{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:19:45Z","timestamp":1781713185632,"version":"3.54.5"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197963","type":"print"},{"value":"9783031197970","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\/978-3-031-19797-0_15","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T20:28:41Z","timestamp":1667420921000},"page":"257-273","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Learning Spatiotemporal Frequency-Transformer for\u00a0Compressed Video Super-Resolution"],"prefix":"10.1007","author":[{"given":"Zhongwei","family":"Qiu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlong","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongmei","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"15_CR1","unstructured":"Cao, J., Li, Y., Zhang, K., Van Gool, L.: Video super-resolution transformer. arXiv preprint arXiv:2106.06847 (2021)"},{"key":"15_CR2","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: CVPR, pp. 4947\u20134956 (2021)","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"15_CR3","doi-asserted-by":"crossref","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 TOG 39(4), 75-1 (2020)","DOI":"10.1145\/3386569.3392457"},{"key":"15_CR4","unstructured":"Dosovitskiy, A., Beyeret al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"15_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/978-3-030-58598-3_18","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Ehrlich","year":"2020","unstructured":"Ehrlich, M., Davis, L., Lim, S.-N., Shrivastava, A.: Quantization guided JPEG artifact correction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 293\u2013309. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_18"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Ehrlich, M., Davis, L.S.: Deep residual learning in the jpeg transform domain. In: ICCV, pp. 3484\u20133493 (2019)","DOI":"10.1109\/ICCV.2019.00358"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Fritsche, M., Gu, S., Timofte, R.: Frequency separation for real-world super-resolution. In: ICCVW, pp. 3599\u20133608. IEEE (2019)","DOI":"10.1109\/ICCVW.2019.00445"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Fu, J., Zheng, H., Mei, T.: Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: CVPR, pp. 4438\u20134446 (2017)","DOI":"10.1109\/CVPR.2017.476"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Goto, T., Fukuoka, T., Nagashima, F., Hirano, S., Sakurai, M.: Super-resolution system for 4k-HDTV. In: ICPR, pp. 4453\u20134458. IEEE (2014)","DOI":"10.1109\/ICPR.2014.762"},{"key":"15_CR10","unstructured":"Gueguen, L., Sergeev, A., Kadlec, B., Liu, R., Yosinski, J.: Faster neural networks straight from JPEG. In: NeurIPS 31 (2018)"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Haris, M., Shakhnarovich, G., Ukita, N.: Recurrent back-projection network for video super-resolution. In: CVPR, pp. 3897\u20133906 (2019)","DOI":"10.1109\/CVPR.2019.00402"},{"key":"15_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1007\/978-3-030-58610-2_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Isobe","year":"2020","unstructured":"Isobe, T., Jia, X., Gu, S., Li, S., Wang, S., Tian, Q.: Video super-resolution with recurrent structure-detail network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 645\u2013660. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_38"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Jo, Y., Oh, S.W., Kang, J., Kim, S.J.: Deep video super-resolution network using dynamic upsampling filters without explicit motion compensation. In: CVPR, pp. 3224\u20133232 (2018)","DOI":"10.1109\/CVPR.2018.00340"},{"key":"15_CR14","unstructured":"Kim, S.Y., Lim, J., Na, T., Kim, M.: 3DSRnet: video super-resolution using 3D convolutional neural networks. arXiv preprint arXiv:1812.09079 (2018)"},{"key":"15_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/978-3-030-01219-9_7","volume-title":"Computer Vision \u2013 ECCV 2018","author":"TH Kim","year":"2018","unstructured":"Kim, T.H., Sajjadi, M.S.M., Hirsch, M., Sch\u00f6lkopf, B.: Spatio-temporal transformer network for video restoration. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 111\u2013127. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_7"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Lai, W.S., Huang, J.B., Ahuja, N., Yang, M.H.: Deep Laplacian pyramid networks for fast and accurate super-resolution. In: CVPR, pp. 624\u2013632 (2017)","DOI":"10.1109\/CVPR.2017.618"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Li, S., He, F., Du, B., Zhang, L., Xu, Y., Tao, D.: Fast spatio-temporal residual network for video super-resolution. In: CVPR, pp. 10522\u201310531 (2019)","DOI":"10.1109\/CVPR.2019.01077"},{"key":"15_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/978-3-030-58607-2_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W Li","year":"2020","unstructured":"Li, W., Tao, X., Guo, T., Qi, L., Lu, J., Jia, J.: MuCAN: multi-correspondence aggregation network for video super-resolution. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 335\u2013351. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_20"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., Jin, X., Yu, T., Sun, S., Pang, Y., Zhang, Z., Chen, Z.: Learning omni-frequency region-adaptive representations for real image super-resolution. In: AAAI, vol. 35, pp. 1975\u20131983 (2021)","DOI":"10.1609\/aaai.v35i3.16293"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Jin, P., Yang, F., Liu, C., Yang, M.H., Milanfar, P.: COMISR: compression-informed video super-resolution. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00254"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Liu, C., Yang, H., Fu, J., Qian, X.: Learning trajectory-aware transformer for video super-resolution. In: CVPR, pp. 5687\u20135696 (2022)","DOI":"10.1109\/CVPR52688.2022.00560"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., et a.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"15_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1007\/978-3-030-01264-9_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Lu","year":"2018","unstructured":"Lu, G., Ouyang, W., Xu, D., Zhang, X., Gao, Z., Sun, M.-T.: Deep Kalman filtering network for video compression artifact reduction. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 591\u2013608. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_35"},{"key":"15_CR24","first-page":"1725","volume":"29","author":"G Lu","year":"2019","unstructured":"Lu, G., Zhang, X., Ouyang, W., Xu, D., Chen, L., Gao, Z.: Deep non-local kalman network for video compression artifact reduction. TIP 29, 1725\u20131737 (2019)","journal-title":"TIP"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Nah, S., et a.: Ntire 2019 challenge on video deblurring and super-resolution: dataset and study. In: CVPRW (2019)","DOI":"10.1109\/CVPRW.2019.00251"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Qin, Z., Zhang, P., Wu, F., Li, X.: FcaNet: frequency channel attention networks. In: ICCV, pp. 783\u2013792 (2021)","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S., Vemulapalli, R., Brown, M.: Frame-recurrent video super-resolution. In: CVPR, pp. 6626\u20136634 (2018)","DOI":"10.1109\/CVPR.2018.00693"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Tao, X., Gao, H., Liao, R., Wang, J., Jia, J.: Detail-revealing deep video super-resolution. In: ICCV, pp. 4472\u20134480 (2017)","DOI":"10.1109\/ICCV.2017.479"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Tian, Y., Zhang, Y., Fu, Y., Xu, C.: TDAN: temporally-deformable alignment network for video super-resolution. In: CVPR, pp. 3360\u20133369 (2020)","DOI":"10.1109\/CVPR42600.2020.00342"},{"key":"15_CR30","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: CVPRW (2019)","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Z., Liu, D., Chang, S., Ling, Q., Yang, Y., Huang, T.S.: D3: deep dual-domain based fast restoration of jpeg-compressed images. In: CVPR, pp. 2764\u20132772 (2016)","DOI":"10.1109\/CVPR.2016.302"},{"issue":"4","key":"15_CR32","first-page":"600","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE TIP 13(4), 600\u2013612 (2004)","journal-title":"IEEE TIP"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Xu, K., Qin, M., Sun, F., Wang, Y., Chen, Y.K., Ren, F.: Learning in the frequency domain. In: CVPR, pp. 1740\u20131749 (2020)","DOI":"10.1109\/CVPR42600.2020.00181"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Xu, Y., Gao, L., Tian, K., Zhou, S., Sun, H.: Non-local ConvLSTM for video compression artifact reduction. In: ICCV, pp. 7043\u20137052 (2019)","DOI":"10.1109\/ICCV.2019.00714"},{"issue":"8","key":"15_CR35","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. IJCV 127(8), 1106\u20131125 (2019)","journal-title":"IJCV"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Yang, F., Yang, H., Fu, J., Lu, H., Guo, B.: Learning texture transformer network for image super-resolution. In: CVPR, pp. 5791\u20135800 (2020)","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Yi, P., et al.: Omniscient video super-resolution. In: ICCV, pp. 4429\u20134438 (2021)","DOI":"10.1109\/ICCV48922.2021.00439"},{"key":"15_CR38","first-page":"21125","volume":"34","author":"Y Zeng","year":"2021","unstructured":"Zeng, Y., Yang, H., Chao, H., Wang, J., Fu, J.: Improving visual quality of image synthesis by a token-based generator with transformers. NeurIPS 34, 21125\u201321137 (2021)","journal-title":"NeurIPS"},{"issue":"3","key":"15_CR39","doi-asserted-by":"publisher","first-page":"848","DOI":"10.1016\/j.sigpro.2009.09.002","volume":"90","author":"L Zhang","year":"2010","unstructured":"Zhang, L., Zhang, H., Shen, H., Li, P.: A super-resolution reconstruction algorithm for surveillance images. Sig. Process. 90(3), 848\u2013859 (2010)","journal-title":"Sig. Process."},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: ICCV, pp. 5209\u20135217 (2017)","DOI":"10.1109\/ICCV.2017.557"}],"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\/978-3-031-19797-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T20:41:56Z","timestamp":1667421716000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19797-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197963","9783031197970"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19797-0_15","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":"3 November 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)"}}]}}