{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T17:34:59Z","timestamp":1782063299242,"version":"3.54.5"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["Z200002"],"award-info":[{"award-number":["Z200002"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19B2036"],"award-info":[{"award-number":["U19B2036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225601"],"award-info":[{"award-number":["62225601"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002766","name":"Youth Innovative Research Team of the Beijing University of Posts and Telecommunications","doi-asserted-by":"publisher","award":["2023QNTD02"],"award-info":[{"award-number":["2023QNTD02"]}],"id":[{"id":"10.13039\/501100002766","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3302521","type":"journal-article","created":{"date-parts":[[2023,8,10]],"date-time":"2023-08-10T17:51:32Z","timestamp":1691689892000},"page":"4595-4609","source":"Crossref","is-referenced-by-count":21,"title":["Sketch-Segformer: Transformer-Based Segmentation for Figurative and Creative Sketches"],"prefix":"10.1109","volume":"32","author":[{"given":"Yixiao","family":"Zheng","sequence":"first","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3659-9476","authenticated-orcid":false,"given":"Jiyang","family":"Xie","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aneeshan","family":"Sain","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5908-3275","authenticated-orcid":false,"given":"Yi-Zhe","family":"Song","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-2488","authenticated-orcid":false,"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298795"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3138\/FM57-6770-U75U-7727"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00679"},{"key":"ref56","first-page":"1","article-title":"A neural representation of sketch drawings","author":"ha","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2895155"},{"key":"ref59","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"diederik","year":"2015","journal-title":"Int Conf Learn Represent (ICLR)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2745106"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref53","first-page":"1","article-title":"CoSE: Compositional stroke embeddings","author":"aksan","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref52","article-title":"DoodleFormer: Creative sketch drawing with transformers","author":"kumar bhunia","year":"2021","journal-title":"arXiv 2112 03258"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00523"},{"key":"ref55","first-page":"833","article-title":"Encoder–decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Eur Conf Comput Vis (ECCV)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0932-3"},{"key":"ref54","first-page":"1","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2898351"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661280"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3160076"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3450284"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09837-y"},{"key":"ref50","first-page":"1","article-title":"CrossTransformers: Spatially-aware few-shot transfer","author":"doersch","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref46","article-title":"Visual transformers: Token-based image representation and processing for computer vision","author":"wu","year":"2020","journal-title":"arXiv 2006 03677"},{"key":"ref45","article-title":"MViTv2: Improved multiscale vision transformers for classification and detection","author":"li","year":"2021","journal-title":"arXiv 2112 01526"},{"key":"ref48","first-page":"1","article-title":"Stand-alone self-attention in vision models","volume":"32","author":"ramachandran","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00830"},{"key":"ref42","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04167-0_34"},{"key":"ref44","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014491"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3147570"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2335395"},{"key":"ref4","first-page":"1","article-title":"Learning to draw: Emergent communication through sketching","author":"mihai","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref3","first-page":"1","article-title":"Creative sketch generation","author":"ge","year":"2020","journal-title":"Proc Int Conf Learn Representations (ICLR)"},{"key":"ref6","article-title":"Deep learning for free-hand sketch: A survey","author":"xu","year":"2020","journal-title":"arXiv 2001 02600"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01379"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_45"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","first-page":"1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref36","first-page":"14141","article-title":"Sketchformer: Transformer-based representation for sketched structure","author":"ribeiro","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01131"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","first-page":"4605","article-title":"Advanced dropout: A model-free methodology for Bayesian dropout optimization","volume":"44","author":"xie","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref32","first-page":"8230","article-title":"GPCA: A probabilistic framework for Gaussian process embedded channel attention","volume":"44","author":"xie","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929804"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_36"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.10.022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530133"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.12.117"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2018.2884192"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-08706-y"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08158-z"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851974"},{"key":"ref22","first-page":"1","article-title":"Communicating semantic part information in drawings","author":"mukherjee","year":"2019","journal-title":"Proc Annu Conf Cognit Sci Soc (CogSci)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00994"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP56404.2022.10008880"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8516988"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10214525.pdf?arnumber=10214525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T18:26:56Z","timestamp":1693852016000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10214525\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3302521","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}