{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T09:31:22Z","timestamp":1758274282997,"version":"3.40.3"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031373190"},{"type":"electronic","value":"9783031373206"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-37320-6_2","type":"book-chapter","created":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T09:02:55Z","timestamp":1688634175000},"page":"24-48","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-stage Conditional GAN Architectures for\u00a0Person-Image Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4530-9717","authenticated-orcid":false,"given":"Sheela Raju","family":"Kurupathi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3299-3655","authenticated-orcid":false,"given":"Veeru","family":"Dumpala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Didier","family":"Stricker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,7]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","unstructured":"Kurupathi, S., Murthy, P., Stricker, D.: Generation of Human Images with Clothing using Advanced Conditional Generative Adversarial Networks. In: Proceedings of the 1st International Conference on Deep Learning Theory and Applications, pp. 30\u201341. SciTePress, France (2020). https:\/\/doi.org\/10.5220\/0009832200300041","DOI":"10.5220\/0009832200300041"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Alp G\u00fcler, R., Neverova, N., Kokkinos, I.: Densepose: Dense human poseestimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision andPattern Recognition, pp. 7297\u20137306 (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"2_CR3","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":"2_CR4","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":"2_CR5","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Sangineto, E., Lathuili\u00e8re, S., Sebe, N.: Deformable gansfor pose-based human image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3408\u20133416 (2018)","DOI":"10.1109\/CVPR.2018.00359"},{"key":"2_CR6","unstructured":"Walsh, J., et al.: Deep learning vs. traditionalcomputer vision (2019)"},{"key":"2_CR7","unstructured":"R\u00f6ssler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nie\u00dfner, M.: Faceforensics: A large-scale video dataset for forgery detection in human faces. arXivpreprint arXiv:1803.09179 (2018)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.-E., Sheikh, Y.: Realtime multi-person 2d poseestimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"2_CR9","unstructured":"Stewart, M.: Advanced Topics in Gen-erativeAdversarialNetworks(GANs). https:\/\/towardsdatascience.com\/comprehensive-introduction-to-turing-learning-and-gans-part-2-fd8e4a70775 (2019) (Accessed May 8 2019)"},{"key":"2_CR10","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification withdeep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for imagerecognition. In: Proceedings of the IEEE Conference on Computer Vision and Patternrecognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference On Computer Vision And Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2_CR13","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-imagetranslation 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":"2_CR15","unstructured":"Kim, T., Cha, M., Kim, H., Lee, J. K., Kim, J.: Learning to discovercross-domain relations with generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 1857\u20131865. JMLR. org (2017)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation withconditional adversarial networks. In: Proceedings of the IEEE on Computervision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Si, C., Wang, W., Wang, L., Tan, T.: Multistage adversarial losses forpose-based human image synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 118\u2013126 (2018)","DOI":"10.1109\/CVPR.2018.00020"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Lassner, C., Pons-Moll, G., Gehler, P.V.: A generative model of peoplein clothing. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 853\u2013862 (2017)","DOI":"10.1109\/ICCV.2017.98"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Omran, M., Lassner, C., Pons-Moll, G., Gehler, P., Schiele, B.: Neural bodyfitting: Unifying deep learning and model based human pose and shape estimation. In: 2018 International Conference on 3D Vision (3DV), pp. 484\u2013494. IEEE (2018)","DOI":"10.1109\/3DV.2018.00062"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: A skinned multi-person linear model. ACM Trans. Graph. (TOG), 34(6), 248 (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"2_CR21","unstructured":"Tang, W., Li, T., Nian, F., Wang, M.: Mscgan: Multi-scale conditional generative adversarial networks for person image generation. CoRR, abs\/1810.08534 (2018)"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Balakrishnan, G., Zhao, A., Dalca, A. V., Durand, F., Guttag, J.: Synthesizing images of humans in unseen poses. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8340\u20138348 (2018)","DOI":"10.1109\/CVPR.2018.00870"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Huang, T., Shi, B., Yu, M., Wang, B., Bai, X.: Progressive pose attention transfer for person image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2347\u20132356 (2019)","DOI":"10.1109\/CVPR.2019.00245"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Esser, P., Sutter, E., Ommer, B.: A variational u-net for conditional appear-ance and shape generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8857\u20138866 (2018)","DOI":"10.1109\/CVPR.2018.00923"},{"key":"2_CR25","unstructured":"Kingma, D.P, Welling, M.: Auto-encoding variational bayes (2013) arXiv preprint arXiv:1312.6114"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Neverova, N., Alp Guler, R., Kokkinos, I.: Dense pose transfer. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 123\u2013138 (2018)","DOI":"10.1007\/978-3-030-01219-9_8"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Horiuchi, Y., Iizuka, S., Simo-Serra, E., Ishikawa, H.: Spectral normalizationand relativistic adversarial training for conditional pose generation with self-attention. In: 2019 16th International Conference on Machine Vision Applications (MVA), pp. 1\u20135. IEEE (2019)","DOI":"10.23919\/MVA.2019.8758013"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Zanfir, M., Popa, A.-I., Zanfir, A., Sminchisescu, C.: Human appear-ance transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5391\u20135399 (2018)","DOI":"10.1109\/CVPR.2018.00565"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Han, X., Wu, Z., Wu, Z., Yu, R., Davis, L.S.: Viton: An image-basedvirtual try-on network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7543\u20137552 (2018)","DOI":"10.1109\/CVPR.2018.00787"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Wang, B., Zheng, H., Liang, X., Chen, Y., Lin, L., Yang, M.: Toward characteristic-preserving image-based virtual try-on network. In: Proceedings of theEuropean Conference on Computer Vision (ECCV), pages 589\u2013604 (2018)","DOI":"10.1007\/978-3-030-01261-8_36"},{"key":"2_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1007\/978-3-030-01258-8_41","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Raj","year":"2018","unstructured":"Raj, A., Sangkloy, P., Chang, H., Hays, J., Ceylan, D., Lu, J.: SwapNet: image based garment transfer. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 679\u2013695. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_41"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, B., Wu, X., Cheng, Z.-Q., Liu, H., Jie, Z., Feng, J.: Multi-view imagegeneration from a single-view. In: 2018 ACM Multimedia Conference on Multimedia Conference, pp. 383\u2013391. ACM (2018)","DOI":"10.1145\/3240508.3240536"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, X., Huang, Q., Sun, X., Xue, X., Wei, Y.: Towards 3d humanpose estimation in the wild: a weakly-supervised approach. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 398\u2013407 (2017)","DOI":"10.1109\/ICCV.2017.51"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Tome, D., Russell, C., Agapito, L.: Lifting from the deep: Convolutional 3dpose estimation from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2500\u20132509 (2017)","DOI":"10.1109\/CVPR.2017.603"},{"key":"2_CR35","unstructured":"Zhihui, S., Ming, Y., Guohui, Z., Lei, D., Jianda, S.: Cascade Feature Aggregation for Human Pose Estimation (2019). CoRR abs\/1902.07837"},{"key":"2_CR36","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. (2015) arXiv preprint arXiv: 1511.06434"},{"key":"2_CR37","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, pp. 5907\u20135915 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"2_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Carreira, J., Agrawal, P., Fragkiadaki, K., Malik, J.: Human pose estimationwith iterative error feedback. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4733\u20134742 (2016)","DOI":"10.1109\/CVPR.2016.512"},{"key":"2_CR40","unstructured":"Quan, T.M., Hildebrand, D.G., Jeong, W.-K.: Fusionnet: A deep fullyresidual convolutional neural network for image segmentation in connectomics. (2016) arXivpreprint arXiv:1612.05360"},{"key":"2_CR41","unstructured":"Srisha, R., Khan, A.: Morphological operations for image processing : Understanding and its applications (2013)"},{"key":"2_CR42","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video predictionbeyond mean square error (2015). arXiv preprint arXiv:1511.05440"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable personre-identification: A benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1116\u20131124 (2015)","DOI":"10.1109\/ICCV.2015.133"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Qiu, S., Wang, X., Tang, X.: Deepfashion: Poweringrobust 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":"2_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P., et al.: Image qualityassessment: from error visibility to structural similarity. IEEE Trans. Image Process.13(4):600\u2013612 (2004)","DOI":"10.1109\/TIP.2003.819861"},{"key":"2_CR46","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. In: Advances in Neural Information Processing Systems, pp. 2234\u20132242 (2016)"},{"key":"2_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"2_CR48","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge 2007 (voc2007) results (2007)"},{"key":"2_CR49","unstructured":"Kingma, D.P. Ba, J.: Adam: A method for stochastic optimization (2014). arXivpreprint arXiv:1412.6980"},{"key":"2_CR50","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop, coursera: Neural networksf or machine learning. University of Toronto, Technical Report (2012)"},{"key":"2_CR51","unstructured":"Schaul, T., Zhang, S., LeCun, Y.: No more pesky learning rates. In: International Conference on Machine Learning, pp. 343\u2013351 (2013)"},{"key":"2_CR52","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generativeadversarial networks (2018). arXiv preprint arXiv:1805.08318"}],"container-title":["Communications in Computer and Information Science","Deep Learning Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-37320-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T09:04:39Z","timestamp":1688634279000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-37320-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031373190","9783031373206"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-37320-6_2","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"7 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DeLTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Deep Learning Theory and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 July 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 July 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"delta2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/delta.scitevents.org\/?y=2020","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":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28","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":"4","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":"8","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":"14% - 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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}