{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:33:56Z","timestamp":1776886436651,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888217","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Improving Food Recognition with Retrieval-Augmented and Domain-Adaptive LVLMs"],"prefix":"10.1109","author":[{"given":"Dehua","family":"Ma","sequence":"first","affiliation":[{"name":"Beijing Univ. of Posts and Telecommun.,Sch. of Integrated Circuits,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenbo","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Univ. of Posts and Telecommun.,Sch. of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianshun","family":"Xing","sequence":"additional","affiliation":[{"name":"Beijing Univ. of Posts and Telecommun.,Sch. of Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Yuan","sequence":"additional","affiliation":[{"name":"Beijing Univ. of Posts and Telecommun.,Sch. of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghan","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing Univ. of Posts and Telecommun.,Sch. of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huijia","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing Univ. of Posts and Telecommun.,Sch. of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Lei","sequence":"additional","affiliation":[{"name":"Beijing Univ. of Posts and Telecommun.,Sch. of Integrated Circuits,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaofeng","family":"He","sequence":"additional","affiliation":[{"name":"Beijing Univ. of Posts and Telecommun.,Sch. of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2017.09.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2831627"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2958761"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/s0065-3454(08)60081-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.146"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00879"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2993948"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00068"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3028478"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25501"},{"key":"ref11","article-title":"Visual instruction tuning","volume-title":"Advances in neural information processing systems","volume":"36","author":"Liu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref13","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671470"},{"key":"ref15","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref17","article-title":"Fastervit: Fast vision transformers with hierarchical attention","author":"Hatamizadeh","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref19","article-title":"Moe-llava: Mixture of experts for large vision-language models","author":"Lin","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.804"},{"key":"ref22","first-page":"5547","article-title":"Glam: Efficient scaling of language models with mixture-of-experts","volume-title":"International Conference on Machine Learning","author":"Du"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964315"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237871"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3193763"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374211"},{"key":"ref28","article-title":"Foodlmm: A versatile food assistant using large multi-modal model","author":"Yin","year":"2023"},{"key":"ref29","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888217.pdf?arnumber=10888217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:18Z","timestamp":1774416258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888217","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}