{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:31:10Z","timestamp":1786113070674,"version":"3.56.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197864","type":"print"},{"value":"9783031197871","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\/978-3-031-19787-1_12","type":"book-chapter","created":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T22:16:11Z","timestamp":1666304171000},"page":"207-223","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":78,"title":["CANF-VC: Conditional Augmented Normalizing Flows for\u00a0Video Compression"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9384-3258","authenticated-orcid":false,"given":"Yung-Han","family":"Ho","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chih-Peng","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9016-3297","authenticated-orcid":false,"given":"Peng-Yu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8308-0776","authenticated-orcid":false,"given":"Alessandro","family":"Gnutti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4421-8031","authenticated-orcid":false,"given":"Wen-Hsiao","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,21]]},"reference":[{"key":"12_CR1","unstructured":"HM reference software for HEVC. https:\/\/vcgit.hhi.fraunhofer.de\/jvet\/HM\/-\/tree\/HM-16.20. Accessed 03 Mar 2022"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Minnen, D., Johnston, N., Balle, J., Hwang, S.J., Toderici, G.: Scale-space flow for end-to-end optimized video compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8503\u20138512 (2020)","DOI":"10.1109\/CVPR42600.2020.00853"},{"key":"12_CR3","unstructured":"Ball\u00e9, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. In: International Conference for Learning Representations (2017)"},{"key":"12_CR4","unstructured":"Ball\u00e9, J., Minnen, D., Singh, S., Hwang, S.J., Johnston, N.: Variational image compression with a scale hyperprior. In: International Conference on Learning Representations (2018)"},{"key":"12_CR5","unstructured":"B\u00e9gaint, J., Racap\u00e9, F., Feltman, S., Pushparaja, A.: Compressai: a pytorch library and evaluation platform for end-to-end compression research. arXiv preprint arXiv:2011.03029 (2020)"},{"key":"12_CR6","unstructured":"Brand, F., Seiler, J., Kaup, A.: Generalized difference coder: a novel conditional autoencoder structure for video compression. arXiv:2112.08011 (2021)"},{"issue":"10","key":"12_CR7","doi-asserted-by":"publisher","first-page":"3736","DOI":"10.1109\/TCSVT.2021.3101953","volume":"31","author":"B Bross","year":"2021","unstructured":"Bross, B., et al.: Overview of the versatile video coding (VVC) standard and its applications. IEEE Trans. Circuits Syst. Video Technol. 31(10), 3736\u20133764 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"12_CR8","doi-asserted-by":"publisher","first-page":"3179","DOI":"10.1109\/TIP.2021.3058615","volume":"30","author":"T Chen","year":"2021","unstructured":"Chen, T., Liu, H., Ma, Z., Shen, Q., Cao, X., Wang, Y.: End-to-end learnt image compression via non-local attention optimization and improved context modeling. IEEE Trans. Image Process. 30, 3179\u20133191 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Sun, H., Takeuchi, M., Katto, J.: Learned image compression with discretized gaussian mixture likelihoods and attention modules. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7939\u20137948 (2020)","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"12_CR10","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. Computing Research Repository (CoRR) (2016)"},{"key":"12_CR11","unstructured":"Frank, B.: Common test conditions and software reference configurations. JCTVC-L1100 12(7) (2013)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Golinski, A., Pourreza, R., Yang, Y., Sautiere, G., Cohen, T.S.: Feedback recurrent autoencoder for video compression. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69538-5_36"},{"key":"12_CR13","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1109\/OJCAS.2021.3123201","volume":"2","author":"YH Ho","year":"2021","unstructured":"Ho, Y.H., Chan, C.C., Peng, W.H., Hang, H.M., Doma\u0144ski, M.: ANFIC: image compression using augmented normalizing flows. IEEE Open J. Circuits Syst. 2, 613\u2013626 (2021)","journal-title":"IEEE Open J. Circuits Syst."},{"key":"12_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/978-3-030-58536-5_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Hu","year":"2020","unstructured":"Hu, Z., Chen, Z., Xu, D., Lu, G., Ouyang, W., Gu, S.: Improving deep video compression by\u00a0resolution-adaptive flow coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 193\u2013209. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_12"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Hu, Z., Lu, G., Xu, D.: FVC: a new framework towards deep video compression in feature space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1502\u20131511 (2021)","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"12_CR16","unstructured":"Huang, C.W., Dinh, L., Courville, A.: Augmented normalizing flows: bridging the gap between generative flows and latent variable models. arXiv preprint arXiv:2002.07101 (2020)"},{"key":"12_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference for Learning Representations (2015)"},{"key":"12_CR18","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1x1 convolutions. arXiv:1807.03039 (2018)"},{"key":"12_CR19","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"issue":"11","key":"12_CR20","doi-asserted-by":"publisher","first-page":"3964","DOI":"10.1109\/TPAMI.2020.2992934","volume":"43","author":"I Kobyzev","year":"2020","unstructured":"Kobyzev, I., Prince, S.J., Brubaker, M.A.: Normalizing flows: an introduction and review of current methods. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 3964\u20133979 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Ladune, T., Philippe, P., Hamidouche, W., Zhang, L., D\u00e9forges, O.: Optical flow and mode selection for learning-based video coding. In: 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP), pp. 1\u20136. IEEE (2020)","DOI":"10.1109\/MMSP48831.2020.9287049"},{"key":"12_CR22","unstructured":"Ladune, T., Philippe, P., Hamidouche, W., Zhang, L., D\u00e9forges, O.: Conditional coding for flexible learned video compression. In: Neural Compression: From Information Theory to Applications-Workshop@ ICLR 2021 (2021)"},{"key":"12_CR23","unstructured":"Li, J., Li, B., Lu, Y.: Deep contextual video compression. In: Advances in Neural Information Processing Systems (2021)"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Lin, J., Liu, D., Li, H., Wu, F.: M-LVC: multiple frames prediction for learned video compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3546\u20133554 (2020)","DOI":"10.1109\/CVPR42600.2020.00360"},{"issue":"8","key":"12_CR25","doi-asserted-by":"publisher","first-page":"3182","DOI":"10.1109\/TCSVT.2020.3035680","volume":"31","author":"H Liu","year":"2020","unstructured":"Liu, H., et al.: Neural video coding using multiscale motion compensation and spatiotemporal context model. IEEE Trans. Circuits Syst. Video Technol. 31(8), 3182\u20133196 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Lu, G., Ouyang, W., Xu, D., Zhang, X., Cai, C., Gao, Z.: DVC: an end-to-end deep video compression framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11006\u201311015 (2019)","DOI":"10.1109\/CVPR.2019.01126"},{"issue":"10","key":"12_CR27","doi-asserted-by":"publisher","first-page":"3292","DOI":"10.1109\/TPAMI.2020.2988453","volume":"43","author":"G Lu","year":"2020","unstructured":"Lu, G., Zhang, X., Ouyang, W., Chen, L., Gao, Z., Xu, D.: An end-to-end learning framework for video compression. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3292\u20133308 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR28","unstructured":"Ma, H., Liu, D., Yan, N., Li, H., Wu, F.: End-to-end optimized versatile image compression with wavelet-like transform. IEEE Trans. Pattern Anal. Mach. Intell. (2020)"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Mercat, A., Viitanen, M., Vanne, J.: UVG dataset: 50\/120fps 4K sequences for video codec analysis and development. In: Proceedings of the 11th ACM Multimedia Systems Conference, pp. 297\u2013302 (2020)","DOI":"10.1145\/3339825.3394937"},{"key":"12_CR30","first-page":"10771","volume":"31","author":"D Minnen","year":"2018","unstructured":"Minnen, D., Ball\u00e9, J., Toderici, G.D.: Joint autoregressive and hierarchical priors for learned image compression. Adv. Neural. Inf. Process. Syst. 31, 10771\u201310780 (2018)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Ranjan, A., Black, M.J.: Optical flow estimation using a spatial pyramid network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4161\u20134170 (2017)","DOI":"10.1109\/CVPR.2017.291"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Rippel, O., Anderson, A.G., Tatwawadi, K., Nair, S., Lytle, C., Bourdev, L.: ELF-VC: efficient learned flexible-rate video coding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 14479\u201314488, October 2021","DOI":"10.1109\/ICCV48922.2021.01421"},{"issue":"12","key":"12_CR33","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","volume":"22","author":"GJ Sullivan","year":"2012","unstructured":"Sullivan, G.J., Ohm, J.R., Han, W.J., Wiegand, T.: Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circuits Syst. Video Technol. 22(12), 1649\u20131668 (2012)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"12_CR34","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":"12_CR35","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: MCL-JCV: a JND-based H.264\/AVC video quality assessment dataset. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 1509\u20131513. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7532610"},{"issue":"8","key":"12_CR36","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. Vision 127(8), 1106\u20131125 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Yang, R., Mentzer, F., Gool, L.V., Timofte, R.: Learning for video compression with hierarchical quality and recurrent enhancement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6628\u20136637 (2020)","DOI":"10.1109\/CVPR42600.2020.00666"},{"issue":"2","key":"12_CR38","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1109\/JSTSP.2020.3043590","volume":"15","author":"R Yang","year":"2020","unstructured":"Yang, R., Mentzer, F., Van Gool, L., Timofte, R.: Learning for video compression with recurrent auto-encoder and recurrent probability model. IEEE J. Sel. Top. Signal Process. 15(2), 388\u2013401 (2020)","journal-title":"IEEE J. Sel. Top. Signal Process."}],"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\/978-3-031-19787-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T07:55:44Z","timestamp":1728201344000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19787-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197864","9783031197871"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19787-1_12","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":"21 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)"}}]}}