{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:37:10Z","timestamp":1742971030537,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785049"},{"type":"electronic","value":"9789819785056"}],"license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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\/978-981-97-8505-6_14","type":"book-chapter","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:02:24Z","timestamp":1730930544000},"page":"195-208","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ISO-VTON: Fine-Grained Style-Local Flows with Dual Cross-Attention for Immersive Outfitting"],"prefix":"10.1007","author":[{"given":"Yuliu","family":"Guo","sequence":"first","affiliation":[]},{"given":"Chao","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Zhaojing","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Li","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"14_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107139","volume":"126","author":"GC Ates","year":"2023","unstructured":"Ates, G.C., Mohan, P., Celik, E.: Dual cross-attention for medical image segmentation. Eng. Appl. Artif. Intell. 126, 107139 (2023)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Bai, S., Zhou, H., Li, Z., Zhou, C., Yang, H.: Single stage virtual try-on via deformable attention flows. In: European Conference on Computer Vision, pp. 409\u2013425. Springer (2022)","DOI":"10.1007\/978-3-031-19784-0_24"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Baldrati, A., Morelli, D., Cartella, G., Cornia, M., Bertini, M., Cucchiara, R.: Multimodal garment designer: human-centric latent diffusion models for fashion image editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23393\u201323402 (2023)","DOI":"10.1109\/ICCV51070.2023.02138"},{"issue":"6","key":"14_CR4","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/34.24792","volume":"11","author":"FL Bookstein","year":"1989","unstructured":"Bookstein, F.L.: Principal warps: thin-plate splines and the decomposition of deformations. IEEE Trans. Pattern Anal. Mach. Intell. 11(6), 567\u2013585 (1989)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Choi, S., Park, S., Lee, M., Choo, J.: Viton-hd: high-resolution virtual try-on via misalignment-aware normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14131\u201314140 (2021)","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Chopra, A., Jain, R., Hemani, M., Krishnamurthy, B.: Zflow: Gated appearance flow-based virtual try-on with 3d priors. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5433\u20135442 (2021)","DOI":"10.1109\/ICCV48922.2021.00538"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Ge, Y., Song, Y., Zhang, R., Ge, C., Liu, W., Luo, P.: Parser-free virtual try-on via distilling appearance flows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8485\u20138493 (2021)","DOI":"10.1109\/CVPR46437.2021.00838"},{"issue":"11","key":"14_CR8","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Gou, J., Sun, S., Zhang, J., Si, J., Qian, C., Zhang, L.: Taming the power of diffusion models for high-quality virtual try-on with appearance flow. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 7599\u20137607 (2023)","DOI":"10.1145\/3581783.3612255"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Han, X., Wu, Z., Wu, Z., Yu, R., Davis, L.S.: Viton: an image-based virtual 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":"14_CR11","doi-asserted-by":"crossref","unstructured":"He, S., Song, Y.Z., Xiang, T.: Style-based global appearance flow for virtual try-on. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3470\u20133479 (2022)","DOI":"10.1109\/CVPR52688.2022.00346"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Kim, J., Gu, G., Park, M., Park, S., Choo, J.: Stableviton: learning semantic correspondence with latent diffusion model for virtual try-on. arXiv preprint arXiv:2312.01725 (2023)","DOI":"10.1109\/CVPR52733.2024.00781"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Lee, S., Gu, G., Park, S., Choi, S., Choo, J.: High-resolution virtual try-on with misalignment and occlusion-handled conditions. In: European Conference on Computer Vision, pp. 204\u2013219. Springer (2022)","DOI":"10.1007\/978-3-031-19790-1_13"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Morelli, D., Baldrati, A., Cartella, G., Cornia, M., Bertini, M., Cucchiara, R.: Ladi-vton: latent diffusion textual-inversion enhanced virtual try-on. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 8580\u20138589 (2023)","DOI":"10.1145\/3581783.3612137"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Parmar, G., Zhang, R., Zhu, J.Y.: On aliased resizing and surprising subtleties in gan evaluation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11410\u201311420 (2022)","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"14_CR17","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Shen, J., Ni, W., Xu, Q., Tang, H.: Efficient spiking neural networks with sparse selective activation for continual learning. Proceed. AAAI Conf. Artif. Intell. 38(1), 611\u2013619 (2024)","DOI":"10.1609\/aaai.v38i1.27817"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Shen, J., Xu, Q., Liu, J.K., Wang, Y., Pan, G., Tang, H.: Esl-snns: an evolutionary structure learning strategy for spiking neural networks. Proceed. AAAI Conf. Artif. Intell. 37(1), 86\u201393 (2023)","DOI":"10.1609\/aaai.v37i1.25079"},{"issue":"9","key":"14_CR21","doi-asserted-by":"publisher","first-page":"5841","DOI":"10.1109\/TNNLS.2021.3131356","volume":"34","author":"J Shen","year":"2021","unstructured":"Shen, J., Zhao, Y., Liu, J.K., Wang, Y.: Hybridsnn: combining bio-machine strengths by boosting adaptive spiking neural networks. IEEE Trans. Neural Netw. Learn. Syst. 34(9), 5841\u20135855 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Shi, X., Hao, Z., Yu, Z.: SpikingResformer: bridging ResNet and vision transformer in spiking neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5610\u20135619 (2024)","DOI":"10.1109\/CVPR52733.2024.00536"},{"key":"14_CR23","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 the European Conference on Computer Vision (ECCV), pp. 589\u2013604 (2018)","DOI":"10.1007\/978-3-030-01261-8_36"},{"issue":"4","key":"14_CR24","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Xie, Z., Huang, Z., Dong, X., Zhao, F., Dong, H., Zhang, X., Zhu, F., Liang, X.: Gp-vton: towards general purpose virtual try-on via collaborative local-flow global-parsing learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23550\u201323559 (2023)","DOI":"10.1109\/CVPR52729.2023.02255"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Xu, X., Guo, J., Wang, Z., Huang, G., Essa, I., Shi, H.: Prompt-free diffusion: taking text out of text-to-image diffusion models (2023). arXiv preprint arXiv:2305.16223","DOI":"10.1109\/CVPR52733.2024.00829"},{"key":"14_CR27","unstructured":"Xu, Y., Gu, T., Chen, W., Chen, C.: Ootdiffusion: outfitting fusion based latent diffusion for controllable virtual try-on (2024). arXiv preprint arXiv:2403.01779"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Zeng, J., Song, D., Nie, W., Tian, H., Wang, T., Liu, A.: CAT-DM: controllable accelerated virtual try-on with diffusion model (2023). arXiv preprint arXiv:2311.18405","DOI":"10.1109\/CVPR52733.2024.00800"},{"key":"14_CR29","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"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8505-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:05:44Z","timestamp":1730930744000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8505-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"ISBN":["9789819785049","9789819785056"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8505-6_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,7]]},"assertion":[{"value":"7 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}