{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:44:12Z","timestamp":1777653852073,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726972","type":"print"},{"value":"9783031726989","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72698-9_9","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T04:45:57Z","timestamp":1729831557000},"page":"148-164","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["GarmentAligner: Text-to-Garment Generation via\u00a0Retrieval-Augmented Multi-level Corrections"],"prefix":"10.1007","author":[{"given":"Shiyue","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Zheng","family":"Chong","sequence":"additional","affiliation":[]},{"given":"Xujie","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Hanhui","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yuhao","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Yiqiang","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Avrahami, O., et al.: SpaText: spatio-textual representation for controllable image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18370\u201318380 (2023)","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"9_CR2","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 (2023)","DOI":"10.1109\/ICCV51070.2023.02138"},{"key":"9_CR3","unstructured":"Blattmann, A., Rombach, R., Oktay, K., M\u00fcller, J., Ommer, B.: Semi-parametric neural image synthesis (2022)"},{"key":"9_CR4","unstructured":"Borgeaud, S., et al.: Improving language models by retrieving from trillions of tokens (2022)"},{"issue":"4","key":"9_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-Excite: attention-based semantic guidance for text-to-image diffusion models. ACM Trans. Graph. 42(4), 1\u201310 (2023). https:\/\/doi.org\/10.1145\/3592116","journal-title":"ACM Trans. Graph."},{"key":"9_CR6","unstructured":"Chen, J., et\u00a0al.: Pixart-$$\\alpha $$: fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426 (2023)"},{"key":"9_CR7","unstructured":"Chen, W., Hu, H., Saharia, C., Cohen, W.W.: Re-Imagen: retrieval-augmented text-to-image generator (2022)"},{"key":"9_CR8","unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis (2023)"},{"key":"9_CR9","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion (2022)"},{"key":"9_CR10","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.W.: REALM: retrieval-augmented language model pre-training (2020)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Yao, K., Zhang, Q., Yu, J., Liu, L., Xu, L.: DressCode: autoregressively sewing and generating garments from text guidance (2024)","DOI":"10.1145\/3658147"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning (2022)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"9_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, vol. 30 (2017)"},{"key":"9_CR14","unstructured":"Khandelwal, U., Levy, O., Jurafsky, D., Zettlemoyer, L., Lewis, M.: Generalization through memorization: nearest neighbor language models (2020)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"9_CR16","unstructured":"Lee, K., et al.: Aligning text-to-image models using human feedback. arXiv preprint arXiv:2302.12192 (2023)"},{"key":"9_CR17","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks (2021)"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Li, N., Liu, Q., Singh, K.K., Wang, Y., Zhang, J., Plummer, B.A., Lin, Z.: UniHuman: a unified model for editing human images in the wild (2023)","DOI":"10.1109\/CVPR52733.2024.00199"},{"key":"9_CR19","doi-asserted-by":"publisher","unstructured":"Lin, A., Zhao, N., Ning, S., Qiu, Y., Wang, B., Han, X.: FashionTex: controllable virtual try-on with text and texture. In: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings. SIGGRAPH \u201923, ACM (2023). https:\/\/doi.org\/10.1145\/3588432.3591568","DOI":"10.1145\/3588432.3591568"},{"key":"9_CR20","unstructured":"Lin, H., Miao, L., Ziai, A.: RAFIC: retrieval-augmented few-shot image classification (2023)"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Ning, S., Wang, D., Qin, Y., Jin, Z., Wang, B., Han, X.: PICTURE: photorealistic virtual try-on from unconstrained designs (2023)","DOI":"10.1109\/CVPR52733.2024.00666"},{"key":"9_CR23","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS-W (2017)"},{"key":"9_CR24","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis (2023)"},{"key":"9_CR25","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"9_CR26","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer (2023)"},{"key":"9_CR27","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents (2022)"},{"key":"9_CR28","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation (2021)"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Razzhigaev, A., et al.: Kandinsky: an improved text-to-image synthesis with image prior and latent diffusion (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.25"},{"key":"9_CR30","unstructured":"Ren, T., et al.: Grounded SAM: assembling open-world models for diverse visual tasks (2024)"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"9_CR33","unstructured":"Seyfioglu, M.S., Bouyarmane, K., Kumar, S., Tavanaei, A., Tutar, I.B.: DreamPaint: few-shot inpainting of e-commerce items for virtual try-on without 3D modeling (2023)"},{"key":"9_CR34","unstructured":"Tang, Z., Yang, Z., Zhu, C., Zeng, M., Bansal, M.: Any-to-any generation via composable diffusion (2023)"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Voynov, A., Aberman, K., Cohen-Or, D.: Sketch-guided text-to-image diffusion models. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591560"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Wu, X., Sun, K., Zhu, F., Zhao, R., Li, H.: Better aligning text-to-image models with human preference (2023)","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"9_CR37","unstructured":"Xie, Z., Li, H., Ding, H., Li, M., Cao, Y.: Hierarchical fashion design with multi-stage diffusion models (2024)"},{"key":"9_CR38","unstructured":"Xu, J., et al.: ImageReward: learning and evaluating human preferences for text-to-image generation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"9_CR39","unstructured":"Xue, Z., et al.: RAPHAEL: text-to-image generation via large mixture of diffusion paths. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"9_CR40","unstructured":"Yasunaga, M., et al.: Retrieval-augmented multimodal language modeling (2023)"},{"key":"9_CR41","unstructured":"Yu, J., et al.: Quality and quantity: Unveiling a million high-quality images for text-to-image synthesis in fashion design (2023)"},{"key":"9_CR42","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation (2022)"},{"key":"9_CR43","doi-asserted-by":"publisher","unstructured":"Zhang, X., Sha, Y., Kampffmeyer, M.C., Xie, Z., Jie, Z., Huang, C., Peng, J., Liang, X.: ARMANI: part-level garment-text alignment for unified cross-modal fashion design. In: Proceedings of the 30th ACM International Conference on Multimedia. MM \u201922, ACM (2022). https:\/\/doi.org\/10.1145\/3503161.3548230","DOI":"10.1145\/3503161.3548230"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: DiffCloth: diffusion based garment synthesis and manipulation via structural cross-modal semantic alignment (2023)","DOI":"10.1109\/ICCV51070.2023.02116"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72698-9_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T07:22:01Z","timestamp":1732951321000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72698-9_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726972","9783031726989"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72698-9_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}