{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:38:22Z","timestamp":1766428702699,"version":"3.37.3"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Ministry of Higher Education (MoHE) of Egypt through the Ph.D. Scholarship"},{"name":"Egypt-Japan University of Science and Technology (E-JUST) as a graduate student"},{"name":"Cyber-Physical System (CPS) Laboratory, Computer Science and Engineering Department, E-JUST"},{"DOI":"10.13039\/501100004423","name":"Waseda University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004423","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2967750","type":"journal-article","created":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T12:32:14Z","timestamp":1579609934000},"page":"18097-18109","source":"Crossref","is-referenced-by-count":3,"title":["Video Alignment Using Bi-Directional Attention Flow in a Multi-Stage Learning Model"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7837-5687","authenticated-orcid":false,"given":"Reham","family":"Abobeah","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8024-3795","authenticated-orcid":false,"given":"Amin","family":"Shoukry","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1671-2614","authenticated-orcid":false,"given":"Jiro","family":"Katto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref38","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"arXiv 1511 04119"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.301"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.04.015"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1016\/j.cviu.2009.03.012","article-title":"Video synchronization from human motion using rank constraints","volume":"113","author":"tresadern","year":"2009","journal-title":"Comput Vis Image Understand"},{"key":"ref30","first-page":"190","article-title":"Using space-time interest points for video sequence synchronization","author":"wedge","year":"2007","journal-title":"Proc IAPR Conf Mach Vis Appl"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0875-0"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00814"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806228"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.318"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.1174"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"2473","DOI":"10.1109\/TIP.2006.877438","article-title":"Tri-focal tensor-based multiple video synchronization with subframe optimization","volume":"15","author":"lei","year":"2006","journal-title":"IEEE Trans Image Process"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399123"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015765"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2095873"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1046148"},{"key":"ref21","first-page":"662","article-title":"A dense-depth representation for VLAD descriptors in content-based image retrieval","author":"magliani","year":"2018","journal-title":"Proc Int Symp Vis Comput"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315108"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238449"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.879852"},{"key":"ref25","first-page":"12","article-title":"Video synchronization via space-time interest point distribution","volume":"1","author":"yan","year":"2004","journal-title":"Proc Adv Concepts Intell Vis Syst"},{"key":"ref50","article-title":"Geometric vlad for large scale image search","author":"wang","year":"2014","journal-title":"arXiv 1403 3829"},{"key":"ref51","first-page":"774","article-title":"Negative Evidences and Co-occurences in image retrieval: The benefit of PCA and whitening","author":"j\u00e9gou","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref59","article-title":"Machine comprehension using match-LSTM and answer pointer","author":"wang","year":"2016","journal-title":"arXiv 1608 07905"},{"key":"ref58","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref57","first-page":"26","article-title":"Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"Neural Networks and Machine Learning"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5220\/0006617505550562"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref53","first-page":"304","article-title":"Hamming embedding and weak geometric consistency for large scale image search","author":"jegou","year":"2008","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref10","article-title":"Memory networks","author":"weston","year":"2015","journal-title":"arXiv 1410 3916"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref12","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","article-title":"Bidirectional attention flow for machine comprehension","author":"seo","year":"2016","journal-title":"arXiv 1611 01603"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5220\/0007524505830589"},{"key":"ref15","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref19","first-page":"404","article-title":"Surf: Speeded up robust features","author":"bay","year":"2006","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-0020-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/11744078_42"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2661229.2661276","article-title":"Videosnapping: Interactive synchronization of multiple videos","volume":"33","author":"wang","year":"2014","journal-title":"TOGACM Trans Graph"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2045714"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.61"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-4841-0"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1145\/3131885.3131905","article-title":"A location-aware embedding technique for accurate landmark recognition","author":"magliani","year":"2017","journal-title":"Proc Int Conf Distrib Smart Cameras"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88688-4_41"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.147"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref41","first-page":"451","article-title":"Ask, attend and answer: Exploring question-guided spatial attention for visual question answering","author":"xu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451103"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08963636.pdf?arnumber=8963636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T20:01:15Z","timestamp":1643313675000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8963636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2967750","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}