{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T03:03:05Z","timestamp":1770346985466,"version":"3.49.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T00:00:00Z","timestamp":1698364800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T00:00:00Z","timestamp":1698364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"NSF","award":["IIS-1814745"],"award-info":[{"award-number":["IIS-1814745"]}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61733002"],"award-info":[{"award-number":["61733002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61876030"],"award-info":[{"award-number":["61876030"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272083"],"award-info":[{"award-number":["62272083"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s00371-023-03123-2","type":"journal-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T17:01:33Z","timestamp":1698426093000},"page":"5575-5588","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A rotation robust shape transformer for cartoon character recognition"],"prefix":"10.1007","volume":"40","author":[{"given":"Qi","family":"Jia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longin Jan","family":"Latecki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"issue":"5","key":"3123_CR1","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1109\/TSMCB.2012.2192108","volume":"42","author":"J Yu","year":"2012","unstructured":"Yu, J., Liu, D., Tao, D., Seah, H.S.: On combining multiple features for cartoon character retrieval and clip synthesis. IEEE Trans. Syst. Man Cybern. B (Cybern.) 42(5), 1413\u20131427 (2012)","journal-title":"IEEE Trans. Syst. Man Cybern. B (Cybern.)"},{"key":"3123_CR2","unstructured":"Rios, E.A., Cheng, W.-H., Lai, B.-C.: Daf: re: A challenging, crowd-sourced, large-scale, long-tailed dataset for anime character recognition. arXiv preprint arXiv:2101.08674 (2021)"},{"key":"3123_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"issue":"18","key":"3123_CR4","doi-asserted-by":"publisher","first-page":"4705","DOI":"10.1523\/JNEUROSCI.3622-16.2017","volume":"37","author":"X Wang","year":"2017","unstructured":"Wang, X., et al.: Domain selectivity in the parahippocampal gyrus is predicted by the same structural connectivity patterns in blind and sighted individuals. J. Neurosci. 37(18), 4705\u20134716 (2017)","journal-title":"J. Neurosci."},{"key":"3123_CR5","unstructured":"Geirhos, R., et al.: ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231 (2018)"},{"key":"3123_CR6","first-page":"831","volume":"13","author":"S Belongie","year":"2001","unstructured":"Belongie, S., Malik, J., Puzicha, J.: Shape context: a new descriptor for shape matching and object recognition. Adv. Neural Inf. Process. Syst. 13, 831\u2013837 (2001)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3123_CR7","doi-asserted-by":"crossref","unstructured":"Shekar, B., Pilar, B., Kittler, J.: An unification of inner distance shape context and local binary pattern for shape representation and classification. In: Proceedings of the 2nd International Conference on Perception and Machine Intelligence, pp. 46\u201355 (2015)","DOI":"10.1145\/2708463.2709062"},{"key":"3123_CR8","doi-asserted-by":"publisher","first-page":"2116","DOI":"10.1016\/j.patcog.2013.12.008","volume":"47","author":"X Wang","year":"2014","unstructured":"Wang, X., Feng, B., Bai, X., Liu, W., Latecki, L.J.: Bag of contour fragments for robust shape classification. Pattern Recognit. 47, 2116\u20132125 (2014)","journal-title":"Pattern Recognit."},{"key":"3123_CR9","first-page":"1106","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1106\u20131114 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3123_CR10","doi-asserted-by":"crossref","unstructured":"Li, Y., Lao, L., Cui, Z., Shan, S., Yang, J.: Graph jigsaw learning for cartoon face recognition. arXiv:2107.06532 (2021)","DOI":"10.1109\/TIP.2022.3177952"},{"key":"3123_CR11","unstructured":"Ritter, S., Barrett, D.G., Santoro, A., Botvinick, M.M.: Cognitive psychology for deep neural networks: a shape bias case study. In: International conference on machine learning, pp. 2940\u20132949 (2017)"},{"key":"3123_CR12","first-page":"3856","volume":"30","author":"S Sabour","year":"2017","unstructured":"Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. Adv. Neural Inf. Process. Syst. 30, 3856\u20133866 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3123_CR13","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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3123_CR14","doi-asserted-by":"crossref","unstructured":"Haseyama, M., Matsumura, A.: A cartoon character retrieval system including trainable scheme. In: Proceedings 2003 International Conference on Image Processing (Cat. No. 03CH37429), vol.\u00a03, pp. III\u201337 (2003)","DOI":"10.1109\/ICIP.2003.1247175"},{"key":"3123_CR15","doi-asserted-by":"publisher","first-page":"1118","DOI":"10.1109\/TIP.2013.2286330","volume":"23","author":"R Hu","year":"2014","unstructured":"Hu, R., Jia, W., Ling, H., Zhao, Y., Gui, J.: Angular pattern and binary angular pattern for shape retrieval. IEEE Trans. Image Process. 23, 1118\u20131127 (2014)","journal-title":"IEEE Trans. Image Process."},{"key":"3123_CR16","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.patrec.2011.09.042","volume":"33","author":"J Wang","year":"2012","unstructured":"Wang, J., Bai, X., You, X., Liu, W., Latecki, L.J.: Shape matching and classification using height functions. Pattern Recognit. Lett. 33, 134\u2013143 (2012)","journal-title":"Pattern Recognit. Lett."},{"key":"3123_CR17","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1016\/j.patcog.2015.11.003","volume":"52","author":"Q Jia","year":"2016","unstructured":"Jia, Q., et al.: Hierarchical projective invariant contexts for shape recognition. Pattern Recognit. 52, 358\u2013374 (2016)","journal-title":"Pattern Recognit."},{"key":"3123_CR18","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.patcog.2017.03.007","volume":"68","author":"S Chen","year":"2017","unstructured":"Chen, S., Xia, R., Zhao, J., Chen, Y., Hu, M.: A hybrid method for ellipse detection in industrial images. Pattern Recognit. 68, 82\u201398 (2017)","journal-title":"Pattern Recognit."},{"key":"3123_CR19","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s11263-016-0971-9","volume":"124","author":"B Micusik","year":"2017","unstructured":"Micusik, B., Wildenauer, H.: Structure from motion with line segments under relaxed endpoint constraints. Int. J. Comput. Vis. 124, 65\u201379 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"3123_CR20","doi-asserted-by":"crossref","unstructured":"Yu, Q., et al.: Sketch me that shoe. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 799\u2013807 (2016)","DOI":"10.1109\/CVPR.2016.93"},{"key":"3123_CR21","doi-asserted-by":"crossref","unstructured":"Sarvadevabhatla, R.K., Kundu, J., Babu, R.V.: Enabling my robot to play pictionary: recurrent neural networks for sketch recognition. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 247\u2013251 (2016)","DOI":"10.1145\/2964284.2967220"},{"key":"3123_CR22","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/s11263-016-0932-3","volume":"122","author":"Q Yu","year":"2017","unstructured":"Yu, Q., et al.: Sketch-a-net: a deep neural network that beats humans. Int. J. Comput. Vis. 122, 411\u2013425 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"3123_CR23","doi-asserted-by":"crossref","unstructured":"Wang, T.-Q., Liu, C.-L.: Fully convolutional network based skeletonization for handwritten Chinese characters. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2540\u20132547 (2018)","DOI":"10.1609\/aaai.v32i1.11868"},{"key":"3123_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2017.05.015","volume":"71","author":"SH Lee","year":"2017","unstructured":"Lee, S.H., Chan, C.S., Mayo, S.J., Remagnino, P.: How deep learning extracts and learns leaf features for plant classification. Pattern Recognit. 71, 1\u201313 (2017)","journal-title":"Pattern Recognit."},{"key":"3123_CR25","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: Deep learning on point sets for 3d classification and segmentation. In: CVPR, pp. 652\u2013660 (2017)"},{"key":"3123_CR26","unstructured":"Sutskever, I., Martens, J., Hinton, G.E.: Generating text with recurrent neural networks. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 1017\u20131024 (2011)"},{"key":"3123_CR27","doi-asserted-by":"crossref","unstructured":"Xu, P., et\u00a0al.: SketchMate: deep hashing for million-scale human sketch retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8090\u20138098 (2018)","DOI":"10.1109\/CVPR.2018.00844"},{"key":"3123_CR28","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"3123_CR29","doi-asserted-by":"crossref","unstructured":"Miyagi, R., Aono, M.: Sliced voxel representations with LSTM and CNN for 3D shape recognition. In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 320\u2013323. IEEE (2017)","DOI":"10.1109\/APSIPA.2017.8282044"},{"key":"3123_CR30","doi-asserted-by":"crossref","unstructured":"Dai, G., Xie, J., Fang, Y.: Siamese CNN-BiLSTM architecture for 3D shape representation learning. In: IJCAI, pp. 670\u2013676 (2018)","DOI":"10.24963\/ijcai.2018\/93"},{"key":"3123_CR31","doi-asserted-by":"crossref","unstructured":"Carion, N., et\u00a0al.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3123_CR32","doi-asserted-by":"crossref","unstructured":"Touvron, H., et al.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"3123_CR33","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A. He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"3123_CR34","unstructured":"Gehring, J., Auli, M., Grangier, D., Yarats, D., Dauphin, Y.N.: Convolutional sequence to sequence learning. In: International Conference on Machine Learning, pp. 1243\u20131252. PMLR (2017)"},{"key":"3123_CR35","volume-title":"NIPS","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Guyon, I., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) NIPS, vol. 30. Curran Associates Inc., Red Hook (2017)"},{"key":"3123_CR36","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. In: NAACL (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"3123_CR37","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.: Attentive language models beyond a fixed-length context, Transformer-xl. arXiv:1901.02860 (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"3123_CR38","unstructured":"Chu, X., Zhang, B., Tian, Z., Wei, X., Xia, H.: Do we really need explicit position encodings for vision transformers. arXiv preprint arXiv:2102.10882 (2021)"},{"key":"3123_CR39","doi-asserted-by":"crossref","unstructured":"Srinivas, A., et\u00a0al.: Bottleneck transformers for visual recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16519\u201316529 (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"3123_CR40","unstructured":"S\u00f6derkvist, O.: Computer vision classification of leaves from Swedish trees. Master\u2019s thesis (2001)"},{"key":"3123_CR41","doi-asserted-by":"crossref","unstructured":"Bai, X., Liu, W., Tu, Z.: Integrating contour and skeleton for shape classification. In: 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, pp. 360\u2013367 (2009)","DOI":"10.1109\/ICCVW.2009.5457679"},{"key":"3123_CR42","unstructured":"Li, F.-F., Andreetto, M., Ranzato, M.A.: Caltech101 image dataset. http:\/\/www.vision.caltech.edu\/Image_Datasets\/Caltech101\/ (2003)"},{"key":"3123_CR43","unstructured":"Simard, P.Y., Steinkraus, D., Platt, J.C., et\u00a0al.: Best practices for convolutional neural networks applied to visual document analysis. In: Icdar, vol. 3 (2003)"},{"key":"3123_CR44","doi-asserted-by":"publisher","first-page":"3222","DOI":"10.1016\/j.patcog.2012.02.020","volume":"45","author":"R-X Hu","year":"2012","unstructured":"Hu, R.-X., Jia, W., Zhao, Y., Gui, J.: Perceptually motivated morphological strategies for shape retrieval. Pattern Recognit. 45, 3222\u20133230 (2012)","journal-title":"Pattern Recognit."},{"key":"3123_CR45","doi-asserted-by":"publisher","first-page":"7823","DOI":"10.1007\/s11042-016-3422-2","volume":"76","author":"Y Sirin","year":"2017","unstructured":"Sirin, Y., Demirci, M.F.: 2D and 3D shape retrieval using skeleton filling rate. Multimed. Tools Appl. 76, 7823\u20137848 (2017)","journal-title":"Multimed. Tools Appl."},{"key":"3123_CR46","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.patrec.2018.02.024","volume":"106","author":"W Shen","year":"2018","unstructured":"Shen, W., Du, C., Jiang, Y., Zeng, D., Zhang, Z.: Bag of shape features with a learned pooling function for shape recognition. Pattern Recognit. Lett. 106, 33\u201340 (2018)","journal-title":"Pattern Recognit. Lett."},{"key":"3123_CR47","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1109\/TPAMI.2007.41","volume":"29","author":"H Ling","year":"2007","unstructured":"Ling, H., Jacobs, D.W.: Shape classification using the inner-distance. IEEE Trans. Pattern Anal. Mach. Intell. 29, 286\u2013299 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03123-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-03123-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03123-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T23:27:31Z","timestamp":1730417251000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-03123-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,27]]},"references-count":47,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["3123"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-03123-2","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,27]]},"assertion":[{"value":"23 September 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service and\/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled, \u201cA Rotation Robust Shape Transformer for Cartoon Character Recognition.\u201d","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}