{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:28:31Z","timestamp":1740122911661,"version":"3.37.3"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T00:00:00Z","timestamp":1726704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T00:00:00Z","timestamp":1726704000000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-20187-x","type":"journal-article","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T03:33:55Z","timestamp":1726716835000},"page":"167-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-driven clothed human image synthesis with 3D human model estimation for assistance in shopping"],"prefix":"10.1007","volume":"84","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-008X","authenticated-orcid":false,"given":"S.","family":"Karkuzhali","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. Syed","family":"Aasim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"StalinRaj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,19]]},"reference":[{"issue":"3","key":"20187_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447648","volume":"40","author":"R Abdal","year":"2021","unstructured":"Abdal R, Zhu P, Mitra NJ, Wonka P (2021) Styleflow: attribute-conditioned exploration of stylegan-generated images using conditional continuous normalizing flows. ACM Trans Graph (ToG) 40(3):1\u201321","journal-title":"ACM Trans Graph (ToG)"},{"issue":"6","key":"20187_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3478513.3480559","volume":"40","author":"B Albahar","year":"2021","unstructured":"Albahar B, Lu J, Yang J, Shu Z, Shechtman E, Huang JB (2021) Pose with style: detail-preserving pose-guided image synthesis with conditional stylegan. ACM Trans Graph (TOG) 40(6):1\u201311","journal-title":"ACM Trans Graph (TOG)"},{"key":"20187_CR3","doi-asserted-by":"publisher","unstructured":"Balakrishnan G, Zhao A, Dalca AV, Durand F, Guttag J (2018) Synthesizing images of humans in unseen poses. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8340\u20138348. https:\/\/doi.org\/10.48550\/arXiv.1804.07739","DOI":"10.48550\/arXiv.1804.07739"},{"key":"20187_CR4","doi-asserted-by":"publisher","unstructured":"Bond-Taylor S, Hessey P, Sasaki H, Breckon TP, Willcocks CG (2022) Unleashing transformers: parallel token prediction with discrete absorbing diffusion for fast high-resolution image generation from vector-quantized codes. In\u00a0European conference on computer vision. Springer Nature Switzerland, Cham, pp 170\u2013188. https:\/\/doi.org\/10.1007\/978-3-031-20050-2_11","DOI":"10.1007\/978-3-031-20050-2_11"},{"key":"20187_CR5","doi-asserted-by":"publisher","unstructured":"Zhang M, Cai Z, Pan L, Hong F, Guo X, Yang L, Liu Z (2024) Motion diffuse: text-driven human motion generation with the diffusion model. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2024.3355414","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"20187_CR6","unstructured":"Brock A, Donahue J, Simonyan K (2018) Large-scale GAN training for high-fidelity natural image synthesis. arXiv preprint arXiv:1809.11096. Accessed 10.04.2023"},{"key":"20187_CR7","doi-asserted-by":"publisher","unstructured":"Cai Z, Ren D, Zeng A, Lin Z, Yu T, Wang W, Fan X, Gao Y, Yu Y, Pan L, Hong F (2022) Human: Multi-modal 4D human dataset for versatile sensing and modeling. In European conference on computer vision. Springer Nature Switzerland, Cham, pp 557\u2013577. https:\/\/doi.org\/10.1007\/978-3-031-20071-7_33","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"20187_CR8","unstructured":"Li D, Chen D, Goh J, Ng SK (2018) Anomaly detection with generative adversarial networks for multivariate time series.\u00a0arXiv preprint arXiv:1809.04758. Accessed 10.04.2023"},{"key":"20187_CR9","doi-asserted-by":"publisher","unstructured":"Chai L, Gharbi M, Shechtman E, Isola P, Zhang R (2022) Any-resolution training for high-resolution image synthesis. In European conference on computer vision. Springer Nature Switzerland, Cham, pp 170\u2013188. https:\/\/doi.org\/10.1007\/978-3-031-19787-1_10","DOI":"10.1007\/978-3-031-19787-1_10"},{"key":"20187_CR10","doi-asserted-by":"publisher","unstructured":"Andriluka M, Pishchulin L, Gehler P, Schiele B (2014) 2D human pose estimation: new benchmark and state of the art analysis. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3686\u20133693. https:\/\/doi.org\/10.1109\/CVPR.2014.471","DOI":"10.1109\/CVPR.2014.471"},{"key":"20187_CR11","first-page":"19900","volume":"35","author":"A Bergman","year":"2022","unstructured":"Bergman A, Kellnhofer P, Yifan W, Chan E, Lindell D, Wetzstein G (2022) Generative neural articulated radiance fields. Adv Neural Inf Process Syst 35:19900\u201319916","journal-title":"Adv Neural Inf Process Syst"},{"key":"20187_CR12","doi-asserted-by":"publisher","unstructured":"Chan ER, Monteiro M, Kellnhofer P, Wu J, Wetzstein G (2021) pi-gan: Periodic implicit generative adversarial networks for 3D-aware image synthesis. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5799\u20135809. https:\/\/doi.org\/10.48550\/arXiv.2012.00926","DOI":"10.48550\/arXiv.2012.00926"},{"key":"20187_CR13","doi-asserted-by":"publisher","unstructured":"Chan ER, Lin CZ, Chan MA, Nagano K, Pan B, De Mello S, Gallo O, Guibas LJ, Tremblay J, Khamis S, Karras T (2022) Efficient geometry-aware 3d generative adversarial networks. In\u00a0Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16123\u201316133. https:\/\/doi.org\/10.48550\/arXiv.2112.07945","DOI":"10.48550\/arXiv.2112.07945"},{"key":"20187_CR14","doi-asserted-by":"publisher","unstructured":"Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, proceedings, Part VIII 14. Springer International Publishing, pp 483\u2013499. https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"20187_CR15","doi-asserted-by":"publisher","unstructured":"Zhu JY, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In proceedings of the IEEE international conference on computer vision, pp 2223\u20132232. https:\/\/doi.org\/10.48550\/arXiv.1703.10593","DOI":"10.48550\/arXiv.1703.10593"},{"key":"20187_CR16","doi-asserted-by":"publisher","unstructured":"Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In\u00a0computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part II 14\u00a0. Springer International Publishing, pp 694\u2013711. https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"20187_CR17","doi-asserted-by":"publisher","unstructured":"Sauer A, Karras T, Laine S, Geiger A, Aila T (2023) Stylegan-t: unlocking the power of gans for fast large-scale text-to-image synthesis. In\u00a0international conference on machine learning. PMLR, pp 30105\u201330118. https:\/\/doi.org\/10.48550\/arXiv.2301.09515","DOI":"10.48550\/arXiv.2301.09515"},{"key":"20187_CR18","doi-asserted-by":"publisher","unstructured":"Cui A, McKee D, Lazebnik S (2021) Dressing in order: recurrent person image generation for pose transfer, virtual try-on and outfit editing. In\u00a0proceedings of the IEEE\/CVF international conference on computer vision, pp 14638\u201314647. https:\/\/doi.org\/10.48550\/arXiv.2104.07021","DOI":"10.48550\/arXiv.2104.07021"},{"key":"20187_CR19","doi-asserted-by":"publisher","unstructured":"Alldieck T, Magnor M, Bhatnagar BL, Theobalt C, Pons-Moll G (2019) Learning to reconstruct people in clothing from a single RGB camera. In\u00a0proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1175\u20131186. https:\/\/doi.org\/10.48550\/arXiv.1903.05885","DOI":"10.48550\/arXiv.1903.05885"},{"key":"20187_CR20","doi-asserted-by":"publisher","unstructured":"Alldieck T, Magnor M, Xu W, Theobalt C, Pons-Moll G (2018) Detailed human avatars from monocular video. In\u00a02018 international conference on 3D vision (3DV). IEEE, pp 98\u2013109. https:\/\/doi.org\/10.48550\/arXiv.1808.01338","DOI":"10.48550\/arXiv.1808.01338"},{"key":"20187_CR21","doi-asserted-by":"publisher","unstructured":"Alldieck T, Magnor M, Xu W, Theobalt C, Pons-Moll G (2018) Video based reconstruction of 3d people models. In\u00a0proceedings of the IEEE conference on computer vision and pattern recognition, pp 8387\u20138397. https:\/\/doi.org\/10.48550\/arXiv.1803.04758","DOI":"10.48550\/arXiv.1803.04758"},{"key":"20187_CR22","doi-asserted-by":"publisher","unstructured":"Anguelov D, Srinivasan P, Koller D, Thrun S, Rodgers J, Davis J (2005) Scape: shape completion and animation of people. In\u00a0ACM SIGGRAPH 2005 Papers, pp 408\u2013416. https:\/\/doi.org\/10.1145\/1073204.1073207","DOI":"10.1145\/1073204.1073207"},{"key":"20187_CR23","doi-asserted-by":"publisher","unstructured":"Balan AO, Sigal L, Black MJ, Davis JE, Haussecker HW (2007) Detailed human shape and pose from images. In\u00a02007 IEEE conference on computer vision and pattern recognition. IEEE, pp 1\u20138. https:\/\/doi.org\/10.1109\/CVPR.2007.383340","DOI":"10.1109\/CVPR.2007.383340"},{"issue":"4","key":"20187_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201337","volume":"37","author":"G Barill","year":"2018","unstructured":"Barill G, Dickson NG, Schmidt R, Levin DI, Jacobson A (2018) Fast winding numbers for soups and clouds. ACM Trans Graph (TOG) 37(4):1\u201312","journal-title":"ACM Trans Graph (TOG)"},{"key":"20187_CR25","doi-asserted-by":"publisher","unstructured":"Bogo F, Kanazawa A, Lassner C, Gehler P, Romero J, Black MJ (2016) Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In\u00a0computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part V 14. Springer International Publishing, pp 561\u2013578. https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"20187_CR26","doi-asserted-by":"publisher","unstructured":"Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In\u00a0proceedings of the European conference on computer vision (ECCV), pp 801\u2013818. https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"20187_CR27","doi-asserted-by":"publisher","unstructured":"Chen Z, Zhang H (2019) Learning implicit fields for generative shape modeling. In\u00a0proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5939\u20135948. https:\/\/doi.org\/10.48550\/arXiv.1812.02822","DOI":"10.48550\/arXiv.1812.02822"},{"key":"20187_CR28","doi-asserted-by":"publisher","unstructured":"Choy CB, Xu D, Gwak J, Chen K, Savarese S (2016) 3d-r2n2: A unified approach for single and multi-view 3d object reconstruction. In\u00a0computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, proceedings, Part VIII 14. Springer International Publishing, pp 628\u2013644. https:\/\/doi.org\/10.1007\/978-3-319-46484-8_38","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"20187_CR29","doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In\u00a02009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248-255 https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"8","key":"20187_CR30","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1109\/TPAMI.2009.161","volume":"32","author":"RM Stereopsis","year":"2010","unstructured":"Stereopsis RM (2010) Accurate, dense, and robust multiview stereopsis. IEEE Trans Pattern Anal Mach Intell 32(8):1362","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"10","key":"20187_CR31","doi-asserted-by":"publisher","first-page":"6642","DOI":"10.1109\/TCSVT.2022.3177320","volume":"32","author":"L Yan","year":"2022","unstructured":"Yan L, Ma S, Wang Q, Chen Y, Zhang X, Savakis A, Liu D (2022) Video captioning using global-local representation. IEEE Trans Circuits Syst Video Technol 32(10):6642\u20136656","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"1","key":"20187_CR32","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1109\/TCSVT.2022.3202574","volume":"33","author":"L Yan","year":"2022","unstructured":"Yan L, Wang Q, Ma S, Wang J, Yu C (2022) Solve the puzzle of instance segmentation in videos: a weakly supervised framework with spatio-temporal collaboration. IEEE Trans Circuits Syst Video Technol 33(1):393\u2013406","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"20187_CR33","unstructured":"Wang W, Han C, Zhou T, Liu D (2022) Visual recognition with deep nearest centroids.\u00a0arXiv preprint arXiv:2209.07383. Accessed 10.04.2023"},{"key":"20187_CR34","first-page":"12826","volume":"35","author":"W Wang","year":"2022","unstructured":"Wang W, Liang J, Liu D (2022) Learning equivariant segmentation with instance-unique querying. Adv Neural Inf Process Syst 35:12826\u201312840","journal-title":"Adv Neural Inf Process Syst"},{"key":"20187_CR35","doi-asserted-by":"publisher","unstructured":"Liu D, Cui Y, Cao Z, Chen Y (2020) Indoor navigation for mobile agents: A multimodal vision fusion model. In\u00a02020 international joint conference on neural networks (IJCNN). IEEE, pp 1-8. https:\/\/doi.org\/10.1109\/IJCNN48605.2020.9207265","DOI":"10.1109\/IJCNN48605.2020.9207265"},{"key":"20187_CR36","doi-asserted-by":"publisher","unstructured":"Yan L, Liu D, Song Y, Yu C (2020) Multimodal aggregation approach for memory vision-voice indoor navigation with meta-learning. In\u00a02020 IEEE\/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 5847-5854. https:\/\/doi.org\/10.48550\/arXiv.2009.00402","DOI":"10.48550\/arXiv.2009.00402"},{"key":"20187_CR37","unstructured":"Ziegler JD, Subramaniam S, Azzarito M, Doyle O, Krusche P, Coroller T (2022) Multi-modal conditional GAN: data synthesis in the medical domain. In NeurIPS 2022 workshop on synthetic data for empowering ML research"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20187-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-20187-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20187-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T09:20:41Z","timestamp":1737969641000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-20187-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,19]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1]]}},"alternative-id":["20187"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-20187-x","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2024,9,19]]},"assertion":[{"value":"23 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}