{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:00Z","timestamp":1778048340720,"version":"3.51.4"},"reference-count":76,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00114","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1106-1116","source":"Crossref","is-referenced-by-count":0,"title":["MBTI: Metric-Based Textual Inversion for Fine-Grained Image Generation"],"prefix":"10.1109","author":[{"given":"Byungkwan","family":"Chae","sequence":"first","affiliation":[{"name":"Soongsil University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngjae","family":"Choi","sequence":"additional","affiliation":[{"name":"Soongsil University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heewon","family":"Kim","sequence":"additional","affiliation":[{"name":"Soongsil University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00453"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00832"},{"key":"ref3","article-title":"Data augmentation generative adversarial networks","volume-title":"ICLR","author":"Antoniou"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00077"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053146"},{"key":"ref6","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"ICLR","author":"Brock"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref8","article-title":"Diffusion Models Beat GANs on Image Synthesis","volume-title":"NeurIPS","author":"Dhariwal"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612599"},{"key":"ref12","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"ICML","author":"Finn"},{"key":"ref13","article-title":"An image is worth one word: personalizing text-to-image generation using textual inversion","volume-title":"ICLR","author":"Gal"},{"key":"ref14","article-title":"Generative adversarial nets","volume-title":"NeurIPS","author":"Goodfellow"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00308"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.328"},{"key":"ref17","article-title":"Is synthetic data from generative models ready for image recognition","volume-title":"ICLR","author":"He"},{"key":"ref18","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS","author":"Ho"},{"key":"ref19","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"issue":"47","key":"ref20","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume-title":"JMLR","volume":"23","author":"Ho"},{"key":"ref21","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"ICLR","author":"Hu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687658"},{"key":"ref23","article-title":"Generative models as a data source for multiview representation learning","volume-title":"ICLR","author":"Jahanian"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref25","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma"},{"key":"ref26","article-title":"Siamese neural networks for one-shot image recognition","volume-title":"ICMLW","author":"Koch"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00654"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref31","article-title":"Fine-grained visual classification of aircraft","volume-title":"CVPR","author":"Maji"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref33","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"PMLR","author":"Nichol"},{"key":"ref34","article-title":"Improved denoising diffusion probabilistic models","volume-title":"ICML","author":"Nichol"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref36","article-title":"Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models","author":"Park","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00053"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01411"},{"key":"ref39","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref40","article-title":"Zero-shot text-to-image generation","volume-title":"ICML","author":"Ramesh"},{"key":"ref41","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","article-title":"Improving Diffusion Models for Conditional Image Generation","author":"Rombach","year":"2024"},{"key":"ref45","article-title":"DreamBooth: Fine tuning text-to-image diffusion models for subject-driven generation","author":"Ruiz","year":"2022"},{"key":"ref46","article-title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","volume-title":"NeurIPS","author":"Saharia"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref48","article-title":"Prototypical networks for few-shot learning","volume-title":"NeurIPS","author":"Snell"},{"key":"ref49","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein"},{"key":"ref50","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref52","article-title":"Data augmentation using GANs","author":"Dos Santos Tanaka","year":"2019"},{"key":"ref53","article-title":"DF-GAN: Deep fusion generative adversarial networks for text-to-image synthesis","volume-title":"CVPR","author":"Tao"},{"key":"ref54","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"ICML","author":"Touvron"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"ref56","article-title":"Effective data augmentation with diffusion models","volume-title":"ICLR","author":"Trabucco"},{"key":"ref57","article-title":"A bayesian data augmentation approach for learning deep models","volume-title":"NeurIPS","author":"Tran"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00257"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref60","article-title":"Matching networks for one shot learning","volume-title":"NeurIPS","author":"Vinyals"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181070"},{"key":"ref62","article-title":"Adaptive cross-modal few-shot learning","volume-title":"NeurIPS","author":"Xing"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00588"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00880"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.137"},{"key":"ref67","article-title":"Scaling autoregressive models for Content-Rich Text-to-Image Generation","volume-title":"ICLR","author":"Yu"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00375"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01001"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01738"},{"key":"ref73","article-title":"Indomain GAN inversion for real image editing","volume-title":"ECCV","author":"Zhu"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref76","article-title":"Improved StyleGAN Embedding: Where are the Good Latents","author":"Zhu","year":"2020"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492172.pdf?arnumber=11492172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:55:11Z","timestamp":1778046911000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00114","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}