{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:43:50Z","timestamp":1781797430050,"version":"3.54.5"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036012"],"award-info":[{"award-number":["62036012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20387"],"award-info":[{"award-number":["U23A20387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322212"],"award-info":[{"award-number":["62322212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072455"],"award-info":[{"award-number":["62072455"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Pengcheng Laboratory Research Project","doi-asserted-by":"publisher","award":["PCL2023A08"],"award-info":[{"award-number":["PCL2023A08"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021ZD0112200"],"award-info":[{"award-number":["2021ZD0112200"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alibaba Innovative Research Program; and in part by the CAS Project for Young Scientists in Basic Research","award":["YSBR-116"],"award-info":[{"award-number":["YSBR-116"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3485518","type":"journal-article","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T17:37:08Z","timestamp":1730223428000},"page":"6253-6267","source":"Crossref","is-referenced-by-count":7,"title":["Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2467-888X","authenticated-orcid":false,"given":"Yifan","family":"Xu","sequence":"first","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengdan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Youtu Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-9755","authenticated-orcid":false,"given":"Xiaoshan","family":"Yang","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"MAIS, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref3","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref5","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref8","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv:2104.13921"},{"key":"ref9","article-title":"DetCLIP: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","author":"Yao","year":"2022","journal-title":"arXiv:2209.09407"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_10"},{"key":"ref14","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref15","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","first-page":"1","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref18","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref19","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"ref21","article-title":"Open vocabulary object detection with proposal mining and prediction equalization","author":"Chen","year":"2022","journal-title":"arXiv:2206.11134"},{"key":"ref22","article-title":"Multi-modal queried object detection in the wild","author":"Xu","year":"2023","journal-title":"arXiv:2305.18980"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_17"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02586"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref30","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","author":"Rasheed","year":"2022","journal-title":"arXiv:2207.03482"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_30"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01322"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0247-3"},{"key":"ref34","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv:1908.08530"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref37","article-title":"Masked vision and language modeling for multi-modal representation learning","author":"Kwon","year":"2022","journal-title":"arXiv:2208.02131"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3139234"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3283916"},{"key":"ref40","article-title":"DesCo: Learning object recognition with rich language descriptions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01290"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205212"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3302162"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286259"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205207"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1176996454"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_14"},{"key":"ref56","first-page":"1","article-title":"Bayesian dark knowledge","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Balan"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10449"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3170728"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3176130"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3141255"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3226416"},{"key":"ref62","article-title":"Unifying distillation and privileged information","author":"Lopez-Paz","year":"2015","journal-title":"arXiv:1511.03643"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3212905"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00483"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3228497"},{"key":"ref67","article-title":"Probabilistic two-stage detection","author":"Zhou","year":"2021","journal-title":"arXiv:2103.07461"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref73","volume-title":"Scenegraphparser","author":"Wu et al","year":"2019"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.311"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01368"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref79","first-page":"5583","article-title":"F-VLM: Open-vocabulary object detection upon frozen vision and language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kuo"},{"key":"ref80","article-title":"Learning object-language alignments for open-vocabulary object detection","author":"Lin","year":"2022","journal-title":"arXiv:2211.14843"},{"key":"ref81","first-page":"1","article-title":"CoDet: Co-occurrence guided region-word alignment for open-vocabulary object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ma"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00681"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00102"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref86","article-title":"Open-vocabulary object detection with meta prompt representation and instance contrastive optimization","author":"Wang","year":"2024","journal-title":"arXiv:2403.09433"},{"key":"ref87","first-page":"22682","article-title":"Aligning pretraining for detection via object-level contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wei"},{"key":"ref88","first-page":"728","article-title":"Simple open-vocabulary object detection with vision transformers","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Minderer"},{"key":"ref89","first-page":"1","article-title":"Scaling open-vocabulary object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Minderer"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10738303.pdf?arnumber=10738303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T03:45:09Z","timestamp":1732679109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10738303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3485518","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}