{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:24:49Z","timestamp":1774419889768,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888226","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion Models are Zero-Shot Generative Text-Vision Retrievers"],"prefix":"10.1109","author":[{"given":"Bao","family":"Li","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeke","family":"Xie","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaomei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref4","first-page":"12 888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref6","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies","author":"Chen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref10","author":"Poole","year":"2022","journal-title":"Dreamfusion: Text-to-3d using 2d diffusion"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095100"},{"key":"ref12","author":"Liu","year":"2024","journal-title":"Alignment of diffusion models: Fundamentals, challenges, and future"},{"key":"ref13","author":"Shao","year":"2024","journal-title":"Bag of design choices for inference of high-resolution masked generative transformer"},{"key":"ref14","first-page":"25 278","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":"ref15","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref17","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687625"},{"key":"ref19","author":"Qi","year":"2024","journal-title":"Not all noises are created equally: Diffusion noise selection and optimization"},{"key":"ref20","author":"Zhou","year":"2024","journal-title":"Golden noise for diffusion models: A learning framework"},{"key":"ref21","author":"Bai","year":"2024","journal-title":"Zigzag diffusion sampling: The path to success is zigzag"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref23","article-title":"Text-to-image diffusion models are zero shot classifiers","volume":"36","author":"Clark","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445945"},{"key":"ref25","author":"Qi","year":"2024","journal-title":"A simple and efficient baseline for zero-shot generative classification"},{"key":"ref26","article-title":"Are diffusion models vision-and-language reasoners?","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Krojer"},{"key":"ref27","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in neural information processing systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref29","author":"Song","year":"2020","journal-title":"Score-based generative modeling through stochastic differential equations"},{"key":"ref30","author":"Hertz","year":"2022","journal-title":"Prompt-to-prompt image editing with cross attention control"},{"key":"ref31","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref33","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref37","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref38","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref39","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","volume":"24","author":"Kr\u00e4henb\u00fchl","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888226.pdf?arnumber=10888226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:15Z","timestamp":1774416315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888226\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888226","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}