{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:19:50Z","timestamp":1776183590574,"version":"3.50.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"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":["61871308"],"award-info":[{"award-number":["61871308"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202106960046"],"award-info":[{"award-number":["202106960046"]}],"id":[{"id":"10.13039\/501100004543","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":[[2023,3]]},"DOI":"10.1109\/tcsvt.2022.3212434","type":"journal-article","created":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T19:36:51Z","timestamp":1664998611000},"page":"1109-1122","source":"Crossref","is-referenced-by-count":63,"title":["Hybrid CNN-Transformer Features for Visual Place Recognition"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5011-1492","authenticated-orcid":false,"given":"Yuwei","family":"Wang","sequence":"first","affiliation":[{"name":"Key Laboratory of Electronic Equipment Structure Design of Ministry of Education, School of Mechano-Electronic Engineering, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8002-6803","authenticated-orcid":false,"given":"Yuanying","family":"Qiu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Electronic Equipment Structure Design of Ministry of Education, School of Mechano-Electronic Engineering, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3570-7511","authenticated-orcid":false,"given":"Peitao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Electronic Equipment Structure Design of Ministry of Education, School of Mechano-Electronic Engineering, Xidian University, Xi’an, China"}]},{"given":"Junyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Electronic Equipment Structure Design of Ministry of Education, School of Mechano-Electronic Engineering, Xidian University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919839761"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2956352"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00270"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107760"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3048945"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2015.7279659"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref10","first-page":"1269","article-title":"Aggregating local deep features for image retrieval","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"Babenko"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_22"},{"key":"ref12","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS52077.2021.00065"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref15","article-title":"Efficient large-scale image retrieval with deep feature orthogonality and hybrid-swin-transformers","author":"Henkel","year":"2021","journal-title":"arXiv:2110.03786"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01328"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01392"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.374"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2007.09.014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2280040"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908090961"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.222"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298790"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3099846"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2881842"},{"key":"ref34","article-title":"Learnable pooling with context gating for video classification","author":"Miech","year":"2017","journal-title":"arXiv:1706.06905"},{"key":"ref35","first-page":"175","article-title":"Image segmentation in video sequences: A probabilistic approach","volume-title":"Proc. 13th Conf. Uncertainty Artif. Intell.","author":"Friedman"},{"key":"ref36","first-page":"281","article-title":"Some methods for classifiction and analysis of multivariate observations","volume-title":"Proc. 5th Symp. Math. Statist. Probab.","author":"MacQueen"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2908982"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.346"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240525"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/rs12233890"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561812"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref46","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"ref48","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3135013"},{"key":"ref53","article-title":"Training vision transformers for image retrieval","author":"El-Nouby","year":"2021","journal-title":"arXiv:2102.05644"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2100463"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989366"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2920905"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3057503"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2517824"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00146"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref62","article-title":"Training a convolutional neural network for appearance-invariant place recognition","author":"Gomez-Ojeda","year":"2015","journal-title":"arXiv:1505.07428"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224623"},{"key":"ref65","first-page":"1","article-title":"Are we there yet? Challenging SeqSLAM on a 3000 km journey across all four seasons","volume-title":"Proc. IEEE Int. Conf. Robot. Autom. Workshop Long-Term Autonomy","author":"S\u00fcnderhauf"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927224"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2409868"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_69"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063052"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3076097"},{"key":"ref73","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref74","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00521"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_43"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10061510\/09912433.pdf?arnumber=9912433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:36:12Z","timestamp":1705962972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9912433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":81,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3212434","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}