{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T22:57:27Z","timestamp":1780527447191,"version":"3.54.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031278174","type":"print"},{"value":"9783031278181","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-27818-1_31","type":"book-chapter","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:20:17Z","timestamp":1680171617000},"page":"374-385","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Space-Time Video Super-Resolution 3D Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6571-9831","authenticated-orcid":false,"given":"Minyan","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9777-1543","authenticated-orcid":false,"given":"Jianping","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,31]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Bao, W., Lai, W.S., Ma, C., Zhang, X., Gao, Z., Yang, M.H.: Depth-aware video frame interpolation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3703\u20133712 (2019)","DOI":"10.1109\/CVPR.2019.00382"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Jiang, H., Sun, D., Jampani, V., Yang, M.H., Learned-Miller, E., Kautz, J.: Super SloMo: high quality estimation of multiple intermediate frames for video interpolation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9000\u20139008 (2018)","DOI":"10.1109\/CVPR.2018.00938"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Niklaus, S., Liu, F.: Context-aware synthesis for video frame interpolation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701\u20131710 (2018)","DOI":"10.1109\/CVPR.2018.00183"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S., Vemulapalli, R., Brown, M.: Frame-recurrent video super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6626\u20136634 (2018)","DOI":"10.1109\/CVPR.2018.00693"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Wang, X., Chan, K.C., Yu, K., Dong, C., Change Loy, C.: EDVR: video restoration with enhanced deformable convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"31_CR6","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Shi, Z., Xu, X., Liu, X., Chen, J., Yang, M.H.: Video frame interpolation transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17482\u201317491 (2022)","DOI":"10.1109\/CVPR52688.2022.01696"},{"key":"31_CR8","unstructured":"Cao, J., Li, Y., Zhang, K., Van Gool, L.: Video super-resolution transformer. arXiv preprint arXiv:2106.06847 (2021)"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Yang, F., Yang, H., Fu, J., Lu, H., Guo, B.: Learning texture transformer network for image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5791\u20135800 (2020)","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Niklaus, S., Mai, L., Liu, F.: Video frame interpolation via adaptive separable convolution. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 261\u2013270 (2017)","DOI":"10.1109\/ICCV.2017.37"},{"key":"31_CR11","unstructured":"Kalluri, T., Pathak, D., Chandraker, M., Tran, D.: FLAVR: flow-agnostic video representations for fast frame interpolation. arXiv preprint arXiv:2012.08512 (2020)"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Chan, K.C., Wang, X., Yu, K., Dong, C., Loy, C.C.: BasicVSR: the search for essential components in video super-resolution and beyond. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4947\u20134956 (2021)","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Haris, M., Shakhnarovich, G., Ukita, N.: Recurrent back-projection network for video super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3897\u20133906 (2019)","DOI":"10.1109\/CVPR.2019.00402"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Lim, B., Lee, K.M.: Deep recurrent ResNet for video super-resolution. In: 2007 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1452\u20131455. IEEE (2017)","DOI":"10.1109\/APSIPA.2017.8282261"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Meyer, S., Djelouah, A., McWilliams, B., Sorkine-Hornung, A., Gross, M., Schroers, C.: PhaseNet for video frame interpolation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 498\u2013507 (2018)","DOI":"10.1109\/CVPR.2018.00059"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Meyer, S., Wang, O., Zimmer, H., Grosse, M., Sorkine-Hornung, A.: Phase-based frame interpolation for video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1410\u20131418 (2015)","DOI":"10.1109\/CVPR.2015.7298747"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8934\u20138943 (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Choi, M., Kim, H., Han, B., Xu, N., Lee, K.M.: Channel attention is all you need for video frame interpolation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10663\u201310671 (2020)","DOI":"10.1609\/aaai.v34i07.6693"},{"key":"31_CR20","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token ViT: training vision transformers from scratch on ImageNet. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 558\u2013567 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A.: Video action transformer network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 244\u2013253 (2019)","DOI":"10.1109\/CVPR.2019.00033"},{"key":"31_CR24","unstructured":"Kumar, M., Weissenborn, D., Kalchbrenner, N.: Colorization transformer. arXiv preprint arXiv:2102.04432 (2021)"},{"key":"31_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Luo, J., Huang, S., Yuan, Y.: Video super-resolution using multi-scale pyramid 3D convolutional networks. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1882\u20131890 (2020)","DOI":"10.1145\/3394171.3413587"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874\u20131883 (2016)","DOI":"10.1109\/CVPR.2016.207"},{"key":"31_CR28","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"31_CR29","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1007\/s11263-018-01144-2","volume":"127","author":"T Xue","year":"2019","unstructured":"Xue, T., Chen, B., Wu, J., Wei, D., Freeman, W.T.: Video enhancement with task-oriented flow. Int. J. Comput. Vis. 127, 1106\u20131125 (2019)","journal-title":"Int. J. Comput. Vis."},{"key":"31_CR30","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/TCI.2016.2532323","volume":"2","author":"A Kappeler","year":"2016","unstructured":"Kappeler, A., Yoo, S., Dai, Q., Katsaggelos, A.K.: Video super-resolution with convolutional neural networks. IEEE Trans. Comput. Imaging 2, 109\u2013122 (2016)","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"31_CR31","unstructured":"Huang, Z., Zhang, T., Heng, W., Shi, B., Zhou, S.: Rife: real-time intermediate flow estimation for video frame interpolation. arXiv preprint arXiv:2011.06294 (2020)"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Sim, H., Oh, J., Kim, M.: XVFI: extreme video frame interpolation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14489\u201314498 (2021)","DOI":"10.1109\/ICCV48922.2021.01422"},{"key":"31_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Haris, M., Shakhnarovich, G., Ukita, N.: Space-time-aware multi-resolution video enhancement. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2020)","DOI":"10.1109\/CVPR42600.2020.00293"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27818-1_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:28:26Z","timestamp":1680172106000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27818-1_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031278174","9783031278181"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27818-1_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"31 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"86","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}