{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T13:38:42Z","timestamp":1768484322106,"version":"3.49.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T00:00:00Z","timestamp":1707264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T00:00:00Z","timestamp":1707264000000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s00138-023-01507-x","type":"journal-article","created":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T19:02:26Z","timestamp":1707332546000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["End-to-end optimized image compression with the frequency-oriented transform"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6840-5165","authenticated-orcid":false,"given":"Yuefeng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,7]]},"reference":[{"key":"1507_CR1","doi-asserted-by":"crossref","unstructured":"Wallace, G.K.: The jpeg still picture compression standard. IEEE Trans. Consum. Electron. (TCE) 38(1) (1992)","DOI":"10.1109\/30.125072"},{"issue":"2","key":"1507_CR2","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1117\/1.1469618","volume":"11","author":"M Rabbani","year":"2002","unstructured":"Rabbani, M.: Jpeg 2000: image compression fundamentals, standards and practice. J. Electron. Imaging (JEI) 11(2), 286 (2002)","journal-title":"J. Electron. Imaging (JEI)"},{"issue":"12","key":"1507_CR3","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. (TCSVT) 22(12), 1649\u20131668 (2012)","journal-title":"IEEE Trans. Circuits Syst. Video Technol. (TCSVT)"},{"issue":"10","key":"1507_CR4","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., Ye, Y., Liu, S., Chen, J., Sullivan, G.J., Ohm, J.: Overview of the versatile video coding (VVC) standard and its applications. IEEE Trans. Circuits Sys. Video Technol. (TCSVT) 31(10), 3736\u20133764 (2021)","journal-title":"IEEE Trans. Circuits Sys. Video Technol. (TCSVT)"},{"key":"1507_CR5","unstructured":"Rippel, O., Bourdev, L.: Real-time adaptive image compression. In: International Conference on Machine Learning (ICML), pp. 2922\u20132930. PMLR (2017)"},{"key":"1507_CR6","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 (ICLR), pp. 1\u201323 (2018)"},{"key":"1507_CR7","unstructured":"Minnen, D., Ball\u00e9, J., Toderici, G.: Joint autoregressive and hierarchical priors for learned image compression. Neural Inf. Process. Syst. (NIPS) (2018)"},{"key":"1507_CR8","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 Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7936\u20137945 (2020)","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"1507_CR9","doi-asserted-by":"crossref","unstructured":"Hu, Y., Yang, W., Ma, Z., Liu, J.: Learning end-to-end lossy image compression: a benchmark. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) (2021)","DOI":"10.1109\/TPAMI.2021.3065339"},{"key":"1507_CR10","unstructured":"Ball\u00e9, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. In: International Conference on Learning Representations (ICLR), pp. 1\u201327 (2017)"},{"key":"1507_CR11","doi-asserted-by":"crossref","unstructured":"Li, X., Jin, X., Yu, T., Pang, Y., Sun, S., Zhang, Z., Chen, Z.: Learning omni-frequency region-adaptive representations for real image super-resolution. In: Proceedings of Association for the Advancement of Artificial Intelligence (AAAI), pp. 1975\u20131983 (2021)","DOI":"10.1609\/aaai.v35i3.16293"},{"key":"1507_CR12","unstructured":"Akbari, M., Liang, J., Han, J., Tu, C.: Generalized octave convolutions for learned multi-frequency image compression. In: Proceedings of Association for the Advancement of Artificial Intelligence (AAAI) (2021)"},{"key":"1507_CR13","doi-asserted-by":"crossref","unstructured":"Bovik, A. (ed.): Handbook of image and video processing (2005)","DOI":"10.1201\/9781420027822.ch14"},{"issue":"2","key":"1507_CR14","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1109\/83.136597","volume":"1","author":"M Antonini","year":"1992","unstructured":"Antonini, M., Barlaud, M., Mathieu, P., Daubechies, I.: Image coding using wavelet transform. IEEE Trans. Image Process. (TIP) 1(2), 205\u2013220 (1992)","journal-title":"IEEE Trans. Image Process. (TIP)"},{"issue":"3","key":"1507_CR15","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1037\/xan0000055","volume":"41","author":"MS Murphy","year":"2015","unstructured":"Murphy, M.S., Brooks, D.I., Cook, R.G.: Pigeons use high spatial frequencies when memorizing pictures. J. Exp. Psychol. Anim. Learn. Cognit. 41(3), 277 (2015)","journal-title":"J. Exp. Psychol. Anim. Learn. Cognit."},{"key":"1507_CR16","doi-asserted-by":"crossref","unstructured":"Nakanishi, K.M., Maeda, S.-i., Miyato, T., Okanohara, D.: Neural multi-scale image compression. In: Asian Conference on Computer Vision (ACCV), pp. 718\u2013732 (2018). Springer","DOI":"10.1007\/978-3-030-20876-9_45"},{"key":"1507_CR17","unstructured":"Company, E.K.: Kodak Lossless True Color Image Suite. http:\/\/r0k.us\/graphics\/kodak\/ (1999)"},{"key":"1507_CR18","unstructured":"George, T., Wenzhe, S., Radu, T., Lucas, T., Johannes, B., Eirikur, A., Nick, J., Fabian, M.: Workshop and Challenge on Learned Image Compression (CLIC2020) (2020). http:\/\/www.compression.cc"},{"key":"1507_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lin, K., Jia, C., Ma, S.: Interpretable learned image compression: A frequency transform decomposition perspective. In: 2022 Data Compression Conference (DCC) (2022)","DOI":"10.1109\/DCC52660.2022.00106"},{"key":"1507_CR20","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of Association for the Advancement of Artificial Intelligence (AAAI), pp. 4278\u20134284 (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1507_CR21","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TCOM.1983.1095851","volume":"31","author":"PJ Burt","year":"1983","unstructured":"Burt, P.J., Adelson, E.H.: The Laplacian pyramid as a compact image code. IEEE Trans. Commun. (TCOM) 31, 532\u2013540 (1983)","journal-title":"IEEE Trans. Commun. (TCOM)"},{"key":"1507_CR22","unstructured":"Adelson, E., Anderson, C., Bergen, J., Burt, P., Ogden, J.: Pyramid methods in image processing. RCA Eng. 29 (1983)"},{"key":"1507_CR23","doi-asserted-by":"crossref","unstructured":"Ranjan, A., Black, M.J.: Optical flow estimation using a spatial pyramid network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2720\u20132729 (2017)","DOI":"10.1109\/CVPR.2017.291"},{"key":"1507_CR24","doi-asserted-by":"publisher","first-page":"9270","DOI":"10.1109\/TIP.2021.3123551","volume":"30","author":"Z Li","year":"2021","unstructured":"Li, Z., Shu, H., Zheng, C.: Multi-scale single image dehazing using Laplacian and gaussian pyramids. IEEE Trans. Image Process. (TIP) 30, 9270\u20139279 (2021)","journal-title":"IEEE Trans. Image Process. (TIP)"},{"issue":"1","key":"1507_CR25","first-page":"81","volume":"4","author":"AB Watson","year":"1994","unstructured":"Watson, A.B.: Image compression using the discrete cosine transform. Math. J. 4(1), 81 (1994)","journal-title":"Math. J."},{"key":"1507_CR26","doi-asserted-by":"crossref","unstructured":"Chen, Y., Fan, H., Xu, B., Yan, Z., Kalantidis, Y., Rohrbach, M., Yan, S., Feng, J.: Drop an octave: reducing spatial redundancy in convolutional neural networks with octave convolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3435\u20133444 (2019)","DOI":"10.1109\/ICCV.2019.00353"},{"key":"1507_CR27","doi-asserted-by":"crossref","unstructured":"Markus, A.F., Kors, J.A., Rijnbeek, P.R.: The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies. J. Biomed. Inf. (JBI), 103655 (2021)","DOI":"10.1016\/j.jbi.2020.103655"},{"key":"1507_CR28","doi-asserted-by":"crossref","unstructured":"Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., Zhong, C.: Interpretable machine learning: fundamental principles and 10 grand challenges. arXiv:2103.11251 (2021)","DOI":"10.1214\/21-SS133"},{"key":"1507_CR29","doi-asserted-by":"crossref","unstructured":"Toderici, G., O\u2019Malley, S.M., Hwang, S.J., Vincent, D., Minnen, D., Baluja, S., Covell, M., Sukthankar, R.: Variable rate image compression with recurrent neural networks. In: International Conference on Learning Representations (ICLR) (2016)","DOI":"10.1109\/CVPR.2017.577"},{"key":"1507_CR30","doi-asserted-by":"crossref","unstructured":"Jia, C., Liu, Z., Wang, Y., Ma, S., Gao, W.: Layered image compression using scalable auto-encoder. In: 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), pp. 431\u2013436 (2019). IEEE","DOI":"10.1109\/MIPR.2019.00087"},{"key":"1507_CR31","doi-asserted-by":"crossref","unstructured":"Choi, Y., El-Khamy, M., Lee, J.: Variable rate deep image compression with a conditional autoencoder. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3146\u20133154 (2019)","DOI":"10.1109\/ICCV.2019.00324"},{"key":"1507_CR32","unstructured":"Duda, J.: Asymmetric numeral systems: Entropy coding combining speed of huffman coding with compression rate of arithmetic coding. arXiv:\u00a0Information Theory (2013)"},{"key":"1507_CR33","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: Ccnet: Criss-cross attention for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"issue":"8","key":"1507_CR34","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. Vis. (IJCV) 127(8), 1106\u20131125 (2019)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"1507_CR35","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: International Conference for Learning Representations (ICLR) (2015)"},{"key":"1507_CR36","unstructured":"Clark, A.: Python Imaging Library (PIL). https:\/\/pillow.readthedocs.io\/en\/5.1.x\/index.html (2010)"},{"key":"1507_CR37","unstructured":"Bellard: BPG Image Format. https:\/\/bellard.org\/bpg\/ (2014)"},{"key":"1507_CR38","unstructured":"JVET: VVC Test Model (VTM). https:\/\/vcgit.hhi.fraunhofer.de\/jvet\/VVCSoftware_VTM (2018)"},{"key":"1507_CR39","unstructured":"Lee, J., Cho, S., Beack, S.-K.: Context-adaptive entropy model for end-to-end optimized image compression. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"1507_CR40","unstructured":"B\u2019egaint, J., Racap\u2019e, F., Feltman, S., Pushparaja, A.: Compressai: a pytorch library and evaluation platform for end-to-end compression research. arXiv:2011.03029 (2020)"},{"key":"1507_CR41","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. (TIP) 30, 3179\u20133191 (2021)","journal-title":"IEEE Trans. Image Process. (TIP)"},{"key":"1507_CR42","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European Conference on Computer Vision (ECCV), pp. 740\u2013755 (2014). Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1507_CR43","unstructured":"Jocher, G.: yolov5: v5.0 - YOLOv5-P6 1280 models. https:\/\/github.com\/ultralytics\/yolov5 (2021)"},{"key":"1507_CR44","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K.P., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 40, 834\u2013848 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"1507_CR45","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J.R.R., Ferrari, V.: Coco-stuff: Thing and stuff classes in context. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01507-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-023-01507-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01507-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,23]],"date-time":"2024-03-23T06:39:38Z","timestamp":1711175978000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-023-01507-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,7]]},"references-count":45,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["1507"],"URL":"https:\/\/doi.org\/10.1007\/s00138-023-01507-x","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,7]]},"assertion":[{"value":"5 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2024","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Typo in email of author Kai Lin corrected","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"27"}}