{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T08:07:34Z","timestamp":1767859654133,"version":"3.49.0"},"reference-count":118,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tcsvt.2023.3349007","type":"journal-article","created":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T20:02:10Z","timestamp":1704139330000},"page":"5424-5439","source":"Crossref","is-referenced-by-count":4,"title":["Context-Aware and Semantic-Consistent Spatial Interactions for One-Shot Object Detection Without Fine-Tuning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4910-1238","authenticated-orcid":false,"given":"Hanqing","family":"Yang","sequence":"first","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sijia","family":"Cai","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Deng","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0329-7458","authenticated-orcid":false,"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Nanyang Avenue, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0043-4904","authenticated-orcid":false,"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3211734"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3069848"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3126591"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3221755"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3198329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3066675"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995220"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3173960"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178173"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3183646"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088545"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00728"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6957"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00525"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01861"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00311"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_18"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_23"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00124"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_34"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_17"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_23"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_39"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_21"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00883"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00117"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00510"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25153"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_25"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/HONET.2018.8551326"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00744"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00450"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00449"},{"key":"ref39","first-page":"6353","article-title":"Generalized and discriminative few-shot object detection via SVD-dictionary enhancement","volume-title":"Proc. NeurIPS","author":"Wu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01386"},{"key":"ref41","first-page":"2725","article-title":"One-shot object detection with co-attention and co-excitation","volume-title":"Proc. NeurIPS","author":"Hsieh"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01207"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00745"},{"key":"ref44","article-title":"One-shot instance segmentation","author":"Michaelis","year":"2018","journal-title":"arXiv:1811.11507"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19959"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00851"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01419"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.02325"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00967"},{"key":"ref55","first-page":"9919","article-title":"Frustratingly simple few-shot object detection","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_12"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01005"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00727"},{"key":"ref59","first-page":"16570","article-title":"Few-shot object detection via association and discrimination","volume-title":"Proc. NeurIPS","author":"Cao"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00856"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11716"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01281"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_27"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00867"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01384"},{"key":"ref66","first-page":"18640","article-title":"Decoupling classifier for boosting few-shot object detection and instance segmentation","volume-title":"Proc. NeuIPS","author":"Gao"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.155"},{"key":"ref68","article-title":"One-shot object detection without fine-tuning","author":"Li","year":"2020","journal-title":"arXiv:2005.03819"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00325"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_38"},{"key":"ref73","first-page":"728","article-title":"Simple open-vocabulary object detection with vision transformers","volume-title":"Proc. ECCV","author":"Minderer"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00767"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00276"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3204090"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3390\/rs14215379"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475202"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3177235"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01998"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12575"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00196"},{"key":"ref89","first-page":"1","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","volume-title":"Proc. ICLR","author":"Mehta"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref95","first-page":"9011","article-title":"CATS: Cost aggregation transformers for visual correspondence","volume-title":"Proc. NeurIPS","author":"Cho"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01211"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00210"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2021.3125195"},{"key":"ref99","first-page":"21984","article-title":"Few-shot segmentation via cycle-consistent transformer","volume-title":"Proc. NeurIPS","author":"Zhang"},{"issue":"11","key":"ref100","first-page":"12832","article-title":"Meta-DETR: Few-shot object detection via unified image-level meta-learning","volume":"45","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref101","first-page":"4005","article-title":"Cross attention network for few-shot classification","volume-title":"Proc. NeuIPS","author":"Hou"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref103","first-page":"1651","article-title":"Neighbourhood consensus networks","volume-title":"Proc. NeurIPS","author":"Rocco"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01021"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00974"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00296"},{"key":"ref108","first-page":"108","article-title":"Cost aggregation is all you need for few-shot segmentation","volume-title":"Proc. ECCV","author":"Hong"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_8"},{"key":"ref110","first-page":"794","article-title":"Volumetric correspondence networks for optical flow","volume-title":"Proc. NeurIPS","author":"Ramanan"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref114","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. ICML","author":"Katharopoulos"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01002"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00943"},{"key":"ref117","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10582818\/10379026.pdf?arnumber=10379026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:12:13Z","timestamp":1736453533000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10379026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":118,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3349007","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}