{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:35:06Z","timestamp":1743075306550,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031204968"},{"type":"electronic","value":"9783031204975"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20497-5_2","type":"book-chapter","created":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T12:09:06Z","timestamp":1671192546000},"page":"18-29","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Attentive Cascaded Pyramid Network for\u00a0Online Video Stabilization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9931-5138","authenticated-orcid":false,"given":"Yufei","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0060-0543","authenticated-orcid":false,"given":"Qiming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-7661","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,17]]},"reference":[{"key":"2_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"issue":"1","key":"2_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3363550","volume":"39","author":"J Choi","year":"2020","unstructured":"Choi, J., Kweon, I.S.: Deep iterative frame interpolation for full-frame video stabilization. ACM Trans. Graph. (TOG) 39(1), 1\u20139 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\, \\times \\,$$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"1","key":"2_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1404880.1404882","volume":"5","author":"ML Gleicher","year":"2008","unstructured":"Gleicher, M.L., Liu, F.: Re-cinematography: Improving the camerawork of casual video. ACM Trans. Multimedia Comput. Commun. Appl. 5(1), 1\u201328 (2008)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"issue":"5","key":"2_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2231816.2231824","volume":"31","author":"A Goldstein","year":"2012","unstructured":"Goldstein, A., Fattal, R.: Video stabilization using Epipolar geometry. ACM Trans. Graph. (TOG) 31(5), 1\u201310 (2012)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Grundmann, M., Kwatra, V., Essa, I.: Auto-directed video stabilization with robust L1 optimal camera paths. In: CVPR 2011, pp. 225\u2013232. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995525"},{"key":"2_CR7","unstructured":"Huang, C.H., Yin, H., Tai, Y.W., Tang, C.K.: Stablenet: semi-online, multi-scale deep video stabilization. arXiv preprint arXiv:1907.10283 (2019)"},{"key":"2_CR8","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017\u20132025 (2015)"},{"key":"2_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"3","key":"2_CR10","first-page":"1","volume":"28","author":"F Liu","year":"2009","unstructured":"Liu, F., Gleicher, M., Jin, H., Agarwala, A.: Content-preserving warps for 3D video stabilization. ACM Trans. Graph. (TOG) 28(3), 1\u20139 (2009)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"1","key":"2_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1899404.1899408","volume":"30","author":"F Liu","year":"2011","unstructured":"Liu, F., Gleicher, M., Wang, J., Jin, H., Agarwala, A.: Subspace video stabilization. ACM Trans. Graph. (TOG) 30(1), 1\u201310 (2011)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1007\/978-3-319-46466-4_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"S Liu","year":"2016","unstructured":"Liu, S., Tan, P., Yuan, L., Sun, J., Zeng, B.: MeshFlow: minimum latency online video\u00a0stabilization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 800\u2013815. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_48"},{"issue":"4","key":"2_CR13","first-page":"1","volume":"32","author":"S Liu","year":"2013","unstructured":"Liu, S., Yuan, L., Tan, P., Sun, J.: Bundled camera paths for video stabilization. ACM Trans. Graph. (TOG) 32(4), 1\u201310 (2013)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Liu, S., Yuan, L., Tan, P., Sun, J.: SteadyFlow: spatially smooth optical flow for video stabilization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4209\u20134216 (2014)","DOI":"10.1109\/CVPR.2014.536"},{"issue":"7","key":"2_CR15","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1109\/TPAMI.2006.141","volume":"28","author":"Y Matsushita","year":"2006","unstructured":"Matsushita, Y., Ofek, E., Ge, W., Tang, X., Shum, H.Y.: Full-frame video stabilization with motion inpainting. IEEE Trans. Pattern Anal. Mach. Intell. 28(7), 1150\u20131163 (2006)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"2_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3494525","volume":"55","author":"M Roberto e Souza","year":"2022","unstructured":"Roberto e Souza, M., Maia, H.D.A., Pedrini, H.: Survey on digital video stabilization: concepts, methods, and challenges. ACM Comput. Surv. (CSUR) 55(3), 1\u201337 (2022)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"2_CR17","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":"2_CR18","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"},{"issue":"5","key":"2_CR19","doi-asserted-by":"publisher","first-page":"2283","DOI":"10.1109\/TIP.2018.2884280","volume":"28","author":"M Wang","year":"2018","unstructured":"Wang, M., et al.: Deep online video stabilization with multi-grid warping transformation learning. IEEE Trans. Image Process. 28(5), 2283\u20132292 (2018)","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"2_CR20","doi-asserted-by":"publisher","first-page":"1354","DOI":"10.1109\/TVCG.2013.11","volume":"19","author":"YS Wang","year":"2013","unstructured":"Wang, Y.S., Liu, F., Hsu, P.S., Lee, T.Y.: Spatially and temporally optimized video stabilization. IEEE Trans. Vis. Comput. Graph. 19(8), 1354\u20131361 (2013)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., So Kweon, I.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J., Cai, J., Rezatofighi, H., Tao, D.: Gmflow: Learning optical flow via global matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8121\u20138130 (2022)","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Xu, S.Z., Hu, J., Wang, M., Mu, T.J., Hu, S.M.: Deep video stabilization using adversarial networks. In: Computer Graphics Forum, vol. 37, pp. 267\u2013276. Wiley Online Library (2018)","DOI":"10.1111\/cgf.13566"},{"key":"2_CR24","doi-asserted-by":"publisher","first-page":"4306","DOI":"10.1109\/TIP.2022.3182887","volume":"31","author":"Y Xu","year":"2022","unstructured":"Xu, Y., Zhang, J., Maybank, S.J., Tao, D.: DUT: learning video stabilization by simply watching unstable videos. IEEE Trans. Image Process. 31, 4306\u20134320 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhang, J., Tao, D.: Out-of-boundary view synthesis towards full-frame video stabilization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4842\u20134851 (2021)","DOI":"10.1109\/ICCV48922.2021.00480"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: ViTPose: simple vision transformer baselines for human pose estimation. arXiv preprint arXiv:2204.12484 (2022)","DOI":"10.1109\/TPAMI.2023.3330016"},{"key":"2_CR27","unstructured":"Xu, Y., Zhang, Q., Zhang, J., Tao, D.: ViTAE: vision transformer advanced by exploring intrinsic inductive bias. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Yu, J., Ramamoorthi, R.: Selfie video stabilization. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 551\u2013566 (2018)","DOI":"10.1007\/978-3-030-01228-1_34"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Yu, J., Ramamoorthi, R.: Robust video stabilization by optimization in CNN weight space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3800\u20133808 (2019)","DOI":"10.1109\/CVPR.2019.00392"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Yu, J., Ramamoorthi, R.: Learning video stabilization using optical flow. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8159\u20138167 (2020)","DOI":"10.1109\/CVPR42600.2020.00818"},{"issue":"10","key":"2_CR31","doi-asserted-by":"publisher","first-page":"7789","DOI":"10.1109\/JIOT.2020.3039359","volume":"8","author":"J Zhang","year":"2020","unstructured":"Zhang, J., Tao, D.: Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things. IEEE Internet Things J. 8(10), 7789\u20137817 (2020)","journal-title":"IEEE Internet Things J."},{"issue":"5","key":"2_CR32","doi-asserted-by":"publisher","first-page":"2219","DOI":"10.1109\/TIP.2017.2676354","volume":"26","author":"L Zhang","year":"2017","unstructured":"Zhang, L., Chen, X.Q., Kong, X.Y., Huang, H.: Geodesic video stabilization in transformation space. IEEE Trans. Image Process. 26(5), 2219\u20132229 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Xu, Y., Zhang, J., Tao, D.: ViTAEv2: vision transformer advanced by exploring inductive bias for image recognition and beyond. arXiv preprint arXiv:2202.10108 (2022)","DOI":"10.1007\/s11263-022-01739-w"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Xu, Y., Zhang, J., Tao, D.: VSA: learning varied-size window attention in vision transformers. arXiv preprint arXiv:2204.08446 (2022)","DOI":"10.1007\/978-3-031-19806-9_27"},{"key":"2_CR35","doi-asserted-by":"publisher","first-page":"3582","DOI":"10.1109\/TIP.2019.2963380","volume":"29","author":"M Zhao","year":"2020","unstructured":"Zhao, M., Ling, Q.: PWStableNet: learning pixel-wise warping maps for video stabilization. IEEE Trans. Image Process. 29, 3582\u20133595 (2020)","journal-title":"IEEE Trans. Image Process."}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20497-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,3]],"date-time":"2023-12-03T04:25:36Z","timestamp":1701577536000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20497-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031204968","9783031204975"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20497-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"472","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":"164","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":"35% - 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":"3.1","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":"3.7","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)"}}]}}