{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:20:59Z","timestamp":1772554859131,"version":"3.50.1"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197833","type":"print"},{"value":"9783031197840","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19784-0_17","type":"book-chapter","created":{"date-parts":[[2022,10,30]],"date-time":"2022-10-30T14:02:50Z","timestamp":1667138570000},"page":"289-305","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Fast-Vid2Vid: Spatial-Temporal Compression for\u00a0Video-to-Video Synthesis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1507-3360","authenticated-orcid":false,"given":"Long","family":"Zhuo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6627-814X","authenticated-orcid":false,"given":"Guangcong","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9674-2556","authenticated-orcid":false,"given":"Shikai","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1364-8151","authenticated-orcid":false,"given":"Wayne","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,31]]},"reference":[{"key":"17_CR1","unstructured":"Aguinaldo, A., Chiang, P.Y., Gain, A., Patil, A., Pearson, K., Feizi, S.: Compressing GANs using knowledge distillation. arXiv preprint arXiv:1902.00159 (2019)"},{"key":"17_CR2","unstructured":"Belousov, S.: MobileStyleGAN: a lightweight convolutional neural network for high-fidelity image synthesis. arXiv preprint arXiv:2104.04767 (2021)"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Chan, C., Ginosar, S., Zhou, T., Efros, A.A.: Everybody dance now. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5933\u20135942 (2019)","DOI":"10.1109\/ICCV.2019.00603"},{"key":"17_CR5","unstructured":"Chen, G., Choi, W., Yu, X., Han, T., Chandraker, M.: Learning efficient object detection models with knowledge distillation. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Distilling portable generative adversarial networks for image translation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 3585\u20133592 (2020)","DOI":"10.1609\/aaai.v34i04.5765"},{"issue":"4","key":"17_CR7","doi-asserted-by":"publisher","first-page":"75:1","DOI":"10.1145\/3386569.3392457","volume":"39","author":"M Chu","year":"2020","unstructured":"Chu, M., Xie, Y., Mayer, J., Leal-Taix\u00e9, L., Thuerey, N.: Learning temporal coherence via self-supervision for GAN-based video generation. ACM Trans. Graph. (TOG) 39(4), 75:1 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"17_CR9","doi-asserted-by":"publisher","first-page":"6985","DOI":"10.1109\/TIP.2021.3101158","volume":"30","author":"Z Feng","year":"2021","unstructured":"Feng, Z., Lai, J., Xie, X.: Resolution-aware knowledge distillation for efficient inference. IEEE Trans. Image Process. 30, 6985\u20136996 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR10","unstructured":"Fu, Y., Chen, W., Wang, H., Li, H., Lin, Y., Wang, Z.: AutoGAN-distiller: searching to compress generative adversarial networks. arXiv preprint arXiv:2006.08198 (2020)"},{"key":"17_CR11","unstructured":"Gafni, O., Wolf, L., Taigman, Y.: Vid2game: Controllable characters extracted from real-world videos. arXiv preprint arXiv:1904.08379 (2019)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Gao, C., Chen, Y., Liu, S., Tan, Z., Yan, S.: AdversarialNAS: adversarial neural architecture search for GANs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5680\u20135689 (2020)","DOI":"10.1109\/CVPR42600.2020.00572"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Gong, X., Chang, S., Jiang, Y., Wang, Z.: AutoGAN: neural architecture search for generative adversarial networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3224\u20133234 (2019)","DOI":"10.1109\/ICCV.2019.00332"},{"key":"17_CR14","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"17_CR15","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural networks. arXiv preprint arXiv:1506.02626 (2015)"},{"key":"17_CR16","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":"17_CR17","doi-asserted-by":"crossref","unstructured":"He, Y., Kang, G., Dong, X., Fu, Y., Yang, Y.: Soft filter pruning for accelerating deep convolutional neural networks. arXiv preprint arXiv:1808.06866 (2018)","DOI":"10.24963\/ijcai.2018\/309"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1389\u20131397 (2017)","DOI":"10.1109\/ICCV.2017.155"},{"key":"17_CR19","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems 30 (2017)"},{"key":"17_CR20","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for MobileNetV3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"17_CR22","unstructured":"Hu, H., Peng, R., Tai, Y., Tang, C., Trimming, N.: A data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250 46 (2016)"},{"key":"17_CR23","unstructured":"Hu, H., Peng, R., Tai, Y.W., Tang, C.K.: Network trimming: a data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250 (2016)"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Jin, Q., et al.: Teachers do more than teach: Compressing image-to-image models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13600\u201313611 (2021)","DOI":"10.1109\/CVPR46437.2021.01339"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Kappel, M., et al.: High-fidelity neural human motion transfer from monocular video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1541\u20131550 (2021)","DOI":"10.1109\/CVPR46437.2021.00159"},{"key":"17_CR26","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 (2016)"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Li, M., Lin, J., Ding, Y., Liu, Z., Zhu, J.Y., Han, S.: GAN compression: efficient architectures for interactive conditional GANs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5284\u20135294 (2020)","DOI":"10.1109\/CVPR42600.2020.00533"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Lin, J., Zhang, R., Ganz, F., Han, S., Zhu, J.Y.: Anycost GANs for interactive image synthesis and editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14986\u201314996 (2021)","DOI":"10.1109\/CVPR46437.2021.01474"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Y., Shu, Z., Li, Y., Lin, Z., Perazzi, F., Kung, S.Y.: Content-aware GAN compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12156\u201312166 (2021)","DOI":"10.1109\/CVPR46437.2021.01198"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2736\u20132744 (2017)","DOI":"10.1109\/ICCV.2017.298"},{"key":"17_CR31","unstructured":"Lopez-Paz, D., Bottou, L., Sch\u00f6lkopf, B., Vapnik, V.: Unifying distillation and privileged information. arXiv preprint arXiv:1511.03643 (2015)"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Luo, P., Zhu, Z., Liu, Z., Wang, X., Tang, X.: Face model compression by distilling knowledge from neurons. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10449"},{"issue":"5","key":"17_CR33","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1109\/83.334974","volume":"3","author":"MT Orchard","year":"1994","unstructured":"Orchard, M.T., Sullivan, G.J.: Overlapped block motion compensation: an estimation-theoretic approach. IEEE Trans. Image Process. 3(5), 693\u2013699 (1994)","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR34","unstructured":"R\u00f6ssler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nie\u00dfner, M.: FaceForensics: a large-scale video dataset for forgery detection in human faces. arXiv preprint arXiv:1803.09179 (2018)"},{"key":"17_CR35","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":"17_CR36","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: First order motion model for image animation. In: Advances in Neural Information Processing Systems 32, pp. 7137\u20137147 (2019)"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Woodford, O.J., Ren, J., Chai, M., Tulyakov, S.: Motion representations for articulated animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13653\u201313662 (2021)","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Tourapis, A.M.: Enhanced predictive zonal search for single and multiple frame motion estimation. In: Visual Communications and Image Processing, vol. 4671, pp. 1069\u20131079. SPIE (2002)","DOI":"10.1117\/12.453031"},{"key":"17_CR39","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"17_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/978-3-030-58548-8_4","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Gui, S., Yang, H., Liu, J., Wang, Z.: GAN slimming: all-in-one GAN compression by a unified optimization framework. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 54\u201373. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_4"},{"key":"17_CR41","unstructured":"Wang, T.C., Liu, M.Y., Tao, A., Liu, G., Kautz, J., Catanzaro, B.: Few-shot video-to-video synthesis. arXiv preprint arXiv:1910.12713 (2019)"},{"key":"17_CR42","unstructured":"Wang, T.C., et al.: Video-to-video synthesis. arXiv preprint arXiv:1808.06601 (2018)"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: End-to-end video instance segmentation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8741\u20138750 (2021)","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"17_CR45","doi-asserted-by":"crossref","unstructured":"Xiao, Z., Fu, X., Huang, J., Cheng, Z., Xiong, Z.: Space-time distillation for video super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2113\u20132122 (2021)","DOI":"10.1109\/CVPR46437.2021.00215"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Xu, G., Xu, J., Li, Z., Wang, L., Sun, X., Cheng, M.M.: Temporal modulation network for controllable space-time video super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6388\u20136397 (2021)","DOI":"10.1109\/CVPR46437.2021.00632"},{"key":"17_CR47","doi-asserted-by":"crossref","unstructured":"Xu, R., Li, X., Zhou, B., Loy, C.C.: Deep flow-guided video inpainting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3723\u20133732 (2019)","DOI":"10.1109\/CVPR.2019.00384"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J., Kim, J.: A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4133\u20134141 (2017)","DOI":"10.1109\/CVPR.2017.754"},{"key":"17_CR49","unstructured":"Yu, C., Pool, J.: Self-supervised GAN compression. arXiv preprint arXiv:2007.01491 (2020)"},{"key":"17_CR50","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-030-01237-3_12","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Zhang","year":"2018","unstructured":"Zhang, T., et al.: A systematic DNN weight pruning framework using alternating direction method of multipliers. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 191\u2013207. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_12"},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wang, Z., Fang, C., Bui, T., Berg, T.: Dance dance generation: motion transfer for internet videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00153"},{"key":"17_CR52","doi-asserted-by":"crossref","unstructured":"Zou, X., Yang, L., Liu, D., Lee, Y.J.: Progressive temporal feature alignment network for video inpainting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16448\u201316457 (2021)","DOI":"10.1109\/CVPR46437.2021.01618"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19784-0_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:34:40Z","timestamp":1710358480000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19784-0_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197833","9783031197840"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19784-0_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"31 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}