{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:47Z","timestamp":1778048327160,"version":"3.51.4"},"reference-count":45,"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\/wacv61042.2026.00620","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6412-6421","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion Noise Optimization for Synthetic VLM Training"],"prefix":"10.1109","author":[{"given":"Ren","family":"Ohkubo","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rintaro","family":"Yanagi","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokatsu","family":"Kataoka","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutaka","family":"Satoh","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref2","article-title":"Ctrlsynth: Controllable image text synthesis for data-efficient multimodal learning","author":"Cao","year":"2024"},{"key":"ref3","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3987"},{"key":"ref7","article-title":"Data filtering networks","author":"Fang","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref9","article-title":"Datacomp: In search of the next generation of multimodal datasets","volume":"36","author":"Gadre","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0254"},{"key":"ref11","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref13","author":"Al Kader Hammoud","year":"2024","journal-title":"Synthclip: Are we ready for a fully synthetic clip training?"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01879"},{"key":"ref15","author":"He","year":"2022","journal-title":"Is synthetic data from generative models ready for image recognition?"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref18","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref21","volume-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02608"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref24","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref25","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref26","volume-title":"Flux","year":"2024"},{"key":"ref27","volume-title":"Clip benchmark","year":"2022"},{"key":"ref28","volume-title":"minisd-diffusers","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref30","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref32","article-title":"Not all noises are created equally: Diffusion noise selection and optimization","author":"Qi","year":"2024"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref35","first-page":"87","article-title":"Adversarial diffusion distillation","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Sauer"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01504"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2098"},{"key":"ref39","article-title":"Effective data augmentation with diffusion models","author":"Trabucco","year":"2023"},{"key":"ref40","article-title":"Balanced similarity with auxiliary prompts: Towards alleviating text-to-image retrieval bias for clip in zero-shot learning","author":"Wang","year":"2024"},{"key":"ref41","author":"Wu","year":"2025","journal-title":"Qwen-image technical report"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00299"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3346"}],"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\/11491931.pdf?arnumber=11491931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:52:57Z","timestamp":1778046777000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491931\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00620","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}