{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T11:05:59Z","timestamp":1790420759139,"version":"4.1.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP 160104075"],"award-info":[{"award-number":["DP 160104075"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806035"],"award-info":[{"award-number":["61806035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ARC Discovery Projects funding","award":["DP140102270"],"award-info":[{"award-number":["DP140102270"]}]},{"name":"University of Sydney Business School ARC Bridging Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1109\/tmm.2018.2877886","type":"journal-article","created":{"date-parts":[[2018,10,24]],"date-time":"2018-10-24T18:53:47Z","timestamp":1540407227000},"page":"1412-1424","source":"Crossref","is-referenced-by-count":185,"title":["Where-and-When to Look: Deep Siamese Attention Networks for Video-Based Person Re-Identification"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6119-058X","authenticated-orcid":false,"given":"Lin","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1029-9280","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9803-0256","authenticated-orcid":false,"given":"Junbin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.73"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.5244\/C.24.21"},{"key":"ref71","first-page":"413","article-title":"Local descriptors encoded by fisher vector for person reidentification","author":"ma","year":"0","journal-title":"Proc European Conf Comp Vis Workshop"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2545929"},{"key":"ref38","article-title":"PersonNet: Person re-identification with deep convolutional neural networks","author":"wu","year":"2016","journal-title":"arXiv 1601 07255"},{"key":"ref33","article-title":"Deep attention-based spatially recursive networks for fine-grained visual recognition","author":"wu","year":"2018","journal-title":"IEEE Trans Cybern"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_9"},{"key":"ref31","article-title":"Deep recurrent convolutional networks for video-based person re-identification: An end-to-end approach","author":"wu","year":"2016","journal-title":"arXiv 1606 01609"},{"key":"ref30","first-page":"843","article-title":"Unsupervised learning of video representation using LSTMs","author":"mansimov","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247939"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.463"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref60","article-title":"Delving deeper into convolutional networks for learning video representations","author":"ballas","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref62","first-page":"91","article-title":"Person re-identification by descriptive and discriminative classification","author":"hirzer","year":"0","journal-title":"Proc 17th Scandin Conf Image Anal"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639349"},{"key":"ref63","first-page":"868","article-title":"Mars: A video benchmark for large-scale person re-identification","author":"zheng","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2861366"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299036"},{"key":"ref66","article-title":"Theano: New features and speed improvements","author":"bastien","year":"0","journal-title":"Proc Deep Learn Unsupervised Learn Adv Neural Inf Process Syst Workshop"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.150"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2015.7301739"},{"key":"ref68","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","author":"tieleman","year":"0","journal-title":"Proc Coursera Course Neural Netw Mach Learn"},{"key":"ref69","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref2","first-page":"1","article-title":"Person re-identification using kernel-based metric learning methods","author":"xiong","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.26"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298832"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.148"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.434"},{"key":"ref23","first-page":"688","article-title":"Person re-identification by video ranking","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_42"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.11.018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487048"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref59","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"shi","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref57","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1421 3555"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.494"},{"key":"ref53","article-title":"Action recognition using visual attention","author":"sharma","year":"0","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref52","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.917403"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2542983"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3159171"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2279658"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2648498"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2655449"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2457339"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2612686"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2498149"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539926"},{"key":"ref19","first-page":"262","article-title":"Viewpoint invariant pedestrian recognition with an ensemble of localized features","author":"gray","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.12.022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.460"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.426"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.11.009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.08.029"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.314"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3131885.3131923"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.004"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.223"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.410"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.405"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.62"},{"key":"ref41","article-title":"Deep transfer learning for person re-identification","author":"geng","year":"2016","journal-title":"arXiv 1611 05244"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.151"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2652725"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8720290\/08506428.pdf?arnumber=8506428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:57:18Z","timestamp":1657745838000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8506428\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":73,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2877886","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6]]}}}