{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:56:07Z","timestamp":1783439767245,"version":"3.54.6"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127317","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"13590-13596","source":"Crossref","is-referenced-by-count":1,"title":["A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space"],"prefix":"10.1109","author":[{"given":"Yonghao","family":"He","sequence":"first","affiliation":[{"name":"D-Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hu","family":"Su","sequence":"additional","affiliation":[{"name":"Institute of Automation of Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyong","family":"Yu","sequence":"additional","affiliation":[{"name":"D-Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Future Science and Engineering, Soochow University,BeeLab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Sui","sequence":"additional","affiliation":[{"name":"D-Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Wang","sequence":"additional","affiliation":[{"name":"D-Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793751"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811856"},{"key":"ref3","first-page":"10521","article-title":"Learning an uncertaintyaware object detector for autonomous driving","volume-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Chiu","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3242169"},{"key":"ref6","article-title":"Learning transferable visual models from natural language supervision","volume-title":"The Thirty-eighth International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093355"},{"key":"ref8","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"The Thirtyeighth International Conference on Machine Learning (ICML)","author":"Jia","year":"2021"},{"key":"ref9","article-title":"Zero-shot detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Open-Vocabulary object detection via vision and language knowledge distillation","volume-title":"The Tenth International Conference on Learning Representations (ICLR)","author":"Gu","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref15","article-title":"Detclip: dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume-title":"The Thirty-sixth Annual Conference on Neural Information Processing Systems (NIPS)","author":"Yao","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01599"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref19","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref22","first-page":"91","article-title":"Faster R-CNN: towards realtime object detection with region proposal networks","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref26","article-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhu","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref29","volume-title":"Ultralyt-icsyolov8","author":"Jocher","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref34","volume-title":"MMYOLO: OpenMMLab YOLO series toolbox and benchmark","year":"2022"},{"key":"ref35","article-title":"MMDetection: Open mmlab detection toolbox and benchmark","author":"Chen","year":"2019","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref37","article-title":"Evaluating large-vocabulary object detectors: The devil is in the details","author":"Dave","year":"2021","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref39","article-title":"GLIPv2: Unifying Localization and Vision-Language Understanding","volume-title":"The Thirty-sixth Annual Conference on Neural Information Processing Systems (NIPS)","author":"Zhang","year":"2022"},{"key":"ref40","article-title":"Grounding DINO 1.5: Advance the \u201cEdge\u201d of Open-Set Object Detection","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"An image is worth 16X16 words: transformers for image recognition at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00349"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127317.pdf?arnumber=11127317","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:03:41Z","timestamp":1756879421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127317\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127317","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}