{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T21:51:41Z","timestamp":1757541101938,"version":"3.40.3"},"publisher-location":"Cham","reference-count":70,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031197864"},{"type":"electronic","value":"9783031197871"}],"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\/978-3-031-19787-1_7","type":"book-chapter","created":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T22:16:11Z","timestamp":1666304171000},"page":"110-127","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Auto-regressive Image Synthesis with\u00a0Integrated Quantization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1502-6847","authenticated-orcid":false,"given":"Fangneng","family":"Zhan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7893-0764","authenticated-orcid":false,"given":"Yingchen","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5586-0628","authenticated-orcid":false,"given":"Rongliang","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9059-7546","authenticated-orcid":false,"given":"Jiahui","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1007-5113","authenticated-orcid":false,"given":"Kaiwen","family":"Cui","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9194-0465","authenticated-orcid":false,"given":"Changgong","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6766-2506","authenticated-orcid":false,"given":"Shijian","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,21]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: COCO-Stuff: thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Chen, L., Srivastava, S., Duan, Z., Xu, C.: Deep cross-modal audio-visual generation. In: Proceedings of the on Thematic Workshops of ACM Multimedia 2017, pp. 349\u2013357 (2017)","DOI":"10.1145\/3126686.3126723"},{"key":"7_CR3","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: International Conference on Machine Learning, pp. 1691\u20131703. PMLR (2020)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: StarGAN v2: diverse image synthesis for multiple domains. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8188\u20138197 (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"7_CR5","unstructured":"Doersch, C.: Tutorial on variational autoencoders. arXiv preprint arXiv:1606.05908 (2016)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"7_CR7","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"7_CR8","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, pp. 6626\u20136637 (2017)"},{"issue":"8","key":"7_CR9","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"7_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-030-01219-9_11","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Huang","year":"2018","unstructured":"Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 179\u2013196. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_11"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"7_CR13","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)"},{"key":"7_CR14","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)"},{"key":"7_CR15","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"issue":"10","key":"7_CR16","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1007\/s11263-019-01284-z","volume":"128","author":"HY Lee","year":"2020","unstructured":"Lee, H.Y., et al.: DRIT++: diverse image-to-image translation via disentangled representations. Int. J. Comput. Vis. 128(10), 2402\u20132417 (2020). https:\/\/doi.org\/10.1007\/s11263-019-01284-z","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"7_CR17","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1109\/TMM.2018.2856090","volume":"21","author":"B Li","year":"2018","unstructured":"Li, B., Liu, X., Dinesh, K., Duan, Z., Sharma, G.: Creating a multitrack classical music performance dataset for multimodal music analysis: challenges, insights, and applications. IEEE Trans. Multimed. 21(2), 522\u2013535 (2018)","journal-title":"IEEE Trans. Multimed."},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Cheng, Y., Gan, Z., Yu, L., Wang, L., Liu, J.: BachGAN: high-resolution image synthesis from salient object layout. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00839"},{"key":"7_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., Meng, F., Chen, Y., Xu, J., Zhou, J.: Confidence-aware scheduled sampling for neural machine translation. arXiv preprint arXiv:2107.10427 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.205"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: DeepFashion: powering robust clothes recognition and retrieval with rich annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1096\u20131104 (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730\u20133738 (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"7_CR23","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"7_CR24","unstructured":"Lucas, J., Tucker, G., Grosse, R., Norouzi, M.: Don\u2019t blame the ELBO! A linear VAE perspective on posterior collapse. arXiv preprint arXiv:1911.02469 (2019)"},{"key":"7_CR25","unstructured":"Ma, L., Jia, X., Georgoulis, S., Tuytelaars, T., Van Gool, L.: Exemplar guided unsupervised image-to-image translation with semantic consistency. In: International Conference on Learning Representations (2018)"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. In: Advances in Neural Information Processing Systems, pp. 406\u2013416 (2017)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"7_CR27","unstructured":"Maddison, C.J., Tarlow, D., Minka, T.: A* sampling. In: NIPS (2014)"},{"issue":"4","key":"7_CR28","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/s10208-011-9093-5","volume":"11","author":"F M\u00e9moli","year":"2011","unstructured":"M\u00e9moli, F.: Gromov-Wasserstein distances and the metric approach to object matching. Found. Comput. Math. 11(4), 417\u2013487 (2011). https:\/\/doi.org\/10.1007\/s10208-011-9093-5","journal-title":"Found. Comput. Math."},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Men, Y., Mao, Y., Jiang, Y., Ma, W.Y., Lian, Z.: Controllable person image synthesis with attribute-decomposed GAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5084\u20135093 (2020)","DOI":"10.1109\/CVPR42600.2020.00513"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Mihaylova, T., Martins, A.F.: Scheduled sampling for transformers. arXiv preprint arXiv:1906.07651 (2019)","DOI":"10.18653\/v1\/P19-2049"},{"key":"7_CR31","unstructured":"Oord, A., et al.: Parallel WaveNet: fast high-fidelity speech synthesis. In: International Conference on Machine Learning, pp. 3918\u20133926. PMLR (2018)"},{"key":"7_CR32","unstructured":"van den Oord, A., Kalchbrenner, N., Vinyals, O., Espeholt, L., Graves, A., Kavukcuoglu, K.: Conditional image generation with PixelCNN decoders. arXiv preprint arXiv:1606.05328 (2016)"},{"key":"7_CR33","unstructured":"van den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. arXiv preprint arXiv:1711.00937 (2017)"},{"key":"7_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-030-58545-7_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Park","year":"2020","unstructured":"Park, T., Efros, A.A., Zhang, R., Zhu, J.-Y.: Contrastive learning for unpaired image-to-image translation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 319\u2013345. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_19"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2337\u20132346 (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"issue":"5\u20136","key":"7_CR36","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1561\/2200000073","volume":"11","author":"G Peyr\u00e9","year":"2019","unstructured":"Peyr\u00e9, G., Cuturi, M., et al.: Computational optimal transport: with applications to data science. Found. Trends\u00ae Mach. Learn. 11(5\u20136), 355\u2013607 (2019)","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Qiao, T., Zhang, J., Xu, D., Tao, D.: MirrorGAN: learning text-to-image generation by redescription. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1505\u20131514 (2019)","DOI":"10.1109\/CVPR.2019.00160"},{"issue":"8","key":"7_CR38","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"7_CR39","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092 (2021)"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Schmidt, F.: Generalization in generation: a closer look at exposure bias. arXiv preprint arXiv:1910.00292 (2019)","DOI":"10.18653\/v1\/D19-5616"},{"key":"7_CR41","unstructured":"Solomon, J.: Optimal transport on discrete domains. AMS Short Course on Discrete Differential Geometry (2018)"},{"key":"7_CR42","doi-asserted-by":"crossref","unstructured":"Sun, W., Wu, T.: Image synthesis from reconfigurable layout and style. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 10531\u201310540 (2019)","DOI":"10.1109\/ICCV.2019.01063"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Tang, H., Xu, D., Liu, G., Wang, W., Sebe, N., Yan, Y.: Cycle in cycle generative adversarial networks for keypoint-guided image generation. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 2052\u20132060 (2019)","DOI":"10.1145\/3343031.3350980"},{"key":"7_CR44","unstructured":"Van Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning, pp. 1747\u20131756. PMLR (2016)"},{"key":"7_CR45","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"7_CR46","unstructured":"Vayer, T., Flamary, R., Tavenard, R., Chapel, L., Courty, N.: Sliced Gromov-Wasserstein. arXiv preprint arXiv:1905.10124 (2019)"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Wang, M., et al.: Example-guided style-consistent image synthesis from semantic labeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1495\u20131504 (2019)","DOI":"10.1109\/CVPR.2019.00159"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8798\u20138807 (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"7_CR49","unstructured":"Welinder, P., et al.: Caltech-UCSD birds 200. California Institute of Technology (2010)"},{"key":"7_CR50","unstructured":"Wiggers, A., Hoogeboom, E.: Predictive sampling with forecasting autoregressive models. In: International Conference on Machine Learning, pp. 10260\u201310269. PMLR (2020)"},{"key":"7_CR51","unstructured":"Xu, H., Luo, D., Henao, R., Shah, S., Carin, L.: Learning autoencoders with relational regularization. In: International Conference on Machine Learning, pp. 10576\u201310586. PMLR (2020)"},{"key":"7_CR52","unstructured":"Xu, H., Luo, D., Zha, H., Duke, L.C.: Gromov-Wasserstein learning for graph matching and node embedding. In: International Conference on Machine Learning, pp. 6932\u20136941. PMLR (2019)"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Yu, Y., et al.: Towards counterfactual image manipulation via clip. arXiv preprint arXiv:2207.02812 (2022)","DOI":"10.1145\/3503161.3547935"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Zhan, F., Xue, C., Lu, S.: GA-DAN: geometry-aware domain adaptation network for scene text detection and recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9105\u20139115 (2019)","DOI":"10.1109\/ICCV.2019.00920"},{"key":"7_CR55","doi-asserted-by":"crossref","unstructured":"Zhan, F., et al.: Unbalanced feature transport for exemplar-based image translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.31219\/osf.io\/f6vur"},{"key":"7_CR56","doi-asserted-by":"crossref","unstructured":"Zhan, F., et al.: Bi-level feature alignment for versatile image translation and manipulation. arXiv preprint arXiv:2107.03021 (2021)","DOI":"10.1007\/978-3-031-19787-1_13"},{"key":"7_CR57","doi-asserted-by":"crossref","unstructured":"Zhan, F., et al.: GMLight: lighting estimation via geometric distribution approximation. arXiv preprint arXiv:2102.10244 (2021)","DOI":"10.1109\/TIP.2022.3151997"},{"key":"7_CR58","unstructured":"Zhan, F., Yu, Y., Wu, R., Zhang, J., Lu, S.: Multimodal image synthesis and editing: a survey. arXiv preprint arXiv:2112.13592 (2021)"},{"key":"7_CR59","doi-asserted-by":"crossref","unstructured":"Zhan, F., Yu, Y., Wu, R., Zhang, J., Lu, S., Zhang, C.: Marginal contrastive correspondence for guided image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10663\u201310672 (2022)","DOI":"10.1109\/CVPR52688.2022.01040"},{"key":"7_CR60","doi-asserted-by":"crossref","unstructured":"Zhan, F., Zhang, C.: Spatial-aware GAN for unsupervised person re-identification. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 6889\u20136896. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412465"},{"key":"7_CR61","doi-asserted-by":"crossref","unstructured":"Zhan, F., et al.: EMLight: lighting estimation via spherical distribution approximation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 3287\u20133295 (2021)","DOI":"10.1609\/aaai.v35i4.16440"},{"key":"7_CR62","doi-asserted-by":"crossref","unstructured":"Zhan, F., Zhang, J., Yu, Y., Wu, R., Lu, S.: Modulated contrast for versatile image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18280\u201318290 (2022)","DOI":"10.1109\/CVPR52688.2022.01774"},{"key":"7_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, P., Zhang, B., Chen, D., Yuan, L., Wen, F.: Cross-domain correspondence learning for exemplar-based image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5143\u20135153 (2020)","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"7_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"7_CR65","doi-asserted-by":"crossref","unstructured":"Zhao, B., Meng, L., Yin, W., Sigal, L.: Image generation from layout. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8584\u20138593 (2019)","DOI":"10.1109\/CVPR.2019.00878"},{"key":"7_CR66","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"7_CR67","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"7_CR68","unstructured":"Zhu, J.Y., et al.: Toward multimodal image-to-image translation. In: Advances in Neural Information Processing Systems 2017, pp. 466\u2013477 (2017)"},{"key":"7_CR69","doi-asserted-by":"crossref","unstructured":"Zhu, P., Abdal, R., Qin, Y., Wonka, P.: SEAN: image synthesis with semantic region-adaptive normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5104\u20135113 (2020)","DOI":"10.1109\/CVPR42600.2020.00515"},{"key":"7_CR70","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xu, Z., You, A., Bai, X.: Semantically multi-modal image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5467\u20135476 (2020)","DOI":"10.1109\/CVPR42600.2020.00551"}],"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\/978-3-031-19787-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:16:49Z","timestamp":1710357409000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19787-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197864","9783031197871"],"references-count":70,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19787-1_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"21 October 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)"}}]}}