{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T09:39:54Z","timestamp":1730281194033,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T00:00:00Z","timestamp":1723680000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T00:00:00Z","timestamp":1723680000000},"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":[[2024,8,15]]},"DOI":"10.1109\/mapr63514.2024.10660805","type":"proceedings-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T18:23:27Z","timestamp":1725992607000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking Text-to-Image as Semantic-Aware Data Augmentation for Indoor Scene Recognition"],"prefix":"10.1109","author":[{"given":"Trong-Vu","family":"Hoang","sequence":"first","affiliation":[{"name":"University of Science, VNU-HCM,Vietnam"}]},{"given":"Quang-Binh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM,Vietnam"}]},{"given":"Dinh-Khoi","family":"Vo","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM,Vietnam"}]},{"given":"Hoai-Danh","family":"Vo","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM,Vietnam"}]},{"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM,Vietnam"}]},{"given":"Trung-Nghia","family":"Le","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM,Vietnam"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.79"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509682"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21005-2_35"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-020-10231-w"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"article-title":"The effectiveness of data augmentation in image classification using deep learning","year":"2017","author":"Perez","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1198\/10618600152418584"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IIPHDW.2018.8388338"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"2","key":"ref13","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref14","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"ref18","first-page":"10 096","article-title":"Efficientnetv2: Smaller models and faster training","volume-title":"ICML","author":"Tan"},{"article-title":"Reducing malicious use of synthetic media research: Considerations and potential release practices for machine learning","year":"2019","author":"Ovadya","key":"ref19"},{"article-title":"Evaluating the social impact of generative ai systems in systems and society","year":"2023","author":"Solaiman","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_251"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref25","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":"NeurIPS"},{"key":"ref26","first-page":"36 479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref27","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"ICML","author":"Ramesh"},{"article-title":"Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis","year":"2023","author":"Sauer","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"article-title":"ediffi: Text-to-image diffusion models with an ensemble of expert denoisers","year":"2022","author":"Balaji","key":"ref30"},{"article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","year":"2021","author":"Nichol","key":"ref31"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"article-title":"xformers: A modular and hackable transformer modelling library","year":"2022","author":"Lefaudeux","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref36"},{"key":"ref37","first-page":"10 012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","volume-title":"CVPR","author":"Liu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref39"},{"key":"ref40","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume":"31","author":"Zhang","year":"2018","journal-title":"NeurIPS"},{"issue":"11","key":"ref41","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","start":{"date-parts":[[2024,8,15]]},"location":"Da Nang, Vietnam","end":{"date-parts":[[2024,8,16]]}},"container-title":["2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10660665\/10660652\/10660805.pdf?arnumber=10660805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T05:34:16Z","timestamp":1726032856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10660805\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,15]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/mapr63514.2024.10660805","relation":{},"subject":[],"published":{"date-parts":[[2024,8,15]]}}}