{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:13:02Z","timestamp":1763190782869,"version":"3.45.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227349","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["LOVD: Open-Vocabulary Object Detection Based on LLM-Enhanced Agents"],"prefix":"10.1109","author":[{"given":"Xinhao","family":"Li","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China"}]},{"given":"Jungang","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Computer Science and Technology,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Deformable detr: Deformable transformers for end-to-end object detection","year":"2020","author":"Zhu","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"article-title":"Yolov6: A single-stage object detection framework for industrial applications","year":"2022","author":"Li","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"article-title":"Pp-yolo: An effective and efficient implementation of object detector","year":"2020","author":"Long","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"article-title":"Open-vocabulary object detection via vision and language knowledge distillation","year":"2021","author":"Gu","key":"ref25"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International conference on machine learning","author":"Radford"},{"article-title":"F-vlm: Open-vocabulary object detection upon frozen vision and language models","year":"2022","author":"Kuo","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref30","first-page":"72 983","article-title":"Scaling open-vocabulary object detection","volume":"36","author":"Minderer","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Surrogate gap minimization improves sharpness-aware training","year":"2022","author":"Zhuang","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"article-title":"Gemini: a family of highly capable multimodal models","year":"2023","author":"Team","key":"ref35"},{"article-title":"Next-gpt: Any-to-any multimodal llm","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Wu","key":"ref36"},{"year":"2022","key":"ref37","article-title":"Mmyolo: Openmmlab yolo series toolbox and benchmark"},{"article-title":"Mmdetection: Open mmlab detection toolbox and benchmark","year":"2019","author":"Chen","key":"ref38"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-024-02420-5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"article-title":"Evaluating large-vocabulary object detectors: The devil is in the details","year":"2021","author":"Dave","key":"ref42"},{"key":"ref43","first-page":"36 067","article-title":"Glipv2: Unifying localization and vision-language understanding","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","first-page":"9125","article-title":"Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227349.pdf?arnumber=11227349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:09:11Z","timestamp":1763190551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227349\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227349","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}