{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:51:01Z","timestamp":1756000261905,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031463044"},{"type":"electronic","value":"9783031463051"}],"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\/978-3-031-46305-1_12","type":"book-chapter","created":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T07:02:41Z","timestamp":1698476561000},"page":"142-154","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Attention-Guided Motion Estimation for\u00a0Video Compression"],"prefix":"10.1007","author":[{"given":"Siru","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Pengrui","family":"Duan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,29]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Wiegand, T., Sullivan, G.J., Bjontegaard, G., Luthra, A.: Overview of the h. 264\/avc video coding standard. IEEE Trans. Circuits Syst. Video Technol. 13(7), 560\u2013576 (2003)","DOI":"10.1109\/TCSVT.2003.815165"},{"issue":"12","key":"12_CR2","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."},{"issue":"10","key":"12_CR3","doi-asserted-by":"publisher","first-page":"3736","DOI":"10.1109\/TCSVT.2021.3101953","volume":"31","author":"B Bross","year":"2021","unstructured":"Bross, B., Wang, Y.K., Ye, Y., Liu, S., Chen, J., Sullivan, G.J., Ohm, J.R.: 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_CR4","doi-asserted-by":"crossref","unstructured":"Bankoski, J., Wilkins, P., Xu, Y.: Technical overview of vp8, an open source video codec for the web. In: 2011 IEEE International Conference on Multimedia and Expo, pp. 1\u20136. IEEE (2011)","DOI":"10.1109\/ICME.2011.6012227"},{"issue":"1","key":"12_CR5","doi-asserted-by":"publisher","first-page":"44","DOI":"10.5594\/j18499","volume":"124","author":"D Mukherjee","year":"2015","unstructured":"Mukherjee, D., Han, J., Bankoski, J., Bultje, R., Grange, A., Koleszar, J., Wilkins, P., Xu, Y.: A technical overview of vp9-the latest open-source video codec. SMPTE Motion Imaging J. 124(1), 44\u201354 (2015)","journal-title":"SMPTE Motion Imaging J."},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: An overview of core coding tools in the av1 video codec. In: 2018 picture coding symposium (PCS), pp. 41\u201345. IEEE (2018)","DOI":"10.1109\/PCS.2018.8456249"},{"key":"12_CR7","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: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01126"},{"key":"12_CR8","doi-asserted-by":"crossref","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), October 2021","DOI":"10.1109\/TPAMI.2020.2988453"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Hu, Z., Lu, G., Guo, J., Liu, S., Jiang, W., Xu, D.: Coarse-to-fine deep video coding with hyperprior-guided mode prediction. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, June 2022","DOI":"10.1109\/CVPR52688.2022.00583"},{"key":"12_CR10","unstructured":"Mentzer, F., Toderici, G., Minnen, D., Hwang, S.J., Caelles, S., Lucic, M., Agustsson, E.: Vct: A video compression transformer. arXiv preprint arXiv:2206.07307 (2022)"},{"key":"12_CR11","unstructured":"Shukor, M., YAO, X., Damodaran, B.B., Hellier, P.: Learning perceptual compression of facial video (2022)"},{"key":"12_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: 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":"12_CR14","unstructured":"Ball\u00e9, J., Minnen, D., Singh, S., Hwang, S.J., Johnston, N.: Variational image compression with a scale hyperprior. arXiv preprint arXiv:1802.01436 (2018)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Pan, X., Ge, C., Lu, R., Song, S., Chen, G., Huang, Z., Huang, G.: On the Integration of Self-Attention and Convolution. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00089"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, G., Zhu, Y., Wang, H., Chen, Y., Wu, G., Wang, L.: Extracting motion and appearance via inter-frame attention for efficient video frame interpolation. arXiv preprint arXiv:2303.00440 (2023)","DOI":"10.1109\/CVPR52729.2023.00550"},{"key":"12_CR17","unstructured":"Ball\u00e9, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. In: 5th International Conference on Learning Representations, ICLR 2017 (2017)"},{"key":"12_CR18","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_CR19","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":"12","key":"12_CR20","doi-asserted-by":"publisher","first-page":"1669","DOI":"10.1109\/TCSVT.2012.2221192","volume":"22","author":"JR Ohm","year":"2012","unstructured":"Ohm, J.R., Sullivan, G.J., Schwarz, H., Tan, T.K., Wiegand, T.: Comparison of the coding efficiency of video coding standards-including high efficiency video coding (hevc). IEEE Trans. Circuits Syst. Video Technol. 22(12), 1669\u20131684 (2012)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"12_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"12_CR22","doi-asserted-by":"publisher","unstructured":"Wang, Z., Simoncelli, E., Bovik, A.: Multiscale structural similarity for image quality assessment. In: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, vol. 2, pp. 1398\u20131402 (2003). https:\/\/doi.org\/10.1109\/ACSSC.2003.1292216","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"12_CR23","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, 1106\u20131125 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"12_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"12_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/978-3-030-58565-5_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T-W Hui","year":"2020","unstructured":"Hui, T.-W., Loy, C.C.: LiteFlowNet3: resolving correspondence ambiguity for more accurate optical flow estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 169\u2013184. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_11"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Hur, J., Roth, S.: Iterative residual refinement for joint optical flow and occlusion estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5754\u20135763 (2019)","DOI":"10.1109\/CVPR.2019.00590"},{"key":"12_CR27","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_CR28","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"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46305-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T07:04:47Z","timestamp":1698476687000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46305-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031463044","9783031463051"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46305-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2023.csig.org.cn\/","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":"Conference Management Toolkit","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"409","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":"166","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":"41% - 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":"3","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)"}}]}}