{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T17:31:39Z","timestamp":1772213499439,"version":"3.50.1"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585389","type":"print"},{"value":"9783030585396","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58539-6_29","type":"book-chapter","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T19:02:46Z","timestamp":1604689366000},"page":"482-499","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Controlling Style and Semantics in Weakly-Supervised Image Generation"],"prefix":"10.1007","author":[{"given":"Dario","family":"Pavllo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aurelien","family":"Lucchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Hofmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"29_CR1","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2019)"},{"key":"29_CR2","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 (CVPR), pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"issue":"4","key":"29_CR3","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","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. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 40(4), 834\u2013848 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q., Koltun, V.: Photographic image synthesis with cascaded refinement networks. In: IEEE International Conference on Computer Vision (ICCV), pp. 1511\u20131520 (2017)","DOI":"10.1109\/ICCV.2017.168"},{"key":"29_CR5","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"29_CR6","unstructured":"Cheng, Y., Gan, Z., Li, Y., Liu, J., Gao, J.: Sequential attention GAN for interactive image editing via dialogue. arXiv preprint arXiv:1812.08352 (2018)"},{"key":"29_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"El-Nouby, A., et al.: Tell, draw, and repeat: generating and modifying images based on continual linguistic instruction. In: IEEE International Conference on Computer Vision (ICCV), pp. 10304\u201310312 (2019)","DOI":"10.1109\/ICCV.2019.01040"},{"key":"29_CR9","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"issue":"11","key":"29_CR12","doi-asserted-by":"publisher","first-page":"5464","DOI":"10.1109\/TIP.2019.2916751","volume":"28","author":"Z He","year":"2019","unstructured":"He, Z., Zuo, W., Kan, M., Shan, S., Chen, X.: Attgan: facial attribute editing by only changing what you want. IEEE Trans. Image Process. 28(11), 5464\u20135478 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"29_CR13","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)"},{"key":"29_CR14","unstructured":"Hinz, T., Heinrich, S., Wermter, S.: Generating multiple objects at spatially distinct locations. arXiv preprint arXiv:1901.00686 (2019)"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Hong, S., Yang, D., Choi, J., Lee, H.: Inferring semantic layout for hierarchical text-to-image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7986\u20137994 (2018)","DOI":"10.1109\/CVPR.2018.00833"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Hu, R., Doll\u00e1r, P., He, K., Darrell, T., Girshick, R.: Learning to segment every thing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4233\u20134241 (2018)","DOI":"10.1109\/CVPR.2018.00445"},{"key":"29_CR17","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 (CVPR), pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1219\u20131228 (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Joseph, K., Pal, A., Rajanala, S., Balasubramanian, V.N.: C4Synth: cross-caption cycle-consistent text-to-image synthesis. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 358\u2013366. IEEE (2019)","DOI":"10.1109\/WACV.2019.00044"},{"key":"29_CR20","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2018)"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: 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 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"29_CR22","unstructured":"Kilcher, Y., Lucchi, A., Hofmann, T.: Semantic interpolation in implicit models. arXiv preprint arXiv:1710.11381 (2018)"},{"key":"29_CR23","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2014)"},{"key":"29_CR24","unstructured":"Kiros, R., et al.: Skip-thought vectors. In: Advances in Neural Information Processing Systems, pp. 3294\u20133302 (2015)"},{"issue":"1","key":"29_CR25","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. (IJCV) 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"29_CR26","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":"29_CR27","unstructured":"Locatello, F., Bauer, S., Lucic, M., Gelly, S., Sch\u00f6lkopf, B., Bachem, O.: Challenging common assumptions in the unsupervised learning of disentangled representations. In: International Conference on Machine Learning, pp. 4114\u20134124 (2019)"},{"key":"29_CR28","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)"},{"key":"29_CR29","unstructured":"Miyato, T., Koyama, M.: cGANs with projection discriminator. arXiv preprint arXiv:1802.05637 (2018)"},{"key":"29_CR30","unstructured":"Mo, S., Cho, M., Shin, J.: Instance-aware image-to-image translation. arXiv preprint arXiv:1812.10889 (2019)"},{"key":"29_CR31","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 (CVPR), pp. 2337\u20132346 (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Qi, X., Chen, Q., Jia, J., Koltun, V.: Semi-parametric image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8808\u20138816 (2018)","DOI":"10.1109\/CVPR.2018.00918"},{"key":"29_CR33","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. arXiv preprint arXiv:1605.05396 (2016)"},{"key":"29_CR34","unstructured":"Reed, S., van den Oord, A., Kalchbrenner, N., Bapst, V., Botvinick, M., de Freitas, N.: Generating interpretable images with controllable structure. Open Rev. (2016)"},{"key":"29_CR35","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"29_CR36","unstructured":"Sharma, S., Suhubdy, D., Michalski, V., Kahou, S.E., Bengio, Y.: Chatpainter: improving text to image generation using dialogue. arXiv preprint arXiv:1802.08216 (2018)"},{"key":"29_CR37","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Singh, K.K., Ojha, U., Lee, Y.J.: FineGAN: unsupervised hierarchical disentanglement for fine-grained object generation and discovery. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6490\u20136499 (2019)","DOI":"10.1109\/CVPR.2019.00665"},{"key":"29_CR39","unstructured":"Srivastava, R.K., Greff, K., Schmidhuber, J.: Highway networks. arXiv preprint arXiv:1505.00387 (2015)"},{"key":"29_CR40","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 (ICCV), pp. 10531\u201310540 (2019)","DOI":"10.1109\/ICCV.2019.01063"},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"29_CR42","first-page":"8901","volume":"33","author":"MO Turkoglu","year":"2019","unstructured":"Turkoglu, M.O., Thong, W., Spreeuwers, L., Kicanaoglu, B.: A layer-based sequential framework for scene generation with GANs. Proc. AAAI Conf. Artif. Intell. 33, 8901\u20138908 (2019)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"29_CR43","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"29_CR44","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 (CVPR), pp. 8798\u20138807 (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1316\u20131324 (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"29_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-319-46493-0_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Yan","year":"2016","unstructured":"Yan, X., Yang, J., Sohn, K., Lee, H.: Attribute2Image: conditional image generation from visual attributes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 776\u2013791. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_47"},{"key":"29_CR47","unstructured":"Yang, J., Kannan, A., Batra, D., Parikh, D.: LR-GAN: layered recursive generative adversarial networks for image generation. arXiv preprint arXiv:1703.01560 (2017)"},{"key":"29_CR48","doi-asserted-by":"crossref","unstructured":"Yin, G., Liu, B., Sheng, L., Yu, N., Wang, X., Shao, J.: Semantics disentangling for text-to-image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2327\u20132336 (2019)","DOI":"10.1109\/CVPR.2019.00243"},{"key":"29_CR49","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: International Conference on Machine Learning (ICML), pp. 7354\u20137363 (2019)"},{"key":"29_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 5907\u20135915 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"issue":"8","key":"29_CR51","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2018","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., Metaxas, D.N.: StackGAN++: realistic image synthesis with stacked generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 41(8), 1947\u20131962 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"29_CR52","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 (CVPR), pp. 8584\u20138593 (2019)","DOI":"10.1109\/CVPR.2019.00878"},{"key":"29_CR53","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 (ICCV), pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58539-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:16:30Z","timestamp":1730852190000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58539-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585389","9783030585396"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58539-6_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"7 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}