{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:17:53Z","timestamp":1788844673647,"version":"build-2803163510"},"reference-count":75,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T00:00:00Z","timestamp":1685664000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T00:00:00Z","timestamp":1685664000000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s11263-023-01809-7","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T08:31:08Z","timestamp":1685694668000},"page":"2333-2355","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Semantic-Aware Visual Decomposition for Image Coding"],"prefix":"10.1007","volume":"131","author":[{"given":"Jianhui","family":"Chang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5486-3125","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiguo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanmin","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siwei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,2]]},"reference":[{"key":"1809_CR1","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Tschannen, M., & Mentzer, F., et\u00a0al. (2019). Generative adversarial networks for extreme learned image compression. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 221\u2013231).","DOI":"10.1109\/ICCV.2019.00031"},{"key":"1809_CR2","doi-asserted-by":"crossref","unstructured":"Akbari, M., Liang, J., & Han, J. (2019). DSSLIC: Deep semantic segmentation-based layered image compression. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 2042\u20132046).","DOI":"10.1109\/ICASSP.2019.8683541"},{"issue":"1","key":"1809_CR3","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s11263-006-4331-z","volume":"67","author":"JF Aujol","year":"2006","unstructured":"Aujol, J. F., Gilboa, G., Chan, T., et al. (2006). Structure\u2013texture image decomposition: Modeling, algorithms, and parameter selection. International Journal of Computer Vision, 67(1), 111\u2013136.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"1809_CR4","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1109\/JSTSP.2020.3034501","volume":"15","author":"J Ball\u00e9","year":"2020","unstructured":"Ball\u00e9, J., Chou, P. A., Minnen, D., et al. (2020). Nonlinear transform coding. IEEE Journal of Selected Topics in Signal Processing, 15(2), 339\u2013353.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"1809_CR5","unstructured":"Ball\u00e9, J., Laparra, V., & Simoncelli, E. (2017). End-to-end optimized image compression. In Proceedings of international conference on learning representations (ICLR)."},{"key":"1809_CR6","unstructured":"Ball\u00e9, J., Minnen, D., & Singh, S., et\u00a0al. (2018). Variational image compression with a scale hyperprior. In Proceedings of international conference on learning representations (ICLR)."},{"key":"1809_CR7","doi-asserted-by":"crossref","unstructured":"Benesty, J., Chen, J., & Huang, Y., et\u00a0al. (2009). Pearson correlation coefficient. In Noise reduction in speech processing (pp. 1\u20134). Springer.","DOI":"10.1007\/978-3-642-00296-0_5"},{"key":"1809_CR8","unstructured":"Bjontegaard, G. (2001). Calculation of average PSNR differences between RD-curves. ITU-T VCEG-M33, Austin, TX, USA."},{"issue":"10","key":"1809_CR9","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., et al. (2021). Overview of the versatile video coding (VVC) standard and its applications. IEEE Transactions on Circuits and Systems for Video Technology, 31(10), 3736\u20133764.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1809_CR10","unstructured":"Bross, B., Wieckowski, A., & Schwarz, H., et\u00a0al. (2016). Suggested process to select the benchmark set. In Document JVET-J0094 10th JVET meeting."},{"issue":"3","key":"1809_CR11","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s10851-012-0359-6","volume":"45","author":"W Casaca","year":"2013","unstructured":"Casaca, W., Paiva, A., Gomez-Nieto, E., et al. (2013). Spectral image segmentation using image decomposition and inner product-based metric. Journal of Mathematical Imaging and Vision, 45(3), 227\u2013238.","journal-title":"Journal of Mathematical Imaging and Vision"},{"key":"1809_CR12","doi-asserted-by":"crossref","unstructured":"Chang, J., Mao, Q., & Zhao, Z., et\u00a0al. (2019). Layered conceptual image compression via deep semantic synthesis. In IEEE international conference on image processing (ICIP) (pp. 694\u2013698).","DOI":"10.1109\/ICIP.2019.8803805"},{"key":"1809_CR13","doi-asserted-by":"publisher","first-page":"2809","DOI":"10.1109\/TIP.2022.3159477","volume":"31","author":"J Chang","year":"2022","unstructured":"Chang, J., Zhao, Z., Jia, C., et al. (2022). Conceptual compression via deep structure and texture synthesis. IEEE Transactions on Image Processing, 31, 2809\u20132823.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1809_CR14","doi-asserted-by":"crossref","unstructured":"Chang, J., Zhao, Z., & Yang, L., et\u00a0al. (2021). Thousand to one: Semantic prior modeling for conceptual coding. In 2021 IEEE international conference on multimedia and expo (ICME) (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICME51207.2021.9428366"},{"key":"1809_CR15","first-page":"17,864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., & Kirillov, A. (2021). Per-pixel classification is not all you need for semantic segmentation. Advances in Neural Information Processing Systems (NeurIPS), 34, 17,864-17,875.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"1809_CR16","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Sun, H., & Takeuchi, M., et\u00a0al. (2020). Learned image compression with discretized Gaussian mixture likelihoods and attention modules. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7939\u20137948).","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"1809_CR17","doi-asserted-by":"crossref","unstructured":"Choi, Y., El-Khamy, M., & Lee, J. (2019). Variable rate deep image compression with a conditional autoencoder. In Proceedings of the IEEE\/CVF international conference on computer vision (CVPR) (pp. 3146\u20133154).","DOI":"10.1109\/ICCV.2019.00324"},{"key":"1809_CR18","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., & Ramos, S., et\u00a0al. (2016). The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.350"},{"issue":"5","key":"1809_CR19","first-page":"2567","volume":"44","author":"K Ding","year":"2022","unstructured":"Ding, K., Ma, K., Wang, S., et al. (2022). Image quality assessment: Unifying structure and texture similarity. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(5), 2567\u20132581.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1809_CR20","doi-asserted-by":"publisher","first-page":"8776","DOI":"10.1109\/TIP.2020.3019185","volume":"29","author":"X Dong","year":"2020","unstructured":"Dong, X., Zhou, H., & Dong, J. (2020). Texture classification using pair-wise difference pooling-based bilinear convolutional neural networks. IEEE Transactions on Image Processing, 29, 8776\u20138790.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1809_CR21","unstructured":"Gregor, K., Besse, F., & Rezende, D. J., et\u00a0al. (2016). Towards conceptual compression. In Advances in neural information processing systems (NeurIPS) (pp. 3549\u20133557)."},{"key":"1809_CR22","doi-asserted-by":"crossref","unstructured":"Gu, S., Meng, D., & Zuo, W., et\u00a0al. (2017). Joint convolutional analysis and synthesis sparse representation for single image layer separation. In Proceedings of the IEEE international conference on computer vision (CVPR) (pp. 1708\u20131716).","DOI":"10.1109\/ICCV.2017.189"},{"issue":"1","key":"1809_CR23","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/j.cviu.2005.09.004","volume":"106","author":"C Guo","year":"2007","unstructured":"Guo, C., Zhu, S. C., & Wu, Y. N. (2007). Primal sketch: Integrating structure and texture. Computer Vision and Image Understanding, 106(1), 5\u201319.","journal-title":"Computer Vision and Image Understanding"},{"key":"1809_CR24","doi-asserted-by":"crossref","unstructured":"Hoang, T. M., Zhou, J., & Fan, Y. (2020). Image compression with encoder\u2013decoder matched semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops (pp. 619\u2013623).","DOI":"10.1109\/CVPRW50498.2020.00088"},{"key":"1809_CR25","unstructured":"Iwai, S., Miyazaki, T., & Sugaya, Y., et\u00a0al. (2020). Fidelity-controllable extreme image compression with generative adversarial networks. In ICPR (pp. 8235\u20138242). IEEE."},{"key":"1809_CR26","doi-asserted-by":"crossref","unstructured":"Jeon, J., Cho, S., & Tong, X., et\u00a0al. (2014). Intrinsic image decomposition using structure-texture separation and surface normals. In European conference on computer vision (ECCV) (pp. 218\u2013233). Springer.","DOI":"10.1007\/978-3-319-10584-0_15"},{"key":"1809_CR27","doi-asserted-by":"crossref","unstructured":"Jia, C., Ge, Z., & Wang, S., et\u00a0al. (2021). Rate distortion characteristic modeling for neural image compression. arXiv preprint arXiv:2106.12954.","DOI":"10.1109\/DCC52660.2022.00028"},{"key":"1809_CR28","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., & Fei-Fei, L. (2016). Perceptual losses for real-time style transfer and super-resolution. In Proceedings of European conference on computer vision (ECCV). Springer.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"1809_CR29","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 4401\u20134410).","DOI":"10.1109\/CVPR.2019.00453"},{"key":"1809_CR30","doi-asserted-by":"crossref","unstructured":"Kazemi, V., & Sullivan, J. (2014). One millisecond face alignment with an ensemble of regression trees. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1867\u20131874).","DOI":"10.1109\/CVPR.2014.241"},{"key":"1809_CR31","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P., Teterwak, P., Wang, C., et al. (2020). Supervised contrastive learning. Advances in Neural Information Processing Systems (NeurIPS), 33, 18661\u201318673.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"issue":"6","key":"1809_CR32","doi-asserted-by":"publisher","first-page":"2692","DOI":"10.1109\/TIP.2018.2889531","volume":"28","author":"Y Kim","year":"2018","unstructured":"Kim, Y., Ham, B., Do, M. N., et al. (2018). Structure\u2013texture image decomposition using deep variational priors. IEEE Transactions on Image Processing, 28(6), 2692\u20132704.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1809_CR33","unstructured":"Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of international conference on learning representations (ICLR)."},{"key":"1809_CR34","doi-asserted-by":"crossref","unstructured":"Lee, C. H., Liu, Z., & Wu, L., et\u00a0al. (2020). Maskgan: Towards diverse and interactive facial image manipulation. In IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"1809_CR35","unstructured":"Lee, J., Cho, S., & Beack, S. K. (2018). Context-adaptive entropy model for end-to-end optimized image compression. In Proceedings of international conference on learning representations (ICLR)."},{"key":"1809_CR36","doi-asserted-by":"crossref","unstructured":"Li, J., Jia, C., & Zhang, X., et\u00a0al. (2021a). Cross modal compression: Towards human-comprehensible semantic compression. In Proceedings of the 29th ACM international conference on multimedia (pp. 4230\u20134238).","DOI":"10.1145\/3474085.3475558"},{"key":"1809_CR37","doi-asserted-by":"crossref","unstructured":"Li, X., Shi, J., & Chen, Z. (2021b). Task-driven semantic coding via reinforcement learning. arXiv preprint arXiv:2106.03511.","DOI":"10.1109\/TIP.2021.3091909"},{"key":"1809_CR38","doi-asserted-by":"crossref","unstructured":"Li, Y., Jia, C., & Wang, S., et\u00a0al. (2018). Joint rate-distortion optimization for simultaneous texture and deep feature compression of facial images. In 2018 IEEE fourth international conference on multimedia big data (BigMM) (pp. 1\u20135). IEEE.","DOI":"10.1109\/BigMM.2018.8499170"},{"key":"1809_CR39","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, S., & Zhang, X., et\u00a0al. (2021c). Quality assessment of end-to-end learned image compression: The benchmark and objective measure. In Proceedings of the 29th ACM international conference on multimedia (pp. 4297\u20134305).","DOI":"10.1145\/3474085.3475569"},{"issue":"1","key":"1809_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3368405","volume":"53","author":"D Liu","year":"2020","unstructured":"Liu, D., Li, Y., Lin, J., et al. (2020). Deep learning-based video coding: A review and a case study. ACM Computing Surveys (CSUR), 53(1), 1\u201335.","journal-title":"ACM Computing Surveys (CSUR)"},{"issue":"5","key":"1809_CR41","doi-asserted-by":"publisher","first-page":"e0196,391","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone, S. R., & Russo, F. A. (2018). The Ryerson audio-visual database of emotional speech and song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English. PLoS ONE, 13(5), e0196,391.","journal-title":"PLoS ONE"},{"key":"1809_CR42","doi-asserted-by":"crossref","unstructured":"Luo, S., Yang, Y., & Yin, Y., et\u00a0al. (2018). DeepSIC: Deep semantic image compression. In International conference on neural information processing (NeurIPS) (pp. 96\u2013106). Springer.","DOI":"10.1007\/978-3-030-04167-0_9"},{"key":"1809_CR43","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1109\/TPAMI.2020.3026003","volume":"44","author":"H Ma","year":"2020","unstructured":"Ma, H., Liu, D., Yan, N., et al. (2020). End-to-end optimized versatile image compression with wavelet-like transform. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 1247\u20131263.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"1809_CR44","doi-asserted-by":"publisher","first-page":"1683","DOI":"10.1109\/TCSVT.2019.2910119","volume":"30","author":"S Ma","year":"2019","unstructured":"Ma, S., Zhang, X., Jia, C., et al. (2019). Image and video compression with neural networks: A review. IEEE Transactions on Circuits and Systems for Video Technology, 30(6), 1683\u20131698.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"107","key":"1809_CR45","first-page":"817","volume":"112","author":"S Mao","year":"2021","unstructured":"Mao, S., Rajan, D., & Chia, L. T. (2021). Deep residual pooling network for texture recognition. Pattern Recognition, 112(107), 817.","journal-title":"Pattern Recognition"},{"key":"1809_CR46","volume-title":"Vision: A computational investigation into the human representation and processing of visual information","author":"D Marr","year":"1982","unstructured":"Marr, D. (1982). Vision: A computational investigation into the human representation and processing of visual information (Vol. 1(2)). Freeman and Company."},{"key":"1809_CR47","unstructured":"Mentzer, F., Toderici, G. D., & Tschannen, M., et\u00a0al. (2020). High-fidelity generative image compression. In Proceedings of advances in neural information processing systems (NeurIPS)."},{"key":"1809_CR48","unstructured":"Minnen, D., Ball\u00e9, J., & Toderici, G. D. (2018). Joint autoregressive and hierarchical priors for learned image compression. In Advances in neural information processing systems (NeurIPS) (pp. 10,771\u201310,780)."},{"key":"1809_CR49","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M. Y., & Wang, T. C., et\u00a0al. (2019). Semantic image synthesis with spatially-adaptive normalization. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00244"},{"key":"1809_CR50","unstructured":"Park, T., Zhu, J. Y., & Wang, O., et\u00a0al. (2020). Swapping autoencoder for deep image manipulation. In Advances in neural information processing systems (NeurIPS)."},{"key":"1809_CR51","first-page":"8026","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke, A., Gross, S., Massa, F., et al. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems (NeurIPS), 32, 8026\u20138037.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"1809_CR52","volume-title":"JPEG: Still image data compression standard","author":"WB Pennebaker","year":"1992","unstructured":"Pennebaker, W. B., & Mitchell, J. L. (1992). JPEG: Still image data compression standard. Springer."},{"issue":"2","key":"1809_CR53","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1117\/1.1469618","volume":"11","author":"M Rabbani","year":"2002","unstructured":"Rabbani, M. (2002). JPEG2000: Image compression fundamentals, standards and practice. Journal of Electronic Imaging, 11(2), 286.","journal-title":"Journal of Electronic Imaging"},{"key":"1809_CR54","unstructured":"Schwarz, H., Rudat, C., & Siekmann, M., et\u00a0al. (2016). Coding efficiency\/complexity analysis of jem 1.0 coding tools for the random access configuration. In Document JVET-B0044 3rd 2nd JVET meeting."},{"key":"1809_CR55","doi-asserted-by":"crossref","unstructured":"Shaham, T. R., Dekel, T., & Michaeli, T. (2019). SinGAN: Learning a generative model from a single natural image. In Proceedings of the IEEE international conference on computer vision (CVPR) (pp. 4570\u20134580).","DOI":"10.1109\/ICCV.2019.00467"},{"key":"1809_CR56","doi-asserted-by":"crossref","unstructured":"Sneyers, J., & Wuille, P. (2016). FLIF: Free lossless image format based on MANIAC compression. In 2016 IEEE international conference on image processing (ICIP) (pp. 66\u201370). IEEE.","DOI":"10.1109\/ICIP.2016.7532320"},{"issue":"9","key":"1809_CR57","doi-asserted-by":"publisher","first-page":"3631","DOI":"10.1109\/TCSVT.2020.3042517","volume":"31","author":"S Sun","year":"2021","unstructured":"Sun, S., He, T., & Chen, Z. (2021). Semantic structured image coding framework for multiple intelligent applications. IEEE Transactions on Circuits and Systems for Video Technology, 31(9), 3631\u20133642.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1809_CR58","doi-asserted-by":"crossref","unstructured":"Sun, Z., Tan, Z., & Sun, X., et\u00a0al. (2021b). Interpolation variable rate image compression. In Proceedings of the 29th ACM international conference on multimedia (pp. 5574\u20135582).","DOI":"10.1145\/3474085.3475698"},{"key":"1809_CR59","first-page":"40","volume":"39","author":"V Sze","year":"2014","unstructured":"Sze, V., Budagavi, M., & Sullivan, G. J. (2014). High efficiency video coding (HEVC). Integrated Circuit and Systems, Algorithms and Architectures Springer, 39, 40.","journal-title":"Integrated Circuit and Systems, Algorithms and Architectures Springer"},{"key":"1809_CR60","doi-asserted-by":"publisher","first-page":"3169","DOI":"10.1109\/TMM.2021.3094300","volume":"24","author":"S Wang","year":"2021","unstructured":"Wang, S., Wang, S., Yang, W., et al. (2021). Towards analysis-friendly face representation with scalable feature and texture compression. IEEE Transactions on Multimedia, 24, 3169\u20133181.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1809_CR61","doi-asserted-by":"crossref","unstructured":"Wang, T. C., Liu, M. Y., & Zhu, J. Y., et\u00a0al. (2018a). High-resolution image synthesis and semantic manipulation with conditional GANs. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 8798\u20138807).","DOI":"10.1109\/CVPR.2018.00917"},{"key":"1809_CR62","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., & Gupta, A., et\u00a0al. (2018b). Non-local neural networks. In Proceedings of the IEEE international conference on computer vision (CVPR) (pp. 7794\u20137803).","DOI":"10.1109\/CVPR.2018.00813"},{"issue":"3","key":"1809_CR63","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1109\/TCSVT.2020.3000331","volume":"31","author":"Y Wang","year":"2020","unstructured":"Wang, Y., Liu, D., Ma, S., et al. (2020). Ensemble learning-based rate-distortion optimization for end-to-end image compression. IEEE Transactions on Circuits and Systems for Video Technology, 31(3), 1193\u20131207.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1809_CR64","doi-asserted-by":"crossref","unstructured":"Xia, Q., Liu, H., & Ma, Z. (2020). Object-based image coding: A learning-driven revisit. In 2020 IEEE international conference on multimedia and expo (ICME) (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICME46284.2020.9102810"},{"key":"1809_CR65","doi-asserted-by":"crossref","unstructured":"Yan, N., Liu, D., & Li, H., et\u00a0al. (2020). Towards semantically scalable image coding using semantic map. In 2020 IEEE international symposium on circuits and systems (ISCAS) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ISCAS45731.2020.9180529"},{"key":"1809_CR66","doi-asserted-by":"crossref","unstructured":"Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In European conference on computer vision (ECCV) (pp. 818\u2013833). Springer.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"1809_CR67","unstructured":"Zhang, H., Zhang, Z., & Odena, A., et\u00a0al. (2020). Consistency regularization for generative adversarial networks. In Proceedings of international conference on learning representations (ICLR)."},{"key":"1809_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, P., Wang, S., & Wang, M., et\u00a0al. (2023). Rethinking semantic image compression: Scalable representation with cross-modality transfer. IEEE Transactions on Circuits and Systems for Video Technology.","DOI":"10.1109\/TCSVT.2023.3241225"},{"key":"1809_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., & Efros, A. A., et\u00a0al. (2018). The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 586\u2013595).","DOI":"10.1109\/CVPR.2018.00068"},{"key":"1809_CR70","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Jia, C., & Wang, S., et\u00a0al. (2021). Learned image compression using adaptive block-wise encoding and reconstruction network. In 2021 IEEE international symposium on circuits and systems (ISCAS) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ISCAS51556.2021.9401164"},{"key":"1809_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., & Puig, X., et\u00a0al. (2017). Scene parsing through ade20k dataset. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.544"},{"key":"1809_CR72","doi-asserted-by":"crossref","unstructured":"Zhu, H., Wu, W., & Zhu, W., et\u00a0al. (2022a). Celebv-hq: A large-scale video facial attributes dataset. In European conference on computer vision (pp. 650\u2013667). Springer.","DOI":"10.1007\/978-3-031-20071-7_38"},{"key":"1809_CR73","doi-asserted-by":"publisher","first-page":"5068","DOI":"10.1109\/TCSVT.2022.3146731","volume":"32","author":"L Zhu","year":"2022","unstructured":"Zhu, L., Yang, W., Chen, B., et al. (2022). Enlightening low-light images with dynamic guidance for context enrichment. IEEE Transactions on Circuits and Systems for Video Technology, 32, 5068\u20135079.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1809_CR74","doi-asserted-by":"crossref","unstructured":"Zhu, P., Abdal, R., & Qin, Y., et\u00a0al. (2020). Sean: Image synthesis with semantic region-adaptive normalization. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00515"},{"key":"1809_CR75","doi-asserted-by":"crossref","unstructured":"Zhu, W., Ding, W., Xu, J., et al. (2014). Screen content coding based on HEVC framework. IEEE Transactions on Multimedia, 16(5), 1316\u20131326.","DOI":"10.1109\/TMM.2014.2315782"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01809-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01809-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01809-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T03:32:08Z","timestamp":1690601528000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01809-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,2]]},"references-count":75,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["1809"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01809-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,2]]},"assertion":[{"value":"17 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}