{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:40:52Z","timestamp":1755826852104,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["21ZR1406600"],"award-info":[{"award-number":["21ZR1406600"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSFC","award":["U2001209, 61902076"],"award-info":[{"award-number":["U2001209, 61902076"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611752","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"1975-1986","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-Guided Spatial Pruning Architecture for Efficient Frame Interpolation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5866-6847","authenticated-orcid":false,"given":"Ri","family":"Cheng","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4646-5052","authenticated-orcid":false,"given":"Xuhao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9598-3043","authenticated-orcid":false,"given":"Ruian","family":"He","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7283-2314","authenticated-orcid":false,"given":"Shili","family":"Zhou","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7677-4772","authenticated-orcid":false,"given":"Weimin","family":"Tan","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0256-9682","authenticated-orcid":false,"given":"Bo","family":"Yan","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0390-2"},{"volume-title":"2007 11th IEEE International Conference on Computer Vision. IEEE Computer Society","author":"Baker S.","key":"e_1_3_2_2_3_1","unstructured":"S. Baker, R. Szeliski, M. J. Black, D. Scharstein, J. Lewis, and S. Roth. 2007. A Database and Evaluation Methodology for Optical Flow. In 2007 11th IEEE International Conference on Computer Vision. IEEE Computer Society, Los Alamitos, CA, USA, 1--8."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00382"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2941941"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"536","author":"Bolukbasi Tolga","year":"2017","unstructured":"Tolga Bolukbasi, Joseph Wang, Ofer Dekel, and Venkatesh Saligrama. 2017. Adaptive Neural Networks for Efficient Inference. In Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 70). 527--536."},{"key":"e_1_3_2_2_7_1","volume-title":"Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction. arXiv e-prints (March","author":"Cai Yuanhao","year":"2022","unstructured":"Yuanhao Cai, Jing Lin, Xiaowan Hu, Haoqian Wang, Xin Yuan, Yulun Zhang, Radu Timofte, and Luc Van Gool. 2022. Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction. arXiv e-prints (March 2022)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6634"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3100714"},{"key":"e_1_3_2_2_11_1","first-page":"107","article-title":"All at Once","volume":"2020","author":"Chi Zhixiang","year":"2020","unstructured":"Zhixiang Chi, Rasoul Mohammadi Nasiri, Zheng Liu, Juwei Lu, Jin Tang, and Konstantinos N. Plataniotis. 2020. All at Once: Temporally Adaptive Multi-frame Interpolation with Advanced Motion Modeling. In Computer Vision - ECCV 2020. 107--123.","journal-title":"Temporally Adaptive Multi-frame Interpolation with Advanced Motion Modeling. In Computer Vision - ECCV"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6693"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01358"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00791"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_9"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00272"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"e_1_3_2_2_18_1","volume-title":"NIPS Deep Learning and Representation Learning Workshop. http:\/\/arxiv.org\/abs\/1503","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. In NIPS Deep Learning and Representation Learning Workshop. http:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096540"},{"key":"e_1_3_2_2_20_1","unstructured":"Gao Huang Danlu Chen Tianhong Li Felix Wu Laurens van der Maaten and Kilian Q Weinberger. 2018. Multi-scale dense networks for resource efficient image classification. ICLR."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_36"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00938"},{"key":"e_1_3_2_2_23_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Kendall Alex","year":"2017","unstructured":"Alex Kendall and Yarin Gal. 2017. What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?. In Advances in Neural Information Processing Systems, Vol. 30. Curran Associates, Inc."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6788"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00201"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01184"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00536"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01211"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"e_1_3_2_2_30_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In ICLR."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00352"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12276"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Mullapudi Ravi Teja","year":"2018","unstructured":"Ravi Teja Mullapudi, William R. Mark, Noam Shazeer, and Kayvon Fatahalian. 2018. HydraNets: Specialized Dynamic Architectures for Efficient Inference. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00183"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00548"},{"key":"e_1_3_2_2_36_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Niklaus Simon","year":"2017","unstructured":"Simon Niklaus, Long Mai, and Feng Liu. 2017a. Video Frame Interpolation via Adaptive Convolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.37"},{"key":"e_1_3_2_2_38_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Ning Qian","year":"2021","unstructured":"Qian Ning, Weisheng Dong, Xin Li, Jinjian Wu, and GUANGMING Shi. 2021. Uncertainty-Driven Loss for Single Image Super-Resolution. In Advances in Neural Information Processing Systems, Vol. 34. Curran Associates, Inc., 16398--16409."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01217"},{"key":"e_1_3_2_2_40_1","volume-title":"BMBC: Bilateral Motion Estimation with Bilateral Cost","author":"Park Junheum","year":"2020","unstructured":"Junheum Park, Keunsoo Ko, Chul Lee, and Chang-Su Kim. 2020. BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation. In Computer Vision - ECCV 2020, Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.). 109--125."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01427"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00250"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_44"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01696"},{"key":"e_1_3_2_2_45_1","volume-title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. CoRR (12","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Zamir, and Mubarak Shah. 2012. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. CoRR (12 2012)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00488"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_26"},{"key":"e_1_3_2_2_48_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Wu Zuxuan","year":"2018","unstructured":"Zuxuan Wu, Tushar Nagarajan, Abhishek Kumar, Steven Rennie, Larry S. Davis, Kristen Grauman, and Rogerio Feris. 2018a. Block Drop: Dynamic Inference Paths in Residual Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_31"},{"key":"e_1_3_2_2_50_1","first-page":"275","article-title":"Early Exit or Not","volume":"2020","author":"Xing Qunliang","year":"2020","unstructured":"Qunliang Xing, Mai Xu, Tianyi Li, and Zhenyu Guan. 2020. Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images. In Computer Vision - ECCV 2020. 275--292.","journal-title":"Resource-Efficient Blind Quality Enhancement for Compressed Images. In Computer Vision - ECCV"},{"key":"e_1_3_2_2_51_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Xu Xiangyu","year":"2019","unstructured":"Xiangyu Xu, Li Siyao, Wenxiu Sun, Qian Yin, and Ming-Hsuan Yang. 2019. Quadratic Video Interpolation. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20200"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"e_1_3_2_2_54_1","first-page":"286","article-title":"View Synthesis by Appearance Flow","volume":"2016","author":"Zhou Tinghui","year":"2016","unstructured":"Tinghui Zhou, Shubham Tulsiani, Weilun Sun, Jitendra Malik, and Alexei A. Efros. 2016. View Synthesis by Appearance Flow. In Computer Vision - ECCV 2016. 286--301.","journal-title":"Computer Vision - ECCV"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611752","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:12:27Z","timestamp":1755821547000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611752"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":54,"alternative-id":["10.1145\/3581783.3611752","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611752","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}