{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T14:55:16Z","timestamp":1790693716731,"version":"4.1.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2021,6,30]],"date-time":"2021-06-30T00:00:00Z","timestamp":1625011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research & Development Program of China","award":["2018YFE0100900"],"award-info":[{"award-number":["2018YFE0100900"]}]},{"name":"Research Grants Council of the Hong Kong Special Administrative Region, China","award":["CityU 11212119, and CityU 11237116"],"award-info":[{"award-number":["CityU 11212119, and CityU 11237116"]}]},{"DOI":"10.13039\/100007567","name":"City University of Hong Kong","doi-asserted-by":"crossref","award":["7005176"],"award-info":[{"award-number":["7005176"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Centre for Applied Computing and Interactive Media (ACIM) of School of Creative Media, CityU"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2021,6,30]]},"abstract":"<jats:p>\n                    We introduce\n                    <jats:italic>SketchGNN<\/jats:italic>\n                    , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our\n                    <jats:italic>SketchGNN<\/jats:italic>\n                    uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level.\n                    <jats:italic>SketchGNN<\/jats:italic>\n                    significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.\n                  <\/jats:p>","DOI":"10.1145\/3450284","type":"journal-article","created":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T14:35:55Z","timestamp":1627828555000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":69,"title":["SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks"],"prefix":"10.1145","volume":"40","author":[{"given":"Lumin","family":"Yang","sequence":"first","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajie","family":"Zhuang","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbo","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Creative Media, City University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangzhi","family":"Wei","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youyi","family":"Zheng","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University, Hangzhou"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,8]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1209"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"e_1_2_2_3_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917)","author":"Charles R. Qi","unstructured":"R. Qi Charles , Su Hao , Kaichun Mo , and Leonidas J. Guibas . 2017. PointNet: Deep learning on point sets for 3D classification and segmentation . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917) . 77\u201385. R. Qi Charles, Su Hao, Kaichun Mo, and Leonidas J. Guibas. 2017. PointNet: Deep learning on point sets for 3D classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201917). 77\u201385."},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157527"},{"key":"e_1_2_2_6_1","volume-title":"A flexible framework for online document segmentation by pairwise stroke distance learning.Pattern Recog. 48, 4","author":"Delaye Adrien","year":"2015","unstructured":"Adrien Delaye and Kibok Lee . 2015. A flexible framework for online document segmentation by pairwise stroke distance learning.Pattern Recog. 48, 4 ( 2015 ), 1197\u20131210. Adrien Delaye and Kibok Lee. 2015. A flexible framework for online document segmentation by pairwise stroke distance learning.Pattern Recog. 48, 4 (2015), 1197\u20131210."},{"key":"e_1_2_2_7_1","volume-title":"Peucker","author":"Douglas David H.","year":"1973","unstructured":"David H. Douglas and Thomas K . Peucker . 1973 . Algorithms for the Reduction of the Number of Points Required to Represent a Line or Its Caricature. University of Toronto Press . David H. Douglas and Thomas K. Peucker. 1973. Algorithms for the Reduction of the Number of Points Required to Represent a Line or Its Caricature. University of Toronto Press."},{"key":"e_1_2_2_8_1","article-title":"How do humans sketch objects?ACM","volume":"31","author":"Eitz Mathias","year":"2012","unstructured":"Mathias Eitz , James Hays , and Marc Alexa . 2012 a. How do humans sketch objects?ACM Trans. Graph. (Proc. SIGGRAPH) 31 , 4 (2012), 44:1\u201344:10. Mathias Eitz, James Hays, and Marc Alexa. 2012a. How do humans sketch objects?ACM Trans. Graph. (Proc. SIGGRAPH) 31, 4 (2012), 44:1\u201344:10.","journal-title":"Trans. Graph. (Proc. SIGGRAPH)"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185527"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2005.05.007"},{"key":"e_1_2_2_11_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR\u201918)","author":"Ha David","year":"2017","unstructured":"David Ha and Douglas Eck . 2017 . A neural representation of sketch drawings . In Proceedings of the 6th International Conference on Learning Representations (ICLR\u201918) . David Ha and Douglas Eck. 2017. A neural representation of sketch drawings. In Proceedings of the 6th International Conference on Learning Representations (ICLR\u201918)."},{"key":"e_1_2_2_12_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems. 1025\u20131035","author":"Hamilton William L.","year":"2017","unstructured":"William L. Hamilton , Rex Ying , and Jure Leskovec . 2017 . Inductive representation learning on large graphs . In Proceedings of the 31st International Conference on Neural Information Processing Systems. 1025\u20131035 . William L. Hamilton, Rex Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 1025\u20131035."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661280"},{"key":"e_1_2_2_14_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Thomas","unstructured":"Thomas N. Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks . In Proceedings of the International Conference on Learning Representations. Thomas N. Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00936"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_36"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2895155"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2018.2884192"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3005358.3005372"},{"key":"e_1_2_2_20_1","first-page":"1","article-title":"Sketch-R2CNN: An RNN-rasterization-CNN architecture for vector sketch recognition","volume":"99","author":"Li Lei","year":"2020","unstructured":"Lei Li , Changqing Zou , Youyi Zheng , Qingkun Su , and Chiew Lan Tai . 2020 . Sketch-R2CNN: An RNN-rasterization-CNN architecture for vector sketch recognition . IEEE Trans. Visualiz. Comput. Graph. PP , 99 (2020), 1 \u2013 1 . Lei Li, Changqing Zou, Youyi Zheng, Qingkun Su, and Chiew Lan Tai. 2020. Sketch-R2CNN: An RNN-rasterization-CNN architecture for vector sketch recognition. IEEE Trans. Visualiz. Comput. Graph. PP, 99 (2020), 1\u20131.","journal-title":"IEEE Trans. Visualiz. Comput. Graph. PP"},{"key":"e_1_2_2_21_1","volume-title":"Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 3538\u20133545","author":"Li Qimai","year":"2018","unstructured":"Qimai Li , Zhichao Han , and Xiao-Ming Wu . 2018 a. Deeper insights into graph convolutional networks for semi-supervised learning . In Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 3538\u20133545 . Qimai Li, Zhichao Han, and Xiao-Ming Wu. 2018a. Deeper insights into graph convolutional networks for semi-supervised learning. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 3538\u20133545."},{"key":"e_1_2_2_22_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems 30","author":"Monti Federico","year":"2017","unstructured":"Federico Monti , Michael Bronstein , and Xavier Bresson . 2017 . Geometric matrix completion with recurrent multi-graph neural networks . In Proceedings of the Advances in Neural Information Processing Systems 30 . 3697\u20133707. Federico Monti, Michael Bronstein, and Xavier Bresson. 2017. Geometric matrix completion with recurrent multi-graph neural networks. In Proceedings of the Advances in Neural Information Processing Systems 30. 3697\u20133707."},{"key":"e_1_2_2_23_1","first-page":"8","article-title":"Smart scribbles for sketch segmentation","volume":"31","author":"Noris Gioacchino","year":"2012","unstructured":"Gioacchino Noris , Daniel Sykora , A. Shamir , Stelian Coros , Brian Whited , Maryann Simmons , Alexander Hornung , Markus H. Gross , and Robert W. Sumner . 2012 . Smart scribbles for sketch segmentation . Comput. Graph. For. 31 , 8 (Jan. 2012). Gioacchino Noris, Daniel Sykora, A. Shamir, Stelian Coros, Brian Whited, Maryann Simmons, Alexander Hornung, Markus H. Gross, and Robert W. Sumner. 2012. Smart scribbles for sketch segmentation. Comput. Graph. For. 31, 8 (Jan. 2012).","journal-title":"Comput. Graph. For."},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807442.2807455"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738056"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.03.023"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298795"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929804"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925954"},{"key":"e_1_2_2_30_1","volume-title":"Proceedings of the 25th ACM International Conference on Multimedia. 10\u201318","author":"Sarvadevabhatla Ravi Kiran","unstructured":"Ravi Kiran Sarvadevabhatla , Isht Dwivedi , Abhijat Biswas , Sahil Manocha , and R. Venkatesh Babu . 2017. SketchParse: Towards rich descriptions for poorly drawn sketches using multi-task hierarchical deep networks . In Proceedings of the 25th ACM International Conference on Multimedia. 10\u201318 . Ravi Kiran Sarvadevabhatla, Isht Dwivedi, Abhijat Biswas, Sahil Manocha, and R. Venkatesh Babu. 2017. SketchParse: Towards rich descriptions for poorly drawn sketches using multi-task hierarchical deep networks. In Proceedings of the 25th ACM International Conference on Multimedia. 10\u201318."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2898351"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"e_1_2_2_34_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201918)","author":"Song Jifei","unstructured":"Jifei Song , Kaiyue Pang , Yi-Zhe Song , Tao Xiang , and Timothy M. Hospedales . 2018. Learning to sketch with shortcut cycle consistency . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201918) . 801\u2013810. Jifei Song, Kaiyue Pang, Yi-Zhe Song, Tao Xiang, and Timothy M. Hospedales. 2018. Learning to sketch with shortcut cycle consistency. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201918). 801\u2013810."},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557109"},{"key":"e_1_2_2_36_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Valsesia Diego","year":"2019","unstructured":"Diego Valsesia , Giulia Fracastoro , and Enrico Magli . 2019 . Learning localized generative models for 3D point clouds via graph convolution . In Proceedings of the International Conference on Learning Representations. Diego Valsesia, Giulia Fracastoro, and Enrico Magli. 2019. Learning localized generative models for 3D point clouds via graph convolution. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"e_1_2_2_38_1","first-page":"71","article-title":"Laws of organization in perceptual forms","volume":"4","author":"Wertheimer Max","year":"1938","unstructured":"Max Wertheimer . 1938 . Laws of organization in perceptual forms . Psychol. Forsch. 4 (1938), 71 \u2013 88 . Max Wertheimer. 1938. Laws of organization in perceptual forms. Psychol. Forsch. 4 (1938), 71\u201388.","journal-title":"Psychol. Forsch."},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8516988"},{"key":"e_1_2_2_40_1","volume-title":"Yu","author":"Wu Zonghan","year":"2019","unstructured":"Zonghan Wu , Shirui Pan , Fengwen Chen , Guodong Long , Chengqi Zhang , and Philip S . Yu . 2019 . A comprehensive survey on graph neural networks. CoRR abs\/1901.00596 (2019). Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and Philip S. Yu. 2019. A comprehensive survey on graph neural networks. CoRR abs\/1901.00596 (2019)."},{"key":"e_1_2_2_41_1","volume-title":"Sketch-to-design: Context-based part assembly. Comput. Graph. For. 32 (11","author":"Xie Xiaohua","year":"2013","unstructured":"Xiaohua Xie , Kai Xu , Niloy Mitra , Daniel Cohen-Or , Wenyong Gong , Qi Su , and Baoquan Chen . 2013 . Sketch-to-design: Context-based part assembly. Comput. Graph. For. 32 (11 2013), 233\u2013245. Retrieved from https:\/\/doi.org\/10.1111\/cgf.12200. Xiaohua Xie, Kai Xu, Niloy Mitra, Daniel Cohen-Or, Wenyong Gong, Qi Su, and Baoquan Chen. 2013. Sketch-to-design: Context-based part assembly. Comput. Graph. For. 32 (11 2013), 233\u2013245. Retrieved from https:\/\/doi.org\/10.1111\/cgf.12200."},{"key":"e_1_2_2_42_1","volume-title":"How powerful are graph neural networks?arXiv preprint arXiv:1810.00826","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu , Weihua Hu , Jure Leskovec , and Stefanie Jegelka . 2018a. How powerful are graph neural networks?arXiv preprint arXiv:1810.00826 ( 2018 ). Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018a. How powerful are graph neural networks?arXiv preprint arXiv:1810.00826 (2018)."},{"key":"e_1_2_2_43_1","first-page":"1","article-title":"Sketch2Scene: Sketch-based co-retrieval and co-placement of 3D models","volume":"32","author":"Xu Kun","year":"2013","unstructured":"Kun Xu , Chen Kang , Hongbo Fu , Wei-Lun Sun , and Shi-Min Hu . 2013 . Sketch2Scene: Sketch-based co-retrieval and co-placement of 3D models . ACM Trans. Graph. (Proc. SIGGRAPH) 32 , 4 (2013), 1 \u2013 15 . Kun Xu, Chen Kang, Hongbo Fu, Wei-Lun Sun, and Shi-Min Hu. 2013. Sketch2Scene: Sketch-based co-retrieval and co-placement of 3D models. ACM Trans. Graph. (Proc. SIGGRAPH) 32, 4 (2013), 1\u201315.","journal-title":"ACM Trans. Graph. (Proc. SIGGRAPH)"},{"key":"e_1_2_2_44_1","volume-title":"Ken Ichi Kawarabayashi, and Stefanie Jegelka","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu , Chengtao Li , Yonglong Tian , Tomohiro Sonobe , Ken Ichi Kawarabayashi, and Stefanie Jegelka . 2018 b. Representation learning on graphs with jumping knowledge networks. Retrieved from: https:\/\/arxiv.org\/abs\/1806.03536. Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken Ichi Kawarabayashi, and Stefanie Jegelka. 2018b. Representation learning on graphs with jumping knowledge networks. Retrieved from: https:\/\/arxiv.org\/abs\/1806.03536."},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08158-z"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3450284","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3450284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:00Z","timestamp":1750178820000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3450284"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,30]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,6,30]]}},"alternative-id":["10.1145\/3450284"],"URL":"https:\/\/doi.org\/10.1145\/3450284","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,30]]},"assertion":[{"value":"2020-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}