{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:35:56Z","timestamp":1773192956013,"version":"3.50.1"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:00:00Z","timestamp":1753920000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:00:00Z","timestamp":1753920000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.61673396"],"award-info":[{"award-number":["No.61673396"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Natural Science Foundation of Shandong Province","award":["No.ZR2022MF260"],"award-info":[{"award-number":["No.ZR2022MF260"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s10586-025-05133-2","type":"journal-article","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T12:51:29Z","timestamp":1753966289000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Learned image compression with CNN-LocalMamba architectures and multi-context entropy model"],"prefix":"10.1007","volume":"28","author":[{"given":"Qian","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Huijin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Mingwen","family":"Shao","sequence":"additional","affiliation":[]},{"given":"Hong","family":"Liang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,31]]},"reference":[{"key":"5133_CR1","volume-title":"JPEG: still image data compression standard","author":"WB Pennebaker","year":"1992","unstructured":"Pennebaker, W.B., Mitchell, J.L.: JPEG: still image data compression standard. Springer, Cham (1992)"},{"issue":"12","key":"5133_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":"5133_CR3","doi-asserted-by":"publisher","first-page":"3736","DOI":"10.1109\/TCSVT.2021.3101953","volume":"31","author":"B Bross","year":"2021","unstructured":"Bross, B., Chen, J., Liu, S., Sullivan, G.J., Ttiree, J.R., Ohm, J.R., Vetro, A., Wiegand, T.: 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":"5133_CR4","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":"5133_CR5","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":"5133_CR6","unstructured":"Minnen, D., Ball\u00e9, J., Toderici, G.D.: Joint autoregressive and hierarchical priors for learned image compression. Advances in neural information processing systems 31 (2018)"},{"key":"5133_CR7","doi-asserted-by":"crossref","unstructured":"He, D., Zheng, Y., Sun, B., Wang, Y., Qin, H.: Checkerboard context model for efficient learned image compression, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021), pp. 14771\u201314780","DOI":"10.1109\/CVPR46437.2021.01453"},{"issue":"4","key":"5133_CR8","doi-asserted-by":"publisher","first-page":"2329","DOI":"10.1109\/TCSVT.2021.3089491","volume":"32","author":"Z Guo","year":"2021","unstructured":"Guo, Z., Zhang, Z., Feng, R., Chen, Z.: Causal contextual prediction for learned image compression. IEEE Transactions on Circuits and Systems for Video Technology 32(4), 2329\u20132341 (2021)","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"5133_CR9","doi-asserted-by":"crossref","unstructured":"Minnen, D., Singh, S.: Channel-wise autoregressive entropy models for learned image compression, in 2020 IEEE International Conference on Image Processing (ICIP) (IEEE, 2020), pp. 3339\u20133343","DOI":"10.1109\/ICIP40778.2020.9190935"},{"key":"5133_CR10","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\/CVF conference on computer vision and pattern recognition (2020), pp. 7939\u20137948","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"5133_CR11","doi-asserted-by":"crossref","unstructured":"Xie, Y., Cheng, K.L., Chen, Q.: Enhanced invertible encoding for learned image compression, in Proceedings of the 29th ACM international conference on multimedia (2021), pp. 162\u2013170","DOI":"10.1145\/3474085.3475213"},{"key":"5133_CR12","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 Proceedings of the 31st ACM International Conference on Multimedia,\u00a0pp. 7618\u20137627. (2023)\u00a0","DOI":"10.1145\/3581783.3611694"},{"key":"5133_CR13","doi-asserted-by":"publisher","first-page":"2063","DOI":"10.1109\/TIP.2023.3263099","volume":"32","author":"H Fu","year":"2023","unstructured":"Fu, H., Liang, F., Lin, J., Li, B., Akbari, M., Liang, J., Zhang, G., Liu, D., Tu, C., Han, J.: Learned image compression with gaussian-laplacian-logistic mixture model and concatenated residual modules. IEEE Trans. Image Process. 32, 2063\u20132076 (2023)","journal-title":"IEEE Trans. Image Process.\u00a0"},{"key":"5133_CR14","doi-asserted-by":"publisher","first-page":"2739","DOI":"10.1109\/TIP.2022.3160602","volume":"31","author":"H Choi","year":"2022","unstructured":"Choi, H., Baji\u0107, I.V.: Scalable image coding for humans and machines. IEEE Trans. Image Process. 31, 2739\u20132754 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"5133_CR15","unstructured":"Zhu, Y., Yang, Y., Cohen, T.: Transformer-based transform coding, in International Conference on Learning Representations (2022)"},{"key":"5133_CR16","doi-asserted-by":"crossref","unstructured":"Zou, R., Song, C., Zhang, Z.: The devil is in the details: window-based attention for image compression, in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition,\u00a0pp. 17492\u201317501. (2022)\u00a0","DOI":"10.1109\/CVPR52688.2022.01697"},{"key":"5133_CR17","unstructured":"Qian, Y., Tan, Z., Sun, X., Lin, M., Li, D., Sun, Z., Hao, L., Jin, R.: Learning Accurate Entropy Model with Global Reference for Image Compression, in International Conference on Learning Representations (2020)"},{"key":"5133_CR18","unstructured":"Qian, Y., Sun, X., Lin, M., Tan, Z., Jin, R.: Entroformer: a transformer-based entropy model for learned image compression, in International Conference on Learning Representations (2021)"},{"key":"5133_CR19","doi-asserted-by":"crossref","unstructured":"Liu, J., Sun, H., Katto, J.: Learned image compression with mixed transformer-cnn architectures, in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition,\u00a0pp. 14388\u201314397. (2023)","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"5133_CR20","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 Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition,\u00a0pp. 5718\u20135727. (2022)","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"5133_CR21","doi-asserted-by":"crossref","unstructured":"Li, B., Liang, J., Fu, H., Han, J.: Roi-based deep image compression with swin transformers, in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),\u00a0pp. 1\u20135. (2023)","DOI":"10.1109\/ICASSP49357.2023.10094674"},{"key":"5133_CR22","doi-asserted-by":"crossref","unstructured":"Lu, M., Guo, P., Shi, H., Cao, C., Ma, Z.: Transformer-based image compression, in 2022 Data Compression Conference (DCC),\u00a0pp. 469\u2013469. (2022)","DOI":"10.1109\/DCC52660.2022.00080"},{"key":"5133_CR23","doi-asserted-by":"crossref","unstructured":"Bai, Y., Yang, X., Liu, X., Jiang, J., Wang, Y., Ji, X., Gao, W.: Towards end-to-end image compression and analysis with transformers, in Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 104\u2013112. (2022)\u00a0","DOI":"10.1609\/aaai.v36i1.19884"},{"key":"5133_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, L., Li, B., Lu, R., Chen, P., Mao, Q., Wang, Z., Yang, W., Wang, S.: Learned Image Compression for Both Humans and Machines via Dynamic Adaptation, in 2024 IEEE International Conference on Image Processing (ICIP),\u00a0pp. 1788\u20131794. (IEEE, 2024)","DOI":"10.1109\/ICIP51287.2024.10647464"},{"key":"5133_CR25","doi-asserted-by":"crossref","unstructured":"Jiang, W., Choi, H., Racap\u00e9, F.: Adaptive human-centric video compression for humans and machines, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1121\u20131129. (2023)","DOI":"10.1109\/CVPRW59228.2023.00119"},{"key":"5133_CR26","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. Preprint at\u00a0arXiv:2312.00752(2023)"},{"key":"5133_CR27","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces, in International Conference on Learning Representations (2021)"},{"key":"5133_CR28","first-page":"572","volume":"34","author":"A Gu","year":"2021","unstructured":"Gu, A., Johnson, I., Goel, K., et al.: Combining recurrent, convolutional, and continuous-time models with linear state space layers. Adv. Neural Inf. Process. Syst. 34, 572\u2013585 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"5133_CR29","unstructured":"Fu, D.Y., Dao, T., Saab, K.K.: et\u00a0al., Hungry hungry hippos: towards language modeling with state space models, in The Eleventh International Conference on Learning Representations (2022)"},{"key":"5133_CR30","unstructured":"Mehta, H., Gupta, A., Cutkosky, A., Neyshabur, B.: Long range language modeling via gated state spaces. International Conference on Learning Representations (2023)"},{"key":"5133_CR31","unstructured":"Smith, J.T., Warrington, A., Linderman, S.: Simplified state space layers for sequence modeling. The Eleventh International Conference on Learning Representations (2022)"},{"key":"5133_CR32","doi-asserted-by":"crossref","unstructured":"Huang, T., Pei, X., You, S., Wang, F., Qian, C., Xu, C.: Localmamba: visual state space model with windowed selective scan. Preprint at\u00a0arXiv:2403.09338 (2024)","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"5133_CR33","unstructured":"Liu, Y., Tian, Y., Zhao, Y.: et\u00a0al., Vmamba: visual state space model. Preprint at\u00a0arXiv:2401.10166 (2024)"},{"key":"5133_CR34","unstructured":"Bjontegaard, G.: Calculation of average psnr differences between rd-curves. ITU SG16 Doc. VCEG-M33 (2001)"},{"key":"5133_CR35","unstructured":"Theis, L., Shi, W., Cunningham, A., Husz\u00e1r, F.: Lossy image compression with compressive autoencoders, in International conference on learning representations (2022)"},{"key":"5133_CR36","doi-asserted-by":"crossref","unstructured":"Cui, Z., Wang, J., Gao, S., Guo, T., Feng, Y., Bai, B.: Asymmetric gained deep image compression with continuous rate adaptation, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10532\u201310541. (2021)","DOI":"10.1109\/CVPR46437.2021.01039"},{"key":"5133_CR37","unstructured":"Zhu, L., Liao, B., Zhang, Q.: et\u00a0al., Vision mamba: efficient visual representation learning with bidirectional state space model. Preprint at\u00a0arXiv:2401.09417 (2024)"},{"key":"5133_CR38","unstructured":"Qiao, Y., Yu, Z., Guo, L.: et\u00a0al., Vl-mamba: exploring state space models for multimodal learning. Preprint at\u00a0arXiv:2403.13600 (2024)"},{"key":"5133_CR39","unstructured":"Chen, G., Huang, Y., Xu, J.: et\u00a0al., Video mamba suite: state space model as a versatile alternative for video understanding. Preprint at\u00a0arXiv:2403.09626 (2024)"},{"key":"5133_CR40","unstructured":"Ma, J., Li, F., Wang, B.: U-mamba: enhancing long-range dependency for biomedical image segmentation. Preprint at\u00a0arXiv:2401.04722 (2024)"},{"key":"5133_CR41","doi-asserted-by":"crossref","unstructured":"Guo, H., Li, J., Dai, T.: et\u00a0al., Mambair: a simple baseline for image restoration with state-space model. Preprint at\u00a0arXiv:2402.15648 (2024)","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"5133_CR42","doi-asserted-by":"crossref","unstructured":"Han, D., Ye, T., Han, Y., Xia, Z., Pan, S., Wan, P., Song, S., Huang, G.: Agent attention: on the integration of softmax and linear attention, in European Conference on Computer Vision, pp. 124\u2013140. (Springer, 2025)","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"5133_CR43","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":"5133_CR44","unstructured":"P.\u00a0Ramachandran, B.\u00a0Zoph, Q.V. Le, Searching for activation functions. Preprint at\u00a0arXiv:1710.05941 (2017)"},{"key":"5133_CR45","doi-asserted-by":"crossref","unstructured":"Lim, B., Son, S., Kim, H., Nah, S., Mu\u00a0Lee, K.: Enhanced deep residual networks for single image super-resolution, in Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 136\u2013144. (2017)","DOI":"10.1109\/CVPRW.2017.151"},{"key":"5133_CR46","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Timofte, R.: Ntire 2017 challenge on single image super-resolution: dataset and study, in Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp. 126\u2013135. (2017)","DOI":"10.1109\/CVPRW.2017.150"},{"key":"5133_CR47","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 Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755. (Springer, 2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"5133_CR48","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database, in 2009 IEEE conference on computer vision and pattern recognition, pp. 248\u2013255. (Ieee, 2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5133_CR49","unstructured":"B\u00e9gaint, J., Racap\u00e9, F., Feltman, S., Pushparaja, A.: Compressai: a pytorch library and evaluation platform for end-to-end compression research. Preprint at\u00a0arXiv:2011.03029 (2020)"},{"key":"5133_CR50","unstructured":"Kodak, E.: Kodak lossless true color image suite (photocd pcd0992). http:\/\/r0k.us\/graphics\/kodak (1993)"},{"key":"5133_CR51","unstructured":"Asuni, N., Giachetti, A.: et\u00a0al., TESTIMAGES: a large-scale archive for testing visual devices and basic image processing algorithms., in STAG , pp. 63\u201370. (2014)"},{"key":"5133_CR52","unstructured":"Toderici, G., Shi, W., Timofte, R., Theis, L., Balle, J., Agustsson, E., Johnston, N., Mentzer, F.: Workshop and challenge on learned image compression (clic2020), in CVPR (2020)"},{"issue":"10","key":"5133_CR53","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":"5133_CR54","unstructured":"Bellard, F.: Bpg image format (2017). http:\/\/bellard.org\/bpg\/ (2016). Online"},{"key":"5133_CR55","doi-asserted-by":"crossref","unstructured":"Lin, H., Chen, B., Zhang, Z., Lin, J., Wang, X., Zhao, T.: Deepsvc: deep scalable video coding for both machine and human vision, in Proceedings of the 31st ACM International Conference on Multimedia, pp. 9205\u20139214. (2023)","DOI":"10.1145\/3581783.3612500"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-025-05133-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-025-05133-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-025-05133-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:43:41Z","timestamp":1757439821000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-025-05133-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,31]]},"references-count":55,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["5133"],"URL":"https:\/\/doi.org\/10.1007\/s10586-025-05133-2","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,31]]},"assertion":[{"value":"5 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 December 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"446"}}