{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:07:19Z","timestamp":1784308039169,"version":"3.55.0"},"reference-count":42,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers &amp; Graphics"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cag.2026.104647","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T23:06:15Z","timestamp":1780787175000},"page":"104647","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["DistillSkel: Learning pruned skeletons of 2D shapes through progressive knowledge distillation"],"prefix":"10.1016","volume":"138","author":[{"given":"Bincy Antony","family":"Mangottu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anshuman","family":"Mishra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pranav","family":"Raghuram","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dharunpathi","family":"Tamilselvan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramanathan","family":"Muthuganapathy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cag.2026.104647_b1","first-page":"362","article-title":"A transformation for extracting new descriptors of shape","author":"Blum","year":"1967","journal-title":"Model Percept Speech Vis Form"},{"issue":"3","key":"10.1016\/j.cag.2026.104647_b2","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1109\/TPAMI.2007.59","article-title":"Skeleton pruning by contour partitioning with discrete curve evolution","volume":"29","author":"Bai","year":"2007","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.cag.2026.104647_b3","series-title":"Computer graphics forum","article-title":"Variational pruning of medial axes of planar shapes","volume":"vol. 42","author":"Rong","year":"2023"},{"key":"10.1016\/j.cag.2026.104647_b4","doi-asserted-by":"crossref","unstructured":"Demir I, Hahn C, Leonard K, Morin G, Rahbani D, Panotopoulou A, Fondevilla A, Balashova E, Durix B, Kortylewski A. Skelneton 2019: Dataset and challenge on deep learning for geometric shape understanding. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops. 2019.","DOI":"10.1109\/CVPRW.2019.00149"},{"issue":"4","key":"10.1016\/j.cag.2026.104647_b5","doi-asserted-by":"crossref","first-page":"1219","DOI":"10.1007\/s11263-023-01926-3","article-title":"Skeleton ground truth extraction: methodology, annotation tool and benchmarks","volume":"132","author":"Yang","year":"2024","journal-title":"Int J Comput Vis"},{"key":"10.1016\/j.cag.2026.104647_b6","series-title":"Proceedings of the SIGGRAPH Asia 2025 technical communications","isbn-type":"print","doi-asserted-by":"crossref","DOI":"10.1145\/3757376.3771414","article-title":"Convpsnet - a convolution-based single step approach for pruned skeleton from noisy data","author":"Antony","year":"2025","ISBN":"https:\/\/id.crossref.org\/isbn\/9798400721366"},{"key":"10.1016\/j.cag.2026.104647_b7","doi-asserted-by":"crossref","unstructured":"Mirzadeh SI, Farajtabar M, Li A, Levine N, Matsukawa A, Ghasemzadeh H. Improved knowledge distillation via teacher assistant. In: Proceedings of the AAAI conference on artificial intelligence. vol. 34, 2020, p. 5191\u20138.","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"10.1016\/j.cag.2026.104647_b8","series-title":"On compressing u-net using knowledge distillation","author":"Mangalam","year":"2018"},{"issue":"2","key":"10.1016\/j.cag.2026.104647_b9","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1111\/cgf.12865","article-title":"3D skeletons: A state-of-the-art report","volume":"35","author":"Tagliasacchi","year":"2016","journal-title":"Comput Graph Forum"},{"key":"10.1016\/j.cag.2026.104647_b10","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2015.04.006","article-title":"A survey on skeletonization algorithms and their applications","volume":"76","author":"Saha","year":"2016","journal-title":"Pattern Recognit Lett"},{"issue":"3","key":"10.1016\/j.cag.2026.104647_b11","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1145\/357994.358023","article-title":"A fast parallel algorithm for thinning digital patterns","volume":"27","author":"Zhang","year":"1984","journal-title":"Commun ACM"},{"issue":"6","key":"10.1016\/j.cag.2026.104647_b12","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1006\/cgip.1994.1042","article-title":"Building skeleton models via 3-D medial surface axis thinning algorithms","volume":"56","author":"Lee","year":"1994","journal-title":"CVGIP, Graph Models Image Process"},{"issue":"7","key":"10.1016\/j.cag.2026.104647_b13","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1016\/S0010-4485(02)00085-4","article-title":"Constructing medial axis transform of planar domains with curved boundaries","volume":"35","author":"Ramanathan","year":"2003","journal-title":"Comput.-Aided Des"},{"issue":"5","key":"10.1016\/j.cag.2026.104647_b14","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/0262-8856(95)99723-E","article-title":"Skeletonization using an extended euclidean distance transform","volume":"13","author":"Wright","year":"1995","journal-title":"Image Vis Comput"},{"issue":"3","key":"10.1016\/j.cag.2026.104647_b15","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/0031-3203(94)00104-T","article-title":"A skeletonization algorithm by maxima tracking on euclidean distance transform","volume":"28","author":"Shih","year":"1995","journal-title":"Pattern Recognit"},{"issue":"3","key":"10.1016\/j.cag.2026.104647_b16","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1145\/116873.116880","article-title":"Voronoi diagrams\u2014a survey of a fundamental geometric data structure","volume":"23","author":"Aurenhammer","year":"1991","journal-title":"ACM Comput Surv"},{"key":"10.1016\/j.cag.2026.104647_b17","series-title":"ICCV","first-page":"222","article-title":"Shock graphs and shape matching","author":"Siddiqi","year":"1999"},{"key":"10.1016\/j.cag.2026.104647_b18","doi-asserted-by":"crossref","unstructured":"Giesen J, Miklos B, Pauly M, Wormser C. The scale axis transform. In: Proceedings of the twenty-fifth annual symposium on computational geometry. 2009, p. 106\u201315.","DOI":"10.1145\/1542362.1542388"},{"issue":"4","key":"10.1016\/j.cag.2026.104647_b19","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/j.gmod.2005.01.002","article-title":"The \u201c\u03bb-medial axis\u201d","volume":"67","author":"Chazal","year":"2005","journal-title":"Graph Model"},{"key":"10.1016\/j.cag.2026.104647_b20","series-title":"Discrete geometry for computer imagery: 21st IAPR international conference, DGCI 2019, marne-la-vall\u00e9e, France, March 26\u201328, 2019, proceedings 21","first-page":"343","article-title":"The propagated skeleton: A robust detail-preserving approach","author":"Durix","year":"2019"},{"key":"10.1016\/j.cag.2026.104647_b21","series-title":"CVPR","article-title":"Deepflux for skeletons in the wild","author":"Xu","year":"2019"},{"issue":"11","key":"10.1016\/j.cag.2026.104647_b22","doi-asserted-by":"crossref","first-page":"5298","DOI":"10.1109\/TIP.2017.2735182","article-title":"Deepskeleton: Learning multi-task scale-associated deep side outputs for object skeleton extraction in natural images","volume":"26","author":"Shen","year":"2017","journal-title":"IEEE Trans Image Process"},{"key":"10.1016\/j.cag.2026.104647_b23","doi-asserted-by":"crossref","unstructured":"Nathan S, Kansal P. Skeletonnet: Shape pixel to skeleton pixel. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops. 2019.","DOI":"10.1109\/CVPRW.2019.00156"},{"key":"10.1016\/j.cag.2026.104647_b24","doi-asserted-by":"crossref","unstructured":"Panichev O, Voloshyna A. U-net based convolutional neural network for skeleton extraction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops. 2019.","DOI":"10.1109\/CVPRW.2019.00157"},{"key":"10.1016\/j.cag.2026.104647_b25","series-title":"Medical image computing and computer-assisted intervention \u2013 MICCAI 2015","isbn-type":"print","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015","ISBN":"https:\/\/id.crossref.org\/isbn\/9783319245744"},{"key":"10.1016\/j.cag.2026.104647_b26","series-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"issue":"12","key":"10.1016\/j.cag.2026.104647_b27","doi-asserted-by":"crossref","first-page":"8766","DOI":"10.1109\/TPAMI.2020.3013679","article-title":"A topological loss function for deep-learning based image segmentation using persistent homology","volume":"44","author":"Clough","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.cag.2026.104647_b28","article-title":"Topology-preserving deep image segmentation","volume":"32","author":"Hu","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.cag.2026.104647_b29","series-title":"European conference on computer vision","first-page":"41","article-title":"Learning-based symmetry detection in natural images","author":"Tsogkas","year":"2012"},{"key":"10.1016\/j.cag.2026.104647_b30","doi-asserted-by":"crossref","DOI":"10.7717\/peerj.453","article-title":"Scikit-image: image processing in python","volume":"2","author":"Van der Walt","year":"2014","journal-title":"PeerJ"},{"issue":"9","key":"10.1016\/j.cag.2026.104647_b31","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1109\/34.161346","article-title":"Thinning methodologies-a comprehensive survey","volume":"14","author":"Lam","year":"1992","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"11","key":"10.1016\/j.cag.2026.104647_b32","doi-asserted-by":"crossref","first-page":"1496","DOI":"10.1016\/j.cad.2011.09.002","article-title":"Extended grassfire transform on medial axes of 2d shapes","volume":"43","author":"Liu","year":"2011","journal-title":"Comput.-Aided Des"},{"key":"10.1016\/j.cag.2026.104647_b33","series-title":"Discrete voronoi skeletons","author":"Ogniewicz","year":"1992"},{"key":"10.1016\/j.cag.2026.104647_b34","doi-asserted-by":"crossref","unstructured":"Liu Z, Mao H, Wu C-Y, Feichtenhofer C, Darrell T, Xie S. A convnet for the 2020s. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2022, p. 11976\u201386.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"10.1016\/j.cag.2026.104647_b35","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, p. 770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.cag.2026.104647_b36","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.cag.2026.104647_b37","series-title":"Dinov3","author":"Sim\u00e9oni","year":"2025"},{"key":"10.1016\/j.cag.2026.104647_b38","series-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"10.1016\/j.cag.2026.104647_b39","series-title":"Squeezenet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size","author":"Iandola","year":"2016"},{"issue":"1","key":"10.1016\/j.cag.2026.104647_b40","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/JPROC.2022.3226481","article-title":"Efficient acceleration of deep learning inference on resource-constrained edge devices: A review","volume":"111","author":"Shuvo","year":"2022","journal-title":"Proc IEEE"},{"key":"10.1016\/j.cag.2026.104647_b41","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C. Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, p. 4510\u201320.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10.1016\/j.cag.2026.104647_b42","doi-asserted-by":"crossref","unstructured":"Ma N, Zhang X, Zheng H-T, Sun J. Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European conference on computer vision. ECCV, 2018, p. 116\u201331.","DOI":"10.1007\/978-3-030-01264-9_8"}],"container-title":["Computers &amp; Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0097849326001184?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0097849326001184?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:31:47Z","timestamp":1784305907000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0097849326001184"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":42,"alternative-id":["S0097849326001184"],"URL":"https:\/\/doi.org\/10.1016\/j.cag.2026.104647","relation":{},"ISSN":["0097-8493"],"issn-type":[{"value":"0097-8493","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DistillSkel: Learning pruned skeletons of 2D shapes through progressive knowledge distillation","name":"articletitle","label":"Article Title"},{"value":"Computers & Graphics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cag.2026.104647","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104647"}}