{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T14:31:38Z","timestamp":1785249098343,"version":"3.55.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3215168","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T20:58:31Z","timestamp":1667509111000},"page":"110603-110615","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Scale Attention and Structural Relation Graph for Local Feature Matching"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4201-2854","authenticated-orcid":false,"given":"Xiaohu","family":"Nan","sequence":"first","affiliation":[{"name":"Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Ding","sequence":"additional","affiliation":[{"name":"Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00897"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989305"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2001269.2001293"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1049"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2463671"},{"key":"ref8","article-title":"DISK: Learning local features with policy gradient","author":"Tyszkiewicz","year":"2020","journal-title":"arXiv:2006.13566"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00828"},{"key":"ref10","article-title":"R2D2: Repeatable and reliable detector and descriptor","author":"Revaud","year":"2019","journal-title":"arXiv:1906.06195"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIVC47709.2019.8981065"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01127"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3119525"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref15","article-title":"Reinforced feature points: Optimizing feature detection and description for a high-level task","author":"Bhowmik","year":"2019","journal-title":"arXiv:1912.00623"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.302"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.203"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00238"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859883"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3086142"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3016711"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_35"},{"key":"ref23","article-title":"Dual-resolution correspondence networks","author":"Li","year":"2020","journal-title":"arXiv:2006.08844"},{"key":"ref24","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016","journal-title":"arXiv:1609.02907"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_34"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref27","article-title":"GIFT: Learning transformation-invariant dense visual descriptors via group CNNs","author":"Liu","year":"2019","journal-title":"arXiv:1911.05932"},{"key":"ref28","article-title":"LF-Net: Learning local features from images","author":"Ono","year":"2018","journal-title":"arXiv:1805.09662"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_28"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11449-z"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0256500"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/1797471"},{"key":"ref33","article-title":"GiT: Graph interactive transformer for vehicle re-identification","author":"Shen","year":"2021","journal-title":"arXiv:2107.05475"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2888757"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3062498"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00263"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00034"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_44"},{"key":"ref39","article-title":"Toward geometric deep SLAM","author":"DeTone","year":"2017","journal-title":"arXiv:1707.07410"},{"key":"ref40","article-title":"Patch2Pix: Epipolar-guided pixel-level correspondences","author":"Zhou","year":"2020","journal-title":"arXiv:2012.01909"},{"key":"ref41","article-title":"DeMoN: Depth and motion network for learning monocular stereo","author":"Ummenhofer","year":"2016","journal-title":"arXiv:1612.02401"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.700"},{"key":"ref43","article-title":"GLU-Net: Global-local universal network for dense flow and correspondences","author":"Truong","year":"2019","journal-title":"arXiv:1912.05524"},{"key":"ref44","article-title":"GOCor: Bringing globally optimized correspondence volumes into your neural network","author":"Truong","year":"2020","journal-title":"arXiv:2009.07823"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00210"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01021"},{"key":"ref47","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2016","journal-title":"arXiv:1612.03144"},{"key":"ref48","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref49","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"arXiv:1502.03167"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383198"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"ref52","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref53","article-title":"Deep learning using rectified linear units (ReLU)","author":"Agarap","year":"2018","journal-title":"arXiv:1803.08375"},{"key":"ref54","article-title":"Resurrecting the sigmoid in deep learning through dynamical isometry: Theory and practice","author":"Pennington","year":"2017","journal-title":"arXiv:1711.04735"},{"key":"ref55","article-title":"ImageNet large scale visual recognition challenge","author":"Russakovsky","year":"2014","journal-title":"arXiv:1409.0575"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.410"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00752"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560987"},{"key":"ref62","article-title":"Deep layer aggregation","author":"Yu","year":"2017","journal-title":"arXiv:1707.06484"},{"key":"ref63","article-title":"Aggregated residual transformations for deep neural networks","author":"Xie","year":"2016","journal-title":"arXiv:1611.05431"},{"key":"ref64","article-title":"ResNeSt: Split-attention networks","author":"Zhang","year":"2020","journal-title":"arXiv:2004.08955"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09921215.pdf?arnumber=9921215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T05:34:13Z","timestamp":1706074453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9921215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3215168","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}