{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:58:41Z","timestamp":1774594721868,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2223035"],"award-info":[{"award-number":["2223035"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,26]]},"DOI":"10.1109\/aixvr67263.2026.00015","type":"proceedings-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:48:34Z","timestamp":1774554514000},"page":"48-56","source":"Crossref","is-referenced-by-count":0,"title":["Augmented Reality Visual Retrieval for Object Detection and Corpus-Guided Content Generation"],"prefix":"10.1109","author":[{"given":"Alireza","family":"Taheritajar","sequence":"first","affiliation":[{"name":"Augusta University,School of Computer and Cyber Sciences,Augusta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jieqiong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Augusta University,School of Computer and Cyber Sciences,Augusta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Orlosky","sequence":"additional","affiliation":[{"name":"Augusta University,School of Computer and Cyber Sciences,Augusta,GA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"384","article-title":"Zeroshot object detection","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Bansal"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00851"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-1092-9_7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref9","author":"Gu","year":"2021","journal-title":"Open-vocabulary object detection via vision and language knowledge distillation"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref14","author":"Yang","year":"2023","journal-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02644"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02214-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/AIxVR63409.2025.00080"},{"key":"ref18","author":"Sapkota","year":"2025","journal-title":"A review of 3d object detection with vision-language models"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676379"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1935701.1935777"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR67309.2025.00040"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/AIxVR63409.2025.00010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1016-8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00521"},{"key":"ref26","first-page":"9459","article-title":"Retrievalaugmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/AIxMM62960.2025.00008"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.573"},{"key":"ref29","author":"Sharifymoghaddam","year":"2024","journal-title":"Unirag: Universal retrieval augmentation for multi-modal large language models"},{"key":"ref30","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref31","author":"Team","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref32","author":"Li","year":"2024","journal-title":"Llava-onevision: Easy visual task transfer"},{"key":"ref33","author":"Zhu","year":"2015","journal-title":"Building a large-scale multimodal knowledge base system for answering visual queries"},{"key":"ref34","author":"Yasunaga","year":"2022","journal-title":"Retrieval-augmented multimodal language modeling"},{"key":"ref35","author":"Xue","year":"2024","journal-title":"Enhanced multimodal rag-llm for accurate visual question answering"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00907"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2025.3618474"},{"key":"ref39","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009","journal-title":"Technical report, University of Toronto"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"}],"event":{"name":"2026 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)","location":"Osaka, Japan","start":{"date-parts":[[2026,1,26]]},"end":{"date-parts":[[2026,1,28]]}},"container-title":["2026 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11449931\/11449932\/11449977.pdf?arnumber=11449977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:27:43Z","timestamp":1774589263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,26]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/aixvr67263.2026.00015","relation":{},"subject":[],"published":{"date-parts":[[2026,1,26]]}}}