{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T04:07:36Z","timestamp":1784261256666,"version":"3.55.0"},"reference-count":95,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072116"],"award-info":[{"award-number":["62072116"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3590924","type":"journal-article","created":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T18:51:45Z","timestamp":1753901505000},"page":"6949-6961","source":"Crossref","is-referenced-by-count":20,"title":["FoodLMM: A Versatile Food Assistant Using Large Multi-Modal Model"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2194-5594","authenticated-orcid":false,"given":"Yuehao","family":"Yin","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7591-6016","authenticated-orcid":false,"given":"Huiyan","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9213-2611","authenticated-orcid":false,"given":"Bin","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3148-264X","authenticated-orcid":false,"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4182-8261","authenticated-orcid":false,"given":"Chong-Wah","family":"Ngo","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang","year":"2022"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123618"},{"key":"ref4","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref5","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref7","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref8","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","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref10","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref11","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. neural Inf. Process. Syst."},{"key":"ref12","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref13","article-title":"MultiModal-GPT: A vision and language model for dialogue with humans","author":"Gong","year":"2023"},{"key":"ref14","article-title":"NExT-GPT: Any-to-any multimodal LLM","volume-title":"Proc. 41th Int. Conf. Mach. Learn.","author":"Wu","year":"2024"},{"key":"ref15","article-title":"MiniGPT-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3237166"},{"key":"ref17","first-page":"28541","article-title":"LLaVA-MED: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3282874"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964315"},{"key":"ref21","first-page":"394","article-title":"Food ingredients recognition through multi-label learning","volume-title":"Proc. New Trends Image Anal. Process.","author":"Bolaos","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6626"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218790"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3181789"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3123474"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01070"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3366424.3383536"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_22"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181294"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050090"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00879"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3199911"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI51738.2020.00039"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68821-9_51"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475201"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging9100205"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CCIS53392.2021.9754670"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531426"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3330047"},{"key":"ref41","article-title":"Transferring knowledge for food image segmentation using transformers and convolutions","author":"Sinha","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"ref45","article-title":"GPT-4 vs. GPT-3.5: A concise showdown","author":"Koubaa","year":"2023"},{"key":"ref46","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90 chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref47","article-title":"OpenFlamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023"},{"key":"ref48","article-title":"Pmc-llama: Further finetuning llama on medical papers","author":"Wu","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.40895"},{"key":"ref50","article-title":"BiomedGPT: Open multimodal generative pre-trained transformer for biomedicine","author":"Luo","year":"2023"},{"key":"ref51","article-title":"BloombergGPT: A large language model for finance","author":"Wu","year":"2023"},{"key":"ref52","article-title":"ChatLaw: Open-source legal large language model with integrated external knowledge bases","author":"Cui","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3045639"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16199-0_1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237871"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-39601-9_4"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052663"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49724-8_4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3390\/nu9070657"},{"key":"ref60","article-title":"ChineseFoodNet: A large-scale image dataset for chinese food recognition","author":"Chen","year":"2017"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00068"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3371212"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3020079"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01174"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240627"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123428"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3083109"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413809"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_7"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2013.6607548"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3347448.3357162"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1108\/09590550710773246"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2958761"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080826"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/1719970.1720021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1177\/156482650102200201"},{"issue":"159","key":"ref77","first-page":"1","article-title":"National health and nutrition examination survey: Estimation procedures, 2007-2010","author":"Mirel","year":"2013","journal-title":"Vital Health Statistics. Ser. 2 Data Eval. Methods Res."},{"issue":"184","key":"ref78","first-page":"1","article-title":"National health and nutrition examination survey, 2015-2018: Sample design and estimation procedures","author":"Chen","year":"2020","journal-title":"Vital Health Statist. Ser. 2, Data Eval. Methods Res."},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459548"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330734"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.nut.2018.05.003"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-016-1642-6"},{"issue":"2","key":"ref86","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"1","author":"Hu","year":"2022"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00800"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3318958"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019977"},{"key":"ref94","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu","year":"2020"},{"key":"ref95","article-title":"Multi-task learning with deep neural networks: A survey","author":"Crawshaw","year":"2020"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11105019.pdf?arnumber=11105019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:25:32Z","timestamp":1761153932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11105019\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3590924","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}