{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T03:43:37Z","timestamp":1779335017182,"version":"3.51.4"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197994","type":"print"},{"value":"9783031198007","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19800-7_26","type":"book-chapter","created":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T12:09:38Z","timestamp":1667909378000},"page":"447-463","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":74,"title":["Contextformer: A Transformer with\u00a0Spatio-Channel Attention for\u00a0Context Modeling in\u00a0Learned Image Compression"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6291-3476","authenticated-orcid":false,"given":"A. Burakhan","family":"Koyuncu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6547-1557","authenticated-orcid":false,"given":"Han","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0863-4000","authenticated-orcid":false,"given":"Atanas","family":"Boev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3803-5159","authenticated-orcid":false,"given":"Georgii","family":"Gaikov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7099-5371","authenticated-orcid":false,"given":"Elena","family":"Alshina","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8853-2703","authenticated-orcid":false,"given":"Eckehard","family":"Steinbach","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,9]]},"reference":[{"key":"26_CR1","unstructured":"Versatile Video Coding. Standard, Rec. ITU-T H.266 and ISO\/IEC 23090\u20133 (2020)"},{"key":"26_CR2","unstructured":"Asuni, N., Giachetti, A.: Testimages: a large-scale archive for testing visual devices and basic image processing algorithms. In: STAG, pp. 63\u201370 (2014)"},{"issue":"2","key":"26_CR3","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., Singh, S., Johnston, N., Agustsson, E., Hwang, S.J., Toderici, G.: Nonlinear transform coding. IEEE Journal of Selected Topics in Signal Processing 15(2), 339\u2013353 (2020)","journal-title":"IEEE J. Select. Top. Sig. Process."},{"key":"26_CR4","unstructured":"Ball\u00e9, J., Laparra, V., Simoncelli, E.P.: Density modeling of images using a generalized normalization transformation. In: 4th International Conference on Learning Representations, ICLR 2016 (2016)"},{"key":"26_CR5","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":"26_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":"26_CR7","unstructured":"B\u00e9gaint, J., Racap\u00e9, F., Feltman, S., Pushparaja, A.: Compressai: a pyTorch library and evaluation platform for end-to-end compression research. arXiv preprint arXiv:2011.03029 (2020)"},{"key":"26_CR8","unstructured":"Bellard, F.: BPG image format (2015). Accessed 01 Jun 2022. https:\/\/bellard.org\/bpg"},{"key":"26_CR9","unstructured":"Bjontegaard, G.: Calculation of average PSNR differences between RD-curves. VCEG-M33 (2001)"},{"key":"26_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, Nicolas, Massa, Francisco, Synnaeve, Gabriel, Usunier, Nicolas, Kirillov, Alexander, Zagoruyko, Sergey: End-to-end object detection with transformers. In: Vedaldi, Andrea, Bischof, Horst, Brox, Thomas, Frahm, Jan-Michael. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"26_CR11","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 Transactions on Image Processing 30, 3179\u20133191 (2021). DOI: https:\/\/doi.org\/10.1109\/TIP.2021.3058615","journal-title":"IEEE Trans. Image Process."},{"key":"26_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7939\u20137948 (2020)","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"26_CR13","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":"26_CR14","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":"26_CR15","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol.1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"26_CR16","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"26_CR18","unstructured":"Franzen, R.: Kodak lossless true color image suite (1999)"},{"issue":"5","key":"26_CR19","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1109\/79.952802","volume":"18","author":"VK Goyal","year":"2001","unstructured":"Goyal, V.K.: Theoretical foundations of transform coding. IEEE Signal Processing Magazine 18(5), 9\u201321 (2001)","journal-title":"IEEE Signal Process. Mag."},{"key":"26_CR20","doi-asserted-by":"crossref","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 (2021)","DOI":"10.1109\/TCSVT.2021.3089491"},{"key":"26_CR21","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, pp. 14771\u201314780 (2021)","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"26_CR22","unstructured":"Jiang, Y., Chang, S., Wang, Z.: TransGAN: two transformers can make one strong gan. arXiv preprint arXiv:2102.07074 (2021)"},{"key":"26_CR23","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are RNNs: fast autoregressive transformers with linear attention. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, 13\u201318 Jul 2020, vol. 119, pp. 5156\u20135165. PMLR (2020). https:\/\/proceedings.mlr.press\/v119\/katharopoulos20a.html"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Kim, D.W., Chung, J.R., Jung, S.W.: GRDN: grouped residual dense network for real image denoising and gan-based real-world noise modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00261"},{"key":"26_CR25","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Koyuncu, A.B., Cui, K., Boev, A., Steinbach, E.: Parallelized context modeling for faster image coding. In: 2021 International Conference on Visual Communications and Image Processing (VCIP), pp. 1\u20135. IEEE (2021)","DOI":"10.1109\/VCIP53242.2021.9675377"},{"key":"26_CR27","unstructured":"Lee, J., Cho, S., Beack, S.K.: Context-adaptive entropy model for end-to-end optimized image compression. In: 6th International Conference on Learning Representations, ICLR 2018 (2018)"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Lee-Thorp, J., Ainslie, J., Eckstein, I., Ontanon, S.: FNet: mixing tokens with Fourier transforms. arXiv preprint arXiv:2105.03824 (2021)","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Li, D., et al.: Involution: inverting the inherence of convolution for visual recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12321\u201312330 (2021)","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"26_CR30","doi-asserted-by":"publisher","first-page":"5900","DOI":"10.1109\/TIP.2020.2985225","volume":"29","author":"M Li","year":"2020","unstructured":"Li, M., Ma, K., You, J., Zhang, D., Zuo, W.: Efficient and effective context-based convolutional entropy modeling for image compression. IEEE Transactions on Image Processing 29, 5900\u20135911 (2020). DOI: 10.1109\/TIP.2020.2985225","journal-title":"IEEE Trans. Image Process."},{"key":"26_CR31","unstructured":"Liu, H., Chen, T., Shen, Q., Ma, Z.: Practical stacked non-local attention modules for image compression. In: CVPR Workshops (2019)"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Mentzer, F., Agustsson, E., Tschannen, M., Timofte, R., Van Gool, L.: Conditional probability models for deep image compression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4394\u20134402 (2018)","DOI":"10.1109\/CVPR.2018.00462"},{"key":"26_CR33","unstructured":"Minnen, D., Ball\u00e9, J., Toderici, G.: Joint autoregressive and hierarchical priors for learned image compression. In: NeurIPS (2018)"},{"key":"26_CR34","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), pp. 3339\u20133343. IEEE (2020)","DOI":"10.1109\/ICIP40778.2020.9190935"},{"key":"26_CR35","unstructured":"Naseer, M., Ranasinghe, K., Khan, S., Hayat, M., Khan, F.S., Yang, M.H.: Intriguing properties of vision transformers. arXiv preprint arXiv:2105.10497 (2021)"},{"key":"26_CR36","doi-asserted-by":"publisher","unstructured":"Niu, Z., Zhong, G., Yu, H.: A review on the attention mechanism of deep learning. Neurocomputing 452, 48\u201362 (2021). https:\/\/doi.org\/10.1016\/j.neucom.2021.03.091. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S092523122100477X","DOI":"10.1016\/j.neucom.2021.03.091"},{"key":"26_CR37","unstructured":"Parmar, N., et al.: Image transformer. In: International Conference on Machine Learning, pp. 4055\u20134064. PMLR (2018)"},{"key":"26_CR38","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":"26_CR39","unstructured":"Qian, Y., et al.: Learning accurate entropy model with global reference for image compression. In: International Conference on Learning Representations (2020)"},{"issue":"2","key":"26_CR40","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1147\/rd.232.0149","volume":"23","author":"J Rissanen","year":"1979","unstructured":"Rissanen, J., Langdon, G.G.: Arithmetic coding. IBM Journal of research and development 23(2), 149\u2013162 (1979)","journal-title":"IBM J. Res. Dev."},{"key":"26_CR41","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1162\/tacl_a_00353","volume":"9","author":"A Roy","year":"2021","unstructured":"Roy, A., Saffar, M., Vaswani, A., Grangier, D.: Efficient content-based sparse attention with routing transformers. Transactions of the Association for Computational Linguistics 9, 53\u201368 (2021)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Sullivan, G., Ohm, J., Han, W.J., Wiegand, T.: Overview of the high efficiency video coding standard vol. 22, pp. 1648\u20131667 (2012)","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"26_CR43","unstructured":"Team, J.V.E.: Versatile video coding (vvc) reference software: Vvc test model (vtm) (2022). Accessed 01 Jun 2022. https:\/\/vcgit.hhi.fraunhofer.de\/jvet\/VVCSoftware\/_VTM"},{"key":"26_CR44","unstructured":"Toderici, G., et al.: Workshop and challenge on learned image compression (clic2020)"},{"key":"26_CR45","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in neural information processing systems, pp. 5998\u20136008 (2017)"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Wallace, G.K.: The jpeg still picture compression standard. IEEE Trans. Cons. Electr. 38(1), xviii-xxxiv (1992)","DOI":"10.1109\/30.125072"},{"key":"26_CR47","unstructured":"Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, vol. 2, pp. 1398\u20131402. IEEE (2003)"},{"key":"26_CR48","unstructured":"Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, vol. 2, pp. 1398\u20131402. IEEE (2003)"},{"issue":"8","key":"26_CR49","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. International Journal of Computer Vision (IJCV) 127(8), 1106\u20131125 (2019)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"26_CR50","unstructured":"Zhang, Y., Li, K., Li, K., Zhong, B., Fu, Y.: Residual non-local attention networks for image restoration. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=HkeGhoA5FX"},{"key":"26_CR51","doi-asserted-by":"crossref","unstructured":"Zhao, J., Li, B., Li, J., Xiong, R., Lu, Y.: A universal encoder rate distortion optimization framework for learned compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1880\u20131884 (2021)","DOI":"10.1109\/CVPRW53098.2021.00210"},{"key":"26_CR52","unstructured":"Zhou, J., Wen, S., Nakagawa, A., Kazui, K., Tan, Z.: Multi-scale and context-adaptive entropy model for image compression. arXiv preprint arXiv:1910.07844 (2019)"},{"issue":"3","key":"26_CR53","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1109\/TIT.1985.1057034","volume":"31","author":"J Ziv","year":"1985","unstructured":"Ziv, J.: On universal quantization. IEEE Transactions on Information Theory 31(3), 344\u2013347 (1985)","journal-title":"IEEE Trans. Inf. Theory"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19800-7_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T12:17:12Z","timestamp":1667909832000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19800-7_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197994","9783031198007"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19800-7_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"9 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}