{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:35:13Z","timestamp":1784302513945,"version":"3.55.0"},"reference-count":80,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02280","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24591-24602","source":"Crossref","is-referenced-by-count":20,"title":["YOLOE: Real-Time Seeing Anything"],"prefix":"10.1109","author":[{"given":"Ao","family":"Wang","sequence":"first","affiliation":[{"name":"School of Software, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Chen","sequence":"additional","affiliation":[{"name":"BNRist, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijia","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guiguang","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","article-title":"Yolov4: Optimal speed and accuracy of object detection","volume":"1","author":"Bochkovskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00495"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"issue":"70","key":"ref6","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Won Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","article-title":"Evaluating large-vocabulary object detectors: The devil is in the details","author":"Dave","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2019.1684778"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3138\/FM57-6770-U75U-7727"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref13","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"International Conference on Learning Representation","author":"Gu","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755316"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"ref19","article-title":"T-rex: Counting by visual prompting","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_3"},{"key":"ref21","author":"Jocher","year":"2023","journal-title":"Ultralytics YOLO"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00180"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"3","key":"ref24","first-page":"18","volume":"2","author":"Krasin","year":"2017","journal-title":"Openimages: A public dataset for large-scale multi-label and multi-class image classification"},{"key":"ref25","article-title":"F-vlm: Open-vocabulary object detection upon frozen vision and language models","volume-title":"International Conference on Learning Representation","author":"Kuo","year":"2022"},{"key":"ref26","article-title":"Language-driven semantic segmentation","volume-title":"International Conference on Learning Representation","author":"Li","year":"2022"},{"key":"ref27","article-title":"Yolov6: A single-stage object detection framework for industrial applications","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01222"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_27"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01324"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref36","article-title":"Yolo-uniow: Efficient universal open-world object detection","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01462"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref42","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref46","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref48","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref49","article-title":"Dino-x: A unified vision model for openworld object detection and understanding","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","author":"Ren","year":"2024","journal-title":"Grounding dino 1.5: Advance the \u201cedge\u201d of open-set object detection"},{"key":"ref51","article-title":"Crowdhuman: A benchmark for detecting human in a crowd","author":"Shao","year":"2018","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref53","article-title":"Glu variants improve transformer","author":"Shazeer","year":"2020","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01253"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-024-01138-2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01511"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref59","first-page":"107984","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"Wang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref61","article-title":"Ovlw-detr: Open-vocabulary light-weighted detection transformer","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_12"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.23977\/acss.2023.070812"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0663"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02586"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref69","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref73","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Real-time transformer-based open-vocabulary detection with efficient fusion head","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref77","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","volume-title":"International Conference on Learning Representation","author":"Zhu","year":"2021"},{"key":"ref78","author":"Zhu","year":"2021","journal-title":"Deformable detr: Deformable transformers for end-to-end object detection"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0868"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444979.pdf?arnumber=11444979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T04:41:16Z","timestamp":1778820076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02280","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}