{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T10:31:27Z","timestamp":1782642687075,"version":"3.54.5"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201706470082"],"award-info":[{"award-number":["201706470082"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3118975","type":"journal-article","created":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T14:40:28Z","timestamp":1634308828000},"page":"8595-8606","source":"Crossref","is-referenced-by-count":43,"title":["Toward Fine-Grained Sketch-Based 3D Shape Retrieval"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7532-3451","authenticated-orcid":false,"given":"Anran","family":"Qi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulia","family":"Gryaditskaya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jifei","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8280-3541","authenticated-orcid":false,"given":"Yonggang","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4867-7486","authenticated-orcid":false,"given":"Timothy M.","family":"Hospedales","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2530-1059","authenticated-orcid":false,"given":"Tao","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5908-3275","authenticated-orcid":false,"given":"Yi-Zhe","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref38","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"2015","author":"xu","year":"2015","journal-title":"Comput Sci"},{"key":"ref33","first-page":"8","article-title":"Semantic embedding for sketch-based 3D shape retrieval","author":"qi","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3005358.3005372"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.414"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.543"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref35","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.099"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2013.10.004"},{"key":"ref62","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185540"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref28","article-title":"Spherical CNNs","author":"cohen","year":"2018","journal-title":"arXiv 1801 10130"},{"key":"ref64","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","article-title":"Generative and discriminative voxel modeling with convolutional neural networks","author":"brock","year":"2016","journal-title":"arXiv 1608 04236"},{"key":"ref65","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00761"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_4"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22514-8_40"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.93"},{"key":"ref20","first-page":"5099","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","author":"qi","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00979"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.609"},{"key":"ref23","first-page":"307","article-title":"FPNN: Field probing neural networks for 3D data","author":"li","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref25","first-page":"1912","article-title":"3D ShapeNets: A deep representation for volumetric shapes","author":"wu","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2010.07.002"},{"key":"ref59","article-title":"ShapeNet: An information-rich 3D model repository","author":"chang","year":"2015","journal-title":"arXiv 1512 03012"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356533"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459852"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459849"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1449715.1449740"},{"key":"ref53","article-title":"Sketching: The basics; the prequel to sketching: Drawing techniques for product designers","author":"eissen","year":"2011"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_27"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298797"},{"key":"ref11","first-page":"3683","article-title":"Learning cross-domain neural networks for sketch-based 3D shape retrieval","author":"zhu","year":"2016","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref40","first-page":"4233","article-title":"Text-guided attention model for image captioning","author":"mun","year":"2017","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref12","first-page":"3374","article-title":"Deep correlated metric learning for sketch-based 3D shape retrieval","author":"dai","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.385"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00208"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.cviu.2013.11.008","article-title":"A comparison of methods for sketch-based 3D shape retrieval","volume":"119","author":"li","year":"2014","journal-title":"Comput Vis Image Understand"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2897824.2925954","article-title":"The sketchy database: Learning to retrieve badly drawn bunnies","volume":"35","author":"sangkloy","year":"2016","journal-title":"ACM Trans Graph"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00027"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP47243.2019.8965842"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.132"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107148"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.592"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2335382"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873961"},{"key":"ref49","article-title":"A survey on vision transformer","author":"han","year":"2020","journal-title":"arXiv 2012 12556"},{"key":"ref9","first-page":"121","article-title":"SHREC’14 track: Extended large scale sketch-based 3D shape retrieval","author":"li","year":"2014","journal-title":"Proc Eurograph Workshop 3D Object Retr"},{"key":"ref46","article-title":"Generating long sequences with sparse transformers","author":"child","year":"2019","journal-title":"arXiv 1904 10509"},{"key":"ref45","first-page":"4055","article-title":"Image transformer","author":"parmar","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","article-title":"Visual transformers: Token-based image representation and processing for computer vision","author":"wu","year":"2020","journal-title":"arXiv 2006 03677"},{"key":"ref47","article-title":"An image is worth $16\\times16$\n words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref41","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09573376.pdf?arnumber=9573376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:14Z","timestamp":1652194214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9573376\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3118975","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}