{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:22:26Z","timestamp":1771953746019,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681146","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"10287-10295","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Bridging the Gap: Sketch-Aware Interpolation Network for High-Quality Animation Sketch Inbetweening"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3205-6397","authenticated-orcid":false,"given":"Jiaming","family":"Shen","sequence":"first","affiliation":[{"name":"The University of Sydney, Darlington, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6891-8059","authenticated-orcid":false,"given":"Kun","family":"Hu","sequence":"additional","affiliation":[{"name":"The University of Sydney, Darlington, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1874-1766","authenticated-orcid":false,"given":"Wei","family":"Bao","sequence":"additional","affiliation":[{"name":"The University of Sydney, Darlington, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Chang Wen","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8043-0312","authenticated-orcid":false,"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Sydney, Darlington, NSW, Australia"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0390-2"},{"key":"e_1_3_2_1_2_1","volume-title":"European Conferfence on Computer Vision","author":"Chen Shuhong","unstructured":"Shuhong Chen and Matthias Zwicker. 2022. Improving the Perceptual Quality of 2D Animation Interpolation. In European Conferfence on Computer Vision. Springer Nature Switzerland, Cham, 271--287."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"e_1_3_2_1_4_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Vision-Based Freezing of Gait Detection with Anatomic Patch Based Representation. In Asian Conference on Computer Vision. Springer International Publishing, Cham, 564--576","author":"Hu Kun","year":"2019","unstructured":"Kun Hu, Zhiyong Wang, Kaylena Ehgoetz Martens, and Simon Lewis. 2019. Vision-Based Freezing of Gait Detection with Anatomic Patch Based Representation. In Asian Conference on Computer Vision. Springer International Publishing, Cham, 564--576."},{"key":"e_1_3_2_1_7_1","volume-title":"Real-Time Intermediate Flow Estimation for Video Frame Interpolation. In European Conference on Computer Vision. Springer Nature Switzerland, Cham, 624--642","author":"Huang Zhewei","year":"2022","unstructured":"Zhewei Huang, Tianyuan Zhang, Wen Heng, Boxin Shi, and Shuchang Zhou. 2022. Real-Time Intermediate Flow Estimation for Video Frame Interpolation. In European Conference on Computer Vision. Springer Nature Switzerland, Cham, 624--642."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00938"},{"key":"e_1_3_2_1_9_1","volume-title":"Computer Vision -- ACCV 2022 Workshops","author":"Kim Hannah Halin","unstructured":"Hannah Halin Kim, Shuzhi Yu, Shuai Yuan, and Carlo Tomasi. 2023. Cross-Attention Transformer for Video Interpolation. In Computer Vision -- ACCV 2022 Workshops. Springer Nature Switzerland, Cham, 325--342."},{"key":"e_1_3_2_1_10_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/508530.508552"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00536"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3049419"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00352"},{"key":"e_1_3_2_1_17_1","volume-title":"Motion Keyframe Interpolation for Any Human Skeleton via Temporally Consistent Point Cloud Sampling and Reconstruction. arXiv preprint arXiv:2405.07444","author":"Mo Clinton","year":"2024","unstructured":"Clinton Mo, Kun Hu, Chengjiang Long, Dong Yuan, and Zhiyong Wang. 2024. Motion Keyframe Interpolation for Any Human Skeleton via Temporally Consistent Point Cloud Sampling and Reconstruction. arXiv preprint arXiv:2405.07444 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803506"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00548"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.37"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01416"},{"key":"e_1_3_2_1_22_1","volume-title":"Medical Image Computing and Computer-Assisted Intervention","author":"Ronneberger Olaf","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention. Springer International Publishing, Cham, 234--241."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01696"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3132703","article-title":"Mastering sketching: adversarial augmentation for structured prediction","volume":"37","author":"Simo-Serra Edgar","year":"2018","unstructured":"Edgar Simo-Serra, Satoshi Iizuka, and Hiroshi Ishikawa. 2018. Mastering sketching: adversarial augmentation for structured prediction. ACM Transactions on Graphics, Vol. 37, 1 (2018), 1--13.","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925972"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00670"},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Neural Information Processing Systems","author":"Siyao Li","year":"2024","unstructured":"Li Siyao, Yuhang Li, Bo Li, Chao Dong, Ziwei Liu, and Chen Change Loy. 2024. AnimeRun: 2D animation visual correspondence from open source 3D movies. In International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '22). Curran Associates Inc., Red Hook, NY, USA, Article 1380, 12 pages."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00652"},{"key":"e_1_3_2_1_30_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_1_31_1","volume-title":"Markus Hagenbuchner, Ah Chung Tsoi, Mohammed Bennamoun, Simon JG Lewis, and Zhiyong Wang.","author":"Sun Renfei","year":"2023","unstructured":"Renfei Sun, Kun Hu, Kaylena A Ehgoetz Martens, Markus Hagenbuchner, Ah Chung Tsoi, Mohammed Bennamoun, Simon JG Lewis, and Zhiyong Wang. 2023. Higher order polynomial transformer for fine-grained freezing of gait detection. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1572614.1572619"},{"key":"e_1_3_2_1_33_1","unstructured":"Frank Thomas Ollie Johnston and Frank Thomas. 1995. The illusion of life: Disney animation. Hyperion New York."},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In International Conference on Neural Information Processing Systems (Long Beach, California, USA) (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 6000--6010."},{"key":"e_1_3_2_1_35_1","volume-title":"Betweenit: An interactive tool for tight inbetweening.","author":"Whited Brian","year":"2010","unstructured":"Brian Whited, Gioacchino Noris, Maryann Simmons, Robert W Sumner, Markus Gross, and Jarek Rossignac. 2010. Betweenit: An interactive tool for tight inbetweening. , Vol. 29, 2 (2010), 605--614."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2657511"},{"key":"e_1_3_2_1_38_1","volume-title":"Ftp-sc: Fuzzy topology preserving stroke correspondence.","author":"Yang Wenwu","year":"2018","unstructured":"Wenwu Yang, Hock-Soon Seah, Quan Chen, Hong-Ze Liew, and Daniel S\u1ef3kora. 2018. Ftp-sc: Fuzzy topology preserving stroke correspondence. , Vol. 37, 8 (2018), 125--135."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681146","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:53Z","timestamp":1750294673000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681146"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":39,"alternative-id":["10.1145\/3664647.3681146","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681146","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}