{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:15:58Z","timestamp":1787012158765,"version":"build-2736575974"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209782","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification"],"prefix":"10.1109","author":[{"given":"Shijian","family":"Wang","sequence":"first","affiliation":[{"name":"Southeast University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linxin","family":"Song","sequence":"additional","affiliation":[{"name":"Waseda University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryotaro","family":"Shimizu","sequence":"additional","affiliation":[{"name":"ZOZO Research,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masayuki","family":"Goto","sequence":"additional","affiliation":[{"name":"Waseda University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanqian","family":"Wu","sequence":"additional","affiliation":[{"name":"Southeast University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","article-title":"Language models are few-shot learners","author":"Mann","year":"2020"},{"issue":"8","key":"ref3","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref4","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3293318"},{"key":"ref6","article-title":"Visual classification via description from large language models","author":"Menon","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref9","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International conference on machine learning","author":"Nichol"},{"key":"ref10","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref12","article-title":"Uncertainty inclusive contrastive learning for leveraging synthetic images","volume-title":"Synthetic Data for Computer Vision Workshop@ CVPR 2024","author":"Cai"},{"key":"ref13","article-title":"Is synthetic image useful for transfer learning? an investigation into data generation, volume, and utilization","author":"Li","year":"2024"},{"key":"ref14","article-title":"Is synthetic data from generative models ready for image recognition?","author":"He","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00705"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00011"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.151"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00194"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1070-x"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812291"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00084"},{"key":"ref23","article-title":"Diversify, don\u2019t fine-tune: Scaling up visual recognition training with synthetic images","author":"Yu","year":"2023"},{"key":"ref24","article-title":"On the diversity of realistic image synthesis","author":"Yang","year":"2017"},{"key":"ref25","article-title":"Large language model as attributed training data generator: A tale of diversity and bias","volume":"36","author":"Yu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","article-title":"The caltech-ucsd birds200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00923"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995627"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.474"},{"key":"ref32","article-title":"Comprehensive exploration of synthetic data generation: A survey","author":"Bauer","year":"2024"},{"key":"ref33","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref34","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh"},{"key":"ref35","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref36","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209782.pdf?arnumber=11209782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:32:44Z","timestamp":1761888764000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209782","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}