{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:05:21Z","timestamp":1780949121719,"version":"3.54.1"},"reference-count":99,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3672908","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:36:39Z","timestamp":1773347799000},"page":"8678-8693","source":"Crossref","is-referenced-by-count":1,"title":["T-Rex2++: Toward Generic Object Perception via Text-Visual Prompt Synergy"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2067-6411","authenticated-orcid":false,"given":"Qing","family":"Jiang","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Vision and Robotics, International Digital Economy Academy, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoyang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Computer Vision and Robotics, International Digital Economy Academy, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhe","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Computer Vision and Robotics, International Digital Economy Academy, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilong","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Vision and Robotics, International Digital Economy Academy, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6926-0538","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Vision and Robotics, International Digital Economy Academy, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref4","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref9","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3413013"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref19","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23977\/acss.2023.070812"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0868"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_27"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01222"},{"key":"ref25","article-title":"T-rex: Counting by visual prompting","author":"Jiang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02280"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref31","article-title":"ELEVATER: A benchmark and toolkit for evaluating language-augmented visual models","author":"Li","year":"2022"},{"key":"ref32","article-title":"Roboflow 100: A rich, multi-domain object detection benchmark","author":"Ciaglia","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02586"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00394"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3551648"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_27"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00110"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref50","article-title":"Matcher: Segment anything with one shot using all-purpose feature matching","author":"Liu","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01222"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref54","article-title":"Unified-IO: A unified model for vision, language, and multi-modal tasks","author":"Lu","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01253"},{"key":"ref56","article-title":"DINO-X: A unified vision model for open-world object detection and understanding","author":"Team","year":"2025"},{"key":"ref57","first-page":"61501","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref58","first-page":"69925","article-title":"VisionLLM v2: An end-to-end generalist multimodal large language model for hundreds of vision-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2024"},{"key":"ref59","article-title":"NExT-chat: An LMM for chat, detection and segmentation","author":"Zhang","year":"2023"},{"key":"ref60","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"ref61","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00915","article-title":"LISA: Reasoning segmentation via large language model","author":"Lai","year":"2024"},{"key":"ref62","article-title":"OneThinker: All-in-one reasoning model for image and video","author":"Feng","year":"2025"},{"key":"ref63","article-title":"ChatRex: Taming multimodal LLM for joint perception and understanding","author":"Jiang","year":"2025"},{"key":"ref64","article-title":"The all-seeing project: Towards panoptic visual recognition and understanding of the open world","author":"Wang","year":"2023"},{"key":"ref65","article-title":"Griffon-G: Bridging vision-language and vision-centric tasks via large multimodal models","author":"Zhan","year":"2024"},{"key":"ref66","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref68","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00297"},{"key":"ref70","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0663"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref76","article-title":"OpenImages: A public dataset for large-scale multi-label and multi-class image classification","author":"Krasin","year":"2017"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref78","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"ref79","article-title":"Bamboo: Building mega-scale vision dataset continually with human-machine synergy","author":"Zhang","year":"2022"},{"key":"ref80","article-title":"Scaling open-vocabulary object detection","author":"Minderer","year":"2024"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"ref82","article-title":"CrowdHuman: A benchmark for detecting human in a crowd","author":"Shao","year":"2018"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_19"},{"key":"ref84","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref85","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref86","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.00135","article-title":"Masked-attention mask transformer for universal image segmentation","author":"Cheng","year":"2022"},{"key":"ref87","article-title":"OneFormer: One transformer to rule universal image segmentation","author":"Jain","year":"2022"},{"key":"ref88","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.01058","article-title":"MaskCLIP: Masked self-distillation advances contrastive language-image pretraining","author":"Dong","year":"2023"},{"key":"ref89","article-title":"Generalized decoding for pixel, image, and language","author":"Zou","year":"2022"},{"key":"ref90","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.01324","article-title":"Generative region-language pretraining for open-ended object detection","author":"Lin","year":"2024"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_20"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00931"},{"key":"ref93","article-title":"CounTR: Transformer-based generalised visual counting","author":"Liu","year":"2022"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00340"},{"key":"ref95","article-title":"CountGD: Multi-modal open-world counting","author":"Amini-Naieni","year":"2025"},{"key":"ref96","article-title":"A low-shot object counting network with iterative prototype adaptation","author":"Djukic","year":"2023"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01607"},{"key":"ref98","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"11","key":"ref99","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11430523.pdf?arnumber=11430523","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:51:37Z","timestamp":1780948297000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11430523\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":99,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3672908","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}