{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T10:18:13Z","timestamp":1743157093507,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031783883"},{"type":"electronic","value":"9783031783890"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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\/978-3-031-78389-0_20","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T14:13:49Z","timestamp":1733321629000},"page":"293-309","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantically Consistent Person Image Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1733-5670","authenticated-orcid":false,"given":"Prasun","family":"Roy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1273-7969","authenticated-orcid":false,"given":"Saumik","family":"Bhattacharya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3242-3406","authenticated-orcid":false,"given":"Subhankar","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5426-2618","authenticated-orcid":false,"given":"Umapada","family":"Pal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9908-3744","authenticated-orcid":false,"given":"Michael","family":"Blumenstein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"20_CR1","unstructured":"Bhunia, A.K., Khan, S., Cholakkal, H., Anwer, R.M., Laaksonen, J., Shah, M., Khan, F.S.: Person image synthesis via denoising diffusion model. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., Zhang, Y., Zou, Z., Chen, K., Shi, Z.: Dense pixel-to-pixel harmonization via continuous image representation. arXiv preprint arXiv:2303.01681 (2023)","DOI":"10.1109\/TCSVT.2023.3324591"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Cheong, S.Y., Mustafa, A., Gilbert, A.: UPGPT: Universal diffusion model for person image generation, editing and pose transfer. In: The IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops (2023)","DOI":"10.1109\/ICCVW60793.2023.00451"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: A large-scale hierarchical image database. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Esser, P., Sutter, E., Ommer, B.: A variational U-Net for conditional appearance and shape generation. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00923"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Gafni, O., Wolf, L.: Wish you were here: Context-aware human generation. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00786"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"G\u00fcler, R.A., Neverova, N., Kokkinos, I.: Densepose: Dense human pose estimation in the wild. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"20_CR9","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $$<$$0.5mb model size. arXiv preprint arXiv:1602.07360 (2016)"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-Image translation with conditional adversarial networks. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Ke, Z., Sun, C., Zhu, L., Xu, K., Lau, R.W.: Harmonizer: Learning to perform white-box image and video harmonization. In: The European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19784-0_40"},{"key":"20_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: The International Conference on Learning Representations (ICLR) (2015)"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Kulal, S., Brooks, T., Aiken, A., Wu, J., Yang, J., Lu, J., Efros, A.A., Singh, K.K.: Putting people in their place: Affordance-aware human insertion into scenes. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01639"},{"key":"20_CR14","unstructured":"Lee, D., Liu, S., Gu, J., Liu, M.Y., Yang, M.H., Kautz, J.: Context-aware synthesis and placement of object instances. In: The Conference on Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"20_CR15","unstructured":"Li, J., Zhao, J., Wei, Y., Lang, C., Li, Y., Sim, T., Yan, S., Feng, J.: Multiple-human parsing in the wild. arXiv preprint arXiv:1705.07206 (2017)"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, C., Loy, C.C.: Dense intrinsic appearance flow for human pose transfer. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00381"},{"key":"20_CR17","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: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.124"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van\u00a0Gool, L.: Pose guided person image generation. In: The Conference on Neural Information Processing Systems (NeurIPS) (2017)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Ma, L., Sun, Q., Georgoulis, S., Van\u00a0Gool, L., Schiele, B., Fritz, M.: Disentangled person image generation. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"20_CR20","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: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00513"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Neverova, N., Guler, R.A., Kokkinos, I.: Dense pose transfer. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01219-9_8"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Ren, Y., Fan, X., Li, G., Liu, S., Li, T.H.: Neural texture extraction and distribution for controllable person image synthesis. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01317"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Ren, Y., Yu, X., Chen, J., Li, T.H., Li, G.: Deep image spatial transformation for person image generation. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00771"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Sangineto, E., Lathuili\u00e8re, S., Sebe, N.: Deformable GANs for pose-based human image generation. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00359"},{"key":"20_CR26","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: The International Conference on Learning Representations (ICLR) (2015)"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Tan, F., Bernier, C., Cohen, B., Ordonez, V., Barnes, C.: Where and who? automatic semantic-aware person composition. In: The IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2018)","DOI":"10.1109\/WACV.2018.00170"},{"key":"20_CR29","unstructured":"Tang, H., Bai, S., Torr, P.H., Sebe, N.: Bipartite graph reasoning GANs for person image generation. In: The British Machine Vision Conference (BMVC) (2020)"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Tang, H., Bai, S., Zhang, L., Torr, P.H., Sebe, N.: XingGAN for person image generation. In: The European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58595-2_43"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, K., Lai, Y.K., Yang, J.: PISE: Person image synthesis and editing with decoupled gan. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00789"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, P., Yang, L., Lai, J.H., Xie, X.: Exploring dual-task correlation for pose guided person image generation. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00756"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shen, X., Lin, Z., Sunkavalli, K., Price, B., Jia, J.: Compositing-aware image search. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01219-9_31"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Zhou, X., Huang, S., Li, B., Li, Y., Li, J., Zhang, Z.: Text guided person image synthesis. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00378"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yin, M., Chen, X., Sun, L., Gao, C., Li, Q.: Cross attention based style distribution for controllable person image synthesis. In: The European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19784-0_10"},{"key":"20_CR36","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: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00245"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78389-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T15:08:27Z","timestamp":1733324907000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78389-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031783883","9783031783890"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78389-0_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}