{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T15:44:23Z","timestamp":1788623063409,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729911","type":"print"},{"value":"9783031729928","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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\/978-3-031-72992-8_19","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:29:02Z","timestamp":1730190542000},"page":"329-348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Rate-Distortion-Cognition Controllable Versatile Neural Image Compression"],"prefix":"10.1007","author":[{"given":"Jinming","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruoyu","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunpeng","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhibo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Minnen, D., Toderici, G., Mentzer, F.: Multi-realism image compression with a conditional generator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22324\u201322333 (2023)","DOI":"10.1109\/CVPR52729.2023.02138"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Tschannen, M., Mentzer, F., Timofte, R., Gool, L.V.: Generative adversarial networks for extreme learned image compression. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 221\u2013231 (2019)","DOI":"10.1109\/ICCV.2019.00031"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Akbari, M., Liang, J., Han, J.: DSSLIC: deep semantic segmentation-based layered image compression. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2042\u20132046. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683541"},{"key":"19_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1007\/978-3-319-10590-1_38","volume-title":"Computer Vision \u2013 ECCV 2014","author":"A Babenko","year":"2014","unstructured":"Babenko, A., Slesarev, A., Chigorin, A., Lempitsky, V.: Neural codes for image retrieval. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 584\u2013599. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_38"},{"issue":"12","key":"19_CR5","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. TPAMI 39(12), 2481\u20132495 (2017)","journal-title":"TPAMI"},{"key":"19_CR6","unstructured":"Ball\u00e9, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. In: ICLR (2017)"},{"key":"19_CR7","unstructured":"Bjontegaard, G.: Calculation of average PSNR differences between RD-curves. In: VCEG-M33 (2001)"},{"key":"19_CR8","unstructured":"Blau, Y., Michaeli, T.: Rethinking lossy compression: the rate-distortion-perception tradeoff. In: International Conference on Machine Learning. pp, 675\u2013685. PMLR (2019)"},{"key":"19_CR9","first-page":"3736","volume":"31","author":"B Bross","year":"2021","unstructured":"Bross, B., et al.: Overview of the versatile video coding (VVC) standard and its applications. TCSVT 31, 3736\u20133764 (2021)","journal-title":"TCSVT"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Chamain, L.D., Racap\u00e9, F., B\u00e9gaint, J., Pushparaja, A., Feltman, S.: End-to-end optimized image compression for machines, a study. In: 2021 Data Compression Conference (DCC), pp. 163\u2013172. IEEE (2021)","DOI":"10.1109\/DCC50243.2021.00024"},{"issue":"4","key":"19_CR12","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. TPAMI 40(4), 834\u2013848 (2017)","journal-title":"TPAMI"},{"key":"19_CR13","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607. PMLR (2020)"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Y.H., Weng, Y.C., Kao, C.H., Chien, C., Chiu, W.C., Peng, W.H.: Transtic: transferring transformer-based image compression from human perception to machine perception. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23297\u201323307 (2023)","DOI":"10.1109\/ICCV51070.2023.02129"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Chen, Z., Fan, K., Wang, S., Duan, L.Y., Lin, W., Kot, A.: Lossy intermediate deep learning feature compression and evaluation. In: ACM MM, pp. 2414\u20132422 (2019)","DOI":"10.1145\/3343031.3350849"},{"key":"19_CR16","first-page":"2230","volume":"29","author":"Z Chen","year":"2019","unstructured":"Chen, Z., Fan, K., Wang, S., Duan, L., Lin, W., Kot, A.C.: Toward intelligent sensing: intermediate deep feature compression. TIP 29, 2230\u20132243 (2019)","journal-title":"TIP"},{"key":"19_CR17","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: CVPR, pp. 7939\u20137948 (2020)","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"19_CR18","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":"19_CR19","doi-asserted-by":"crossref","unstructured":"Choi, Y., El-Khamy, M., Lee, J.: Variable rate deep image compression with a conditional autoencoder. In: ICCV, pp. 3146\u20133154 (2019)","DOI":"10.1109\/ICCV.2019.00324"},{"key":"19_CR20","unstructured":"Cui, Z., Wang, J., Bai, B., Guo, T., Feng, Y.: G-vae: a continuously variable rate deep image compression framework. arXiv preprint arXiv:2003.02012 (2020)"},{"key":"19_CR21","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. ICLR (2020)"},{"issue":"1","key":"19_CR22","first-page":"179","volume":"25","author":"LY Duan","year":"2015","unstructured":"Duan, L.Y., et al.: Overview of the MPEG-CDVS standard. TIP 25(1), 179\u2013194 (2015)","journal-title":"TIP"},{"issue":"2","key":"19_CR23","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/MMUL.2018.2873844","volume":"26","author":"LY Duan","year":"2018","unstructured":"Duan, L.Y., et al.: Compact descriptors for video analysis: the emerging MPEG standard. IEEE Multimedia 26(2), 44\u201354 (2018)","journal-title":"IEEE Multimedia"},{"key":"19_CR24","first-page":"8680","volume":"29","author":"L Duan","year":"2020","unstructured":"Duan, L., Liu, J., Yang, W., Huang, T., Gao, W.: Video coding for machines: a paradigm of collaborative compression and intelligent analytics. TIP 29, 8680\u20138695 (2020)","journal-title":"TIP"},{"key":"19_CR25","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-031-19836-6_29","volume-title":"ECCV 2022","author":"R Feng","year":"2022","unstructured":"Feng, R., et al.: Image coding for machines with omnipotent feature learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13697, pp. 510\u2013528. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_29"},{"key":"19_CR26","unstructured":"Feng, R., Liu, J., Jin, X., Pan, X., Sun, H., Chen, Z.: Prompt-ICM: a unified framework towards image coding for machines with task-driven prompts. arXiv preprint arXiv:2305.02578 (2023)"},{"issue":"11","key":"19_CR27","doi-asserted-by":"publisher","first-page":"4147","DOI":"10.1109\/TCSVT.2021.3104305","volume":"31","author":"W Gao","year":"2021","unstructured":"Gao, W., et al.: Digital retina: a way to make the city brain more efficient by visual coding. IEEE Trans. Circ. Syst. Video Technol. 31(11), 4147\u20134161 (2021)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"19_CR28","first-page":"15908","volume":"34","author":"K Han","year":"2021","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. NeurIPS 34, 15908\u201315919 (2021)","journal-title":"NeurIPS"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"He, T., Sun, S., Guo, Z., Chen, Z.: Beyond coding: detection-driven image compression with semantically structured bit-stream. In: 2019 Picture Coding Symposium (PCS), pp.\u00a01\u20135. IEEE (2019)","DOI":"10.1109\/PCS48520.2019.8954525"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Hu, Y., et\u00a0al.: Planning-oriented autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17853\u201317862 (2023)","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Hu, Y., Yang, S., Yang, W., Duan, L.Y., Liu, J.: Towards coding for human and machine vision: a scalable image coding approach. In: 2020 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136. IEEE (2020)","DOI":"10.1109\/ICME46284.2020.9102750"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Iwai, S., Miyazaki, T., Omachi, S.: Controlling rate, distortion, and realism: towards a single comprehensive neural image compression model. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2900\u20132909 (2024)","DOI":"10.1109\/WACV57701.2024.00288"},{"key":"19_CR35","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/978-3-031-19827-4_41","volume-title":"ECCV 2022","author":"M Jia","year":"2022","unstructured":"Jia, M., et al.: Visual prompt tuning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13693, pp. 709\u2013727. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41"},{"key":"19_CR36","doi-asserted-by":"publisher","first-page":"103816","DOI":"10.1016\/j.jvcir.2023.103816","volume":"93","author":"X Jin","year":"2023","unstructured":"Jin, X., Feng, R., Sun, S., Feng, R., He, T., Chen, Z.: Semantical video coding: instill static-dynamic clues into structured bitstream for AI tasks. J. Vis. Commun. Image Represent. 93, 103816 (2023)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Johnston, N., et al.: Improved lossy image compression with priming and spatially adaptive bit rates for recurrent networks. In: CVPR, pp. 4385\u20134393 (2018)","DOI":"10.1109\/CVPR.2018.00461"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"K\u00f6rber, N., Kromer, E., Siebert, A., Hauke, S., Mueller-Gritschneder, D.: Egic: enhanced low-bit-rate generative image compression guided by semantic segmentation. arXiv preprint arXiv:2309.03244 (2023)","DOI":"10.1007\/978-3-031-72761-0_12"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Le, N., Zhang, H., Cricri, F., Ghaznavi-Youvalari, R., Rahtu, E.: Image coding for machines: an end-to-end learned approach. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1590\u20131594. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414465"},{"key":"19_CR40","unstructured":"Li, H., Li, S., Dai, W., Li, C., Zou, J., Xiong, H.: Frequency-aware transformer for learned image compression. arXiv preprint arXiv:2310.16387 (2023)"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Li, H., Li, S., Ding, S., Dai, W., Cao, M., Li, C., Zou, J., Xiong, H.: Image compression for machine and human vision with spatial-frequency adaptation. In: ECCV. Springer (2024)","DOI":"10.1007\/978-3-031-72983-6_22"},{"key":"19_CR42","first-page":"6307","volume":"30","author":"X Li","year":"2021","unstructured":"Li, X., Shi, J., Chen, Z.: Task-driven semantic coding via reinforcement learning. TIP 30, 6307\u20136320 (2021)","journal-title":"TIP"},{"key":"19_CR43","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-031-20077-9_17","volume-title":"ECCV 2022","author":"Y Li","year":"2022","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13699, pp. 280\u2013296. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Liu, J., Sun, H., Katto, J.: Semantic segmentation in learned compressed domain. In: 2022 Picture Coding Symposium (PCS), pp. 181\u2013185. IEEE (2022)","DOI":"10.1109\/PCS56426.2022.10018036"},{"key":"19_CR45","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, pp. 14388\u201314397 (2023)","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"19_CR47","unstructured":"Lu, G., Ge, X., Zhong, T., Geng, J., Hu, Q.: Preprocessing enhanced image compression for machine vision. arXiv preprint arXiv:2206.05650 (2022)"},{"key":"19_CR48","doi-asserted-by":"crossref","unstructured":"Lu, M., Guo, P., Shi, H., Cao, C., Ma, Z.: Transformer-based image compression. arXiv preprint arXiv:2111.06707 (2021)","DOI":"10.1109\/DCC52660.2022.00080"},{"issue":"3","key":"19_CR49","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., Li, H., Wu, F.: End-to-end optimized versatile image compression with wavelet-like transform. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1247\u20131263 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"10","key":"19_CR50","first-page":"3095","volume":"29","author":"S Ma","year":"2018","unstructured":"Ma, S., Zhang, X., Wang, S., Zhang, X., Jia, C., Wang, S.: Joint feature and texture coding: toward smart video representation via front-end intelligence. TCSVT 29(10), 3095\u20133105 (2018)","journal-title":"TCSVT"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Mentzer, F., Agustsson, E., Tschannen, M., Timofte, R., Van\u00a0Gool, L.: Conditional probability models for deep image compression. In: CVPR, pp. 4394\u20134402 (2018)","DOI":"10.1109\/CVPR.2018.00462"},{"key":"19_CR52","unstructured":"Mentzer, F., Toderici, G., Tschannen, M., Agustsson, E.: High-fidelity generative image compression. arXiv preprint arXiv:2006.09965 (2020)"},{"key":"19_CR53","unstructured":"Minnen, D., Ball\u00e9, J., Toderici, G.: Joint autoregressive and hierarchical priors for learned image compression. In: NeurIPS (2018)"},{"issue":"1","key":"19_CR54","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0923-5965(01)00024-8","volume":"17","author":"M Rabbani","year":"2002","unstructured":"Rabbani, M., Joshi, R.: An overview of the JPEG 2000 still image compression standard. Signal Process. Image Commun. 17(1), 3\u201348 (2002)","journal-title":"Signal Process. Image Commun."},{"key":"19_CR55","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"19_CR56","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: CVPR, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"19_CR57","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. NeurIPS 28, 91\u201399 (2015)","journal-title":"NeurIPS"},{"key":"19_CR58","doi-asserted-by":"crossref","unstructured":"Singh, S., Abu-El-Haija, S., Johnston, N., Ball\u00e9, J., Shrivastava, A., Toderici, G.: End-to-end learning of compressible features. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 3349\u20133353. IEEE (2020)","DOI":"10.1109\/ICIP40778.2020.9190860"},{"key":"19_CR59","doi-asserted-by":"crossref","unstructured":"Song, M., Choi, J., Han, B.: Variable-rate deep image compression through spatially-adaptive feature transform. In: ICCV, pp. 2380\u20132389 (2021)","DOI":"10.1109\/ICCV48922.2021.00238"},{"issue":"12","key":"19_CR60","first-page":"1649","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. TCSVT 22(12), 1649\u20131668 (2012)","journal-title":"TCSVT"},{"key":"19_CR61","first-page":"3631","volume":"31","author":"S Sun","year":"2020","unstructured":"Sun, S., He, T., Chen, Z.: Semantic structured image coding framework for multiple intelligent applications. TCSVT 31, 3631\u20133642 (2020)","journal-title":"TCSVT"},{"key":"19_CR62","doi-asserted-by":"crossref","unstructured":"Terh\u00f6rst, P., et al.: Qmagface: simple and accurate quality-aware face recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3484\u20133494 (2023)","DOI":"10.1109\/WACV56688.2023.00348"},{"key":"19_CR63","doi-asserted-by":"crossref","unstructured":"Toderici, G., et al.: Full resolution image compression with recurrent neural networks. In: CVPR, pp. 5306\u20135314 (2017)","DOI":"10.1109\/CVPR.2017.577"},{"key":"19_CR64","doi-asserted-by":"crossref","unstructured":"Wallace, G.K.: The JPEG still picture compression standard. IEEE Trans. Consum. Electron. 38(1), xviii\u2013xxxiv (1992)","DOI":"10.1109\/30.125072"},{"key":"19_CR65","first-page":"3169","volume":"24","author":"S Wang","year":"2021","unstructured":"Wang, S., et al.: Towards analysis-friendly face representation with scalable feature and texture compression. TMM 24, 3169\u20133181 (2021)","journal-title":"TMM"},{"issue":"7","key":"19_CR66","first-page":"560","volume":"13","author":"T Wiegand","year":"2003","unstructured":"Wiegand, T., Sullivan, G.J., Bjontegaard, G., Luthra, A.: Overview of the H. 264\/AVC video coding standard. TCSVT 13(7), 560\u2013576 (2003)","journal-title":"TCSVT"},{"key":"19_CR67","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"19_CR68","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. NeurIPS 34, 12077\u201312090 (2021)","journal-title":"NeurIPS"},{"issue":"1","key":"19_CR69","doi-asserted-by":"publisher","first-page":"5045","DOI":"10.1038\/s41598-017-05294-0","volume":"7","author":"FF Yan","year":"2017","unstructured":"Yan, F.F., Hou, F., Lu, Z.L., Hu, X., Huang, C.B.: Efficient characterization and classification of contrast sensitivity functions in aging. Sci. Rep. 7(1), 5045 (2017)","journal-title":"Sci. Rep."},{"key":"19_CR70","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1109\/LSP.2020.2970539","volume":"27","author":"F Yang","year":"2020","unstructured":"Yang, F., Herranz, L., Van De Weijer, J., Guiti\u00e1n, J.A.I., L\u00f3pez, A.M., Mozerov, M.G.: Variable rate deep image compression with modulated autoencoder. IEEE Signal Process. Lett. 27, 331\u2013335 (2020)","journal-title":"IEEE Signal Process. Lett."},{"key":"19_CR71","unstructured":"Yang, R., Mandt, S.: Lossy image compression with conditional diffusion models. arXiv preprint arXiv:2209.06950 (2022)"},{"key":"19_CR72","doi-asserted-by":"crossref","unstructured":"Zheng, S., et\u00a0al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: CVPR, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"}],"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\/978-3-031-72992-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:47:10Z","timestamp":1730191630000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72992-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031729911","9783031729928"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72992-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 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"}}]}}