{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:10:31Z","timestamp":1775913031609,"version":"3.50.1"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729515","type":"print"},{"value":"9783031729522","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72952-2_11","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T05:02:02Z","timestamp":1727672522000},"page":"181-197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Region-Adaptive Transform with\u00a0Segmentation Prior for\u00a0Image Compression"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3385-6306","authenticated-orcid":false,"given":"Yuxi","family":"Liu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1692-0069","authenticated-orcid":false,"given":"Wenhan","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3879-8957","authenticated-orcid":false,"given":"Huihui","family":"Bai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2812-8781","authenticated-orcid":false,"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9174-5433","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"key":"11_CR1","unstructured":"Workshop and challenge on learned image compression (CLIC 2020) (2020). http:\/\/www.compression.cc"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Minnen, D., Toderici, G., Mentzer, F.: Multi-realism image compression with a conditional generator. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 22324\u201322333 (2023)","DOI":"10.1109\/CVPR52729.2023.02138"},{"issue":"1","key":"11_CR3","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/T-C.1974.223784","volume":"100","author":"N Ahmed","year":"1974","unstructured":"Ahmed, N., Natarajan, T., Rao, K.R.: Discrete cosine transform. IEEE Trans. Comput. 100(1), 90\u201393 (1974)","journal-title":"IEEE Trans. Comput."},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Akbari, M., Liang, J., Han, J.: DSSLIC: deep semantic segmentation-based layered image compression. In: ICASSP, pp. 2042\u20132046. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683541"},{"key":"11_CR5","unstructured":"Ball\u00e9, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. In: International Conference on Learning Representations (2017)"},{"key":"11_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 (2018)"},{"key":"11_CR7","unstructured":"Bellard, F.: BPG image format (2014). https:\/\/bellard.org\/bpg\/"},{"key":"11_CR8","unstructured":"Bjontegaard, G.: Calculation of average PSNR differences between RD-curves. ITU SG16 Doc. VCEG-M33 (2001)"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: COCO-stuff: thing and stuff classes in context. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Chang, J., et al.: Layered conceptual image compression via deep semantic synthesis. In: IEEE International Conference on Image Processing, pp. 694\u2013698 (2019)","DOI":"10.1109\/ICIP.2019.8803805"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Chang, J., Zhao, Z., Yang, L., Jia, C., Zhang, J., Ma, S.: Thousand to one: semantic prior modeling for conceptual coding. In: International Conference on Multimedia and Expo, pp.\u00a01\u20136. IEEE (2021)","DOI":"10.1109\/ICME51207.2021.9428366"},{"key":"11_CR12","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7939\u20137948 (2020)","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"issue":"5","key":"11_CR14","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1109\/18.57199","volume":"36","author":"I Daubechies","year":"1990","unstructured":"Daubechies, I.: The wavelet transform, time-frequency localization and signal analysis. IEEE Trans. Inf. Theory 36(5), 961\u20131005 (1990)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"11_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Feng, R., Gao, Y., Jin, X., Feng, R., Chen, Z.: Semantically structured image compression via irregular group-based decoupling. In: International Conference on Computer Vision, pp. 17237\u201317247 (2023)","DOI":"10.1109\/ICCV51070.2023.01581"},{"key":"11_CR17","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol.\u00a027. Curran Associates, Inc. (2014)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"He, D., Yang, Z., Peng, W., Ma, R., Qin, H., Wang, Y.: ELIC: efficient learned image compression with unevenly grouped space-channel contextual adaptive coding. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5718\u20135727 (2022)","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"He, D., Zheng, Y., Sun, B., Wang, Y., Qin, H.: Checkerboard context model for efficient learned image compression. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 14771\u201314780 (2021)","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Hoang, T.M., Zhou, J., Fan, Y.: Image compression with encoder-decoder matched semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 160\u2013161 (2020)","DOI":"10.1109\/CVPRW50498.2020.00088"},{"key":"11_CR22","unstructured":"Jia, X., De\u00a0Brabandere, B., Tuytelaars, T., Gool, L.V.: Dynamic filter networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, W., Yang, J., Zhai, Y., Ning, P., Gao, F., Wang, R.: MLIC: multi-reference entropy model for learned image compression. In: ACM International Conference on Multimedia, pp. 7618\u20137627 (2023)","DOI":"10.1145\/3581783.3611694"},{"key":"11_CR24","unstructured":"(JVET), J.V.E.T.: Versatile video coding (2021). https:\/\/jvet.hhi.fraunhofer.de\/"},{"key":"11_CR25","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"11_CR26","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: International Conference on Learning Representations (2014)"},{"key":"11_CR27","unstructured":"Kodak, E.: Kodak lossless true color image suite (PhotoCD PCD0992) (1993). http:\/\/r0k.us\/graphics\/kodak\/"},{"key":"11_CR28","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/978-3-031-19800-7_26","volume-title":"ECCV 2022","author":"AB Koyuncu","year":"2022","unstructured":"Koyuncu, A.B., Gao, H., Boev, A., Gaikov, G., Alshina, E., Steinbach, E.: Contextformer: a transformer with spatio-channel attention for context modeling in learned image compression. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13679, pp. 447\u2013463. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19800-7_26"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, L., Liu, Z., Lei, J., Li, Z.: Multi-frequency representation enhancement with privilege information for video super-resolution. In: International Conference on Computer Vision, pp. 12814\u201312825 (2023)","DOI":"10.1109\/ICCV51070.2023.01177"},{"key":"11_CR30","unstructured":"Liu, J., Lu, G., Hu, Z., Xu, D.: A unified end-to-end framework for efficient deep image compression. arXiv preprint arXiv:2002.03370 (2020)"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Liu, J., Sun, H., Katto, J.: Learned image compression with mixed transformer-CNN architectures. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 14388\u201314397 (2023)","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"11_CR33","unstructured":"Minnen, D., Ball\u00e9, J., Toderici, G.D.: Joint autoregressive and hierarchical priors for learned image compression. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Minnen, D., Singh, S.: Channel-wise autoregressive entropy models for learned image compression. In: IEEE International Conference on Image Processing, pp. 3339\u20133343. IEEE (2020)","DOI":"10.1109\/ICIP40778.2020.9190935"},{"key":"11_CR35","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1007\/978-3-031-19797-0_32","volume-title":"ECCV 2022","author":"G Pan","year":"2022","unstructured":"Pan, G., Lu, G., Hu, Z., Xu, D.: Content adaptive latents and decoder for neural image compression. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13678, pp. 556\u2013573. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19797-0_32"},{"key":"11_CR36","first-page":"8743","volume":"45","author":"L Qi","year":"2022","unstructured":"Qi, L., et al.: Open world entity segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45, 8743\u20138756 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Shen, H., Zhao, Z.Q., Zhang, W.: Adaptive dynamic filtering network for image denoising. In: AAAI, vol.\u00a037, pp. 2227\u20132235 (2023)","DOI":"10.1609\/aaai.v37i2.25317"},{"issue":"5","key":"11_CR38","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/79.952804","volume":"18","author":"A Skodras","year":"2001","unstructured":"Skodras, A., Christopoulos, C., Ebrahimi, T.: The JPEG 2000 still image compression standard. IEEE Signal Process. Mag. 18(5), 36\u201358 (2001)","journal-title":"IEEE Signal Process. Mag."},{"key":"11_CR39","unstructured":"Stark, H., Woods, J.W.: Probability, Random Processes, and Estimation Theory for Engineers. Prentice-Hall, Inc. (1986)"},{"issue":"9","key":"11_CR40","doi-asserted-by":"publisher","first-page":"3631","DOI":"10.1109\/TCSVT.2020.3042517","volume":"31","author":"S Sun","year":"2020","unstructured":"Sun, S., He, T., Chen, Z.: Semantic structured image coding framework for multiple intelligent applications. IEEE Trans. Circuit Syst. Video Technol. 31(9), 3631\u20133642 (2020)","journal-title":"IEEE Trans. Circuit Syst. Video Technol."},{"key":"11_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"4","key":"11_CR42","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1145\/103085.103089","volume":"34","author":"GK Wallace","year":"1991","unstructured":"Wallace, G.K.: The JPEG still picture compression standard. Commun. ACM 34(4), 30\u201344 (1991)","journal-title":"Commun. ACM"},{"key":"11_CR43","doi-asserted-by":"crossref","unstructured":"Wang, D., Yang, W., Hu, Y., Liu, J.: Neural data-dependent transform for learned image compression. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 17379\u201317388 (2022)","DOI":"10.1109\/CVPR52688.2022.01686"},{"key":"11_CR44","unstructured":"Wang, G.H., Li, J., Li, B., Lu, Y.: EVC: towards real-time neural image compression with mask decay. In: International Conference on Learning Representations (2023)"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, K., Dong, C., Loy, C.C.: Recovering realistic texture in image super-resolution by deep spatial feature transform. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 606\u2013615 (2018)","DOI":"10.1109\/CVPR.2018.00070"},{"key":"11_CR46","unstructured":"Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: The Thirty-Seventh Asilomar Conference on Signals, Systems & Computers, vol.\u00a02, pp. 1398\u20131402. IEEE (2003)"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Xu, Y.S., Tseng, S.Y.R., Tseng, Y., Kuo, H.K., Tsai, Y.M.: Unified dynamic convolutional network for super-resolution with variational degradations. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 12496\u201312505 (2020)","DOI":"10.1109\/CVPR42600.2020.01251"},{"key":"11_CR48","unstructured":"Zhu, Y., Yang, Y., Cohen, T.: Transformer-based transform coding. In: International Conference on Learning Representations (2021)"},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Zou, R., Song, C., Zhang, Z.: The devil is in the details: Window-based attention for image compression. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 17492\u201317501 (2022)","DOI":"10.1109\/CVPR52688.2022.01697"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72952-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T05:09:08Z","timestamp":1727672948000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72952-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031729515","9783031729522"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72952-2_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}