where food items are located before secondary human or automated assessment. The present evidence supports assistive use only; human verification and validation under pilot\u2010plant or real production conditions remain necessary before operational use. The detector is therefore intended to provide spatial evidence for subsequent review, not to replace validated food\u2010inspection, quality\u2010assessment, or production\u2010control procedures.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/1750-3841.71414","type":"journal-article","created":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T16:46:36Z","timestamp":1788540396000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual Food Object Detection via Open\u2010Vocabulary Learning"],"prefix":"10.1111","volume":"91","author":[{"given":"Shoulong","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Artificial Intelligence Ludong University  Yantai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guorui","family":"Sheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence Ludong University  Yantai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaojie","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence Ludong University  Yantai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bolin","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence Ludong University  Yantai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6668-9208","authenticated-orcid":false,"given":"Weiqing","family":"Min","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1596-4326","authenticated-orcid":false,"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,4]]},"reference":[{"key":"e_1_2_9_2_1","first-page":"397","volume-title":"Lecture Notes in Computer Science","author":"Bansal A.","year":"2018"},{"key":"e_1_2_9_3_1","doi-asserted-by":"crossref","unstructured":"Bilen H. andA.Vedaldi.2016. \u201cWeakly Supervised Deep Detection Networks.\u201d In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2846\u20132854.IEEE.https:\/\/doi.org\/10.1109\/CVPR.2016.311.","DOI":"10.1109\/CVPR.2016.311"},{"key":"e_1_2_9_4_1","first-page":"393","volume-title":"Lecture Notes in Computer Science","author":"Bravo M. A.","year":"2022"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0260\u20108774(03)00183\u20103"},{"key":"e_1_2_9_6_1","first-page":"213","volume-title":"Lecture Notes in Computer Science","author":"Carion N.","year":"2020"},{"key":"e_1_2_9_7_1","doi-asserted-by":"crossref","unstructured":"Fu S. Q.Yang Q.Mo et\u00a0al.2025. \u201cLLMDet: Learning Strong Open\u2010Vocabulary Object Detectors Under the Supervision of Large Language Models.\u201darXiv.https:\/\/arxiv.org\/abs\/2501.18954.","DOI":"10.1109\/CVPR52734.2025.01396"},{"key":"e_1_2_9_8_1","unstructured":"Gu X. T. Y.Lin W.Kuo andY.Cui.2021.\u201cOpen\u2010Vocabulary Object Detection via Vision and Language Knowledge Distillation.\u201darXiv.https:\/\/arxiv.org\/abs\/2104.13921."},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_10_1","unstructured":"Hinton G. O.Vinyals andJ.Dean.2015. \u201cDistilling the Knowledge in a Neural Network.\u201darXiv.https:\/\/arxiv.org\/abs\/1503.02531."},{"key":"e_1_2_9_11_1","unstructured":"Jia C. Y.Yang Y.Xia et\u00a0al.2021. \u201cScaling up Visual and Vision\u2010Language Representation Learning With Noisy Text Supervision.\u201darXiv.https:\/\/arxiv.org\/abs\/2102.05918."},{"key":"e_1_2_9_12_1","doi-asserted-by":"crossref","unstructured":"Jiang S. andW.Min.2020. \u201cFood Computing for Multimedia.\u201d In Proceedings of the 28th ACM International Conference on Multimedia 4782\u20134784.Association for Computing Machinery.https:\/\/doi.org\/10.1145\/3394171.3418544.","DOI":"10.1145\/3394171.3418544"},{"key":"e_1_2_9_13_1","doi-asserted-by":"crossref","unstructured":"Joseph K. J. S.Khan F. S.Khan andV. N.Balasubramanian.2021. \u201cTowards Open World Object Detection.\u201d In2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 5826\u20135836.IEEE.https:\/\/doi.org\/10.1109\/CVPR46437.2021.00577.","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"e_1_2_9_14_1","doi-asserted-by":"crossref","unstructured":"Kawano Y. andK.Yanai.2014. \u201cFood Image Recognition With Deep Convolutional Features.\u201d InProceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication 589\u2013593.Association for Computing Machinery.https:\/\/doi.org\/10.1145\/2638728.2641339.","DOI":"10.1145\/2638728.2641339"},{"key":"e_1_2_9_15_1","doi-asserted-by":"crossref","unstructured":"Kim J. E.Cho S.Kim andH. J.Kim.2024. \u201cRetrieval\u2010Augmented Open\u2010Vocabulary Object Detection.\u201d In2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 17427\u201317436.IEEE.https:\/\/doi.org\/10.1109\/CVPR52733.2024.01650.","DOI":"10.1109\/CVPR52733.2024.01650"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"e_1_2_9_17_1","unstructured":"Li L. H. P.Zhang H.Zhang et\u00a0al.2021. \u201cGrounded Language\u2010Image Pre\u2010Training.\u201darXiv.https:\/\/arxiv.org\/abs\/2112.03857."},{"key":"e_1_2_9_18_1","doi-asserted-by":"crossref","unstructured":"Li Z. L.Yao X.Zhang X.Wang S.Kanhere andH.Zhang.2019. \u201cZero\u2010shot Object Detection With Textual Descriptions.\u201dProceedings of the AAAI Conference on Artificial Intelligence33 no.01:8690\u20138697.https:\/\/doi.org\/10.1609\/aaai.v33i01.33018690.","DOI":"10.1609\/aaai.v33i01.33018690"},{"key":"e_1_2_9_19_1","doi-asserted-by":"crossref","unstructured":"Lin J. Y.Shen B.Wang S.Lin K.Li andL.Cao.2024. \u201cWeakly Supervised Open\u2010Vocabulary Object Detection.\u201dProceedings of the AAAI Conference on Artificial Intelligence38 no.4:3404\u20133412.https:\/\/doi.org\/10.1609\/aaai.v38i4.28127.","DOI":"10.1609\/aaai.v38i4.28127"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_9_22_1","first-page":"740","volume-title":"Lecture Notes in Computer Science","author":"Lin T. Y.","year":"2014"},{"key":"e_1_2_9_23_1","doi-asserted-by":"crossref","unstructured":"Liu S. Z.Zeng T.Ren et\u00a0al.2023. \u201cGrounding DINO: Marrying DINO With Grounded Pre\u2010Training for Open\u2010Set Object Detection.\u201darXiv.https:\/\/arxiv.org\/abs\/2303.05499.","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2927476"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329168"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237871"},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"Myers A. N.Johnston V.Rathod et\u00a0al.2015. \u201cIm2calories: Towards an Automated Mobile Vision Food Diary.\u201d In2015 IEEE International Conference on Computer Vision (ICCV) 1233\u20131241.IEEE.https:\/\/doi.org\/10.1109\/ICCV.2015.146.","DOI":"10.1109\/ICCV.2015.146"},{"key":"e_1_2_9_28_1","unstructured":"Radford A. J. W.Kim C.Hallacy et\u00a0al.2021. \u201cLearning Transferable Visual Models From Natural Language Supervision.\u201darXiv.https:\/\/arxiv.org\/abs\/2103.00020."},{"key":"e_1_2_9_29_1","doi-asserted-by":"crossref","unstructured":"Rahman S. S.Khan andN.Barnes.2019. \u201cTransductive Learning for Zero\u2010Shot Object Detection.\u201d2019 IEEE\/CVF International Conference on Computer Vision (ICCV) 6081\u20136090.IEEE.https:\/\/doi.org\/10.1109\/ICCV.2019.00618.","DOI":"10.1109\/ICCV.2019.00618"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1111\/1750\u20103841.12987"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263\u2010015\u20100816\u2010y"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876304"},{"key":"e_1_2_9_34_1","doi-asserted-by":"crossref","unstructured":"Tang P. X.Wang X.Bai andW.Liu.2017. \u201cMultiple Instance Detection Network With Online Instance Classifier Refinement.\u201d In2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 3059\u20133067.IEEE.https:\/\/doi.org\/10.1109\/CVPR.2017.326.","DOI":"10.1109\/CVPR.2017.326"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"Zareian A. K. D.Rosa D. H.Hu andS. F.Chang.2021. \u201c Open\u2010Vocabulary Object Detection Using Captions.\u201d In2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 14388\u201314397.IEEE.https:\/\/doi.org\/10.1109\/CVPR46437.2021.01416.","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"e_1_2_9_36_1","doi-asserted-by":"crossref","unstructured":"Zhong Y. J.Yang P.Zhang et\u00a0al.2022. \u201cRegionCLIP: Region\u2010Based Language\u2010Image Pretraining\u201d In2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 16772\u201316782.IEEE.https:\/\/doi.org\/10.1109\/CVPR52688.2022.01629.","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"Zhou K. J.Yang C. C.Loy andZ.Liu.2022a. \u201cConditional Prompt Learning for Vision\u2010Language Models.\u201d In2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 16795\u201316804.IEEE.https:\/\/doi.org\/10.1109\/CVPR52688.2022.01631.","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263\u2010022\u201001653\u20101"},{"key":"e_1_2_9_39_1","doi-asserted-by":"crossref","unstructured":"Zhou X. R.Girdhar A.Joulin P.Kr\u00e4henb\u00fchl andI.Misra.2022. \u201cDetecting Twenty\u2010Thousand Classes Using Image\u2010Level Supervision.\u201darXiv.https:\/\/arxiv.org\/abs\/2201.02605.","DOI":"10.1007\/978-3-031-20077-9_21"}],"container-title":["Journal of Food Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ift.onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/1750-3841.71414","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ift.onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/1750-3841.71414","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ift.onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/1750-3841.71414","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T03:23:19Z","timestamp":1790565799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ift.onlinelibrary.wiley.com\/doi\/10.1111\/1750-3841.71414"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":38,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1111\/1750-3841.71414"],"URL":"https:\/\/doi.org\/10.1111\/1750-3841.71414","archive":["Portico"],"relation":{},"ISSN":["0022-1147","1750-3841"],"issn-type":[{"value":"0022-1147","type":"print"},{"value":"1750-3841","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"2026-02-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e71414"}}