{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T18:10:08Z","timestamp":1744999808939,"version":"3.40.4"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T00:00:00Z","timestamp":1735257600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T00:00:00Z","timestamp":1735257600000},"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":[[2024,12,27]]},"DOI":"10.1109\/icvisp64524.2024.10959589","type":"proceedings-article","created":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T17:37:52Z","timestamp":1744911472000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing VQGAN Performance Through Integration of Multiple Vision Transformers"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6021-763X","authenticated-orcid":false,"given":"Tianyu","family":"Chen","sequence":"first","affiliation":[{"name":"College of computer science and technology, Hangzhou Dianzi University,Hangzhou,China"}]},{"given":"Daxing","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of computer science and technology, Hangzhou Dianzi University,Hangzhou,China"}]},{"given":"Yihao","family":"Qian","sequence":"additional","affiliation":[{"name":"College of computer science and technology, Hangzhou Dianzi University,Hangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3","article-title":"Tutorial on Variational Autoencoders","volume":"1050","author":"Doersch","year":"2021","journal-title":"stat"},{"key":"ref2","first-page":"1537","article-title":"Generative modeling for multi-task visual learning","volume-title":"International Conference on Machine Learning","author":"Bao","year":"2022"},{"key":"ref3","article-title":"Taming a generative model","author":"Malnick","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803510"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.01.023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/EUVIP58404.2023.10323065"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2021.06.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/ima.22979"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5220\/0012421000003636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2235"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref13","article-title":"Generative Adversarial Nets","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Goodfellow","year":"2014"},{"key":"ref14","first-page":"214","article-title":"Wasserstein generative ad-versarial networks","volume-title":"International conference on machine learning","author":"Arjovsky","year":"2017"},{"key":"ref15","article-title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","author":"Zhu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref19","article-title":"Spectral normalization for generative adversarial networks","author":"Miyato","year":"2018","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Wu .. rstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Pernias","year":"2023"},{"key":"ref22","article-title":"Weight initialization for deep learning neural networks","volume":"7","author":"Brownlee","year":"2021","journal-title":"Machine Learning Mastery"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000286"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093378"},{"key":"ref25","article-title":"On the selection ofinitialization and activation function for deep neural networks","author":"Hayou","year":"2018","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Recent theoretical advances in non- convex optimization. arxiv","author":"Danilova","year":"2020","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Adaptively solving the local-minimum problem for deep neural networks","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"journal-title":"Tackling benign nonconvexity with smoothing and stochastic gradients, 2022","author":"Vardhan","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01234"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref35","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Beit v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Image as a foreign language: Beit pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3007669.3007706"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref44","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref47","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume":"34","author":"Raghu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","article-title":"Recent advances in vision transformer: A survey and outlook of recent work","author":"Islam","year":"2022","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9081295"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2009.5206848"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IITSI.2010.74"},{"issue":"6","key":"ref54","first-page":"90","article-title":"Review on determining number of Cluster in K-Means Clustering","volume":"1","author":"Kodinariya","year":"2013","journal-title":"International Journal"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2988796"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/a16120572"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/6041484"}],"event":{"name":"2024 IEEE 8th International Conference on Vision, Image and Signal Processing (ICVISP)","start":{"date-parts":[[2024,12,27]]},"location":"Kunming, China","end":{"date-parts":[[2024,12,29]]}},"container-title":["2024 IEEE 8th International Conference on Vision, Image and Signal Processing (ICVISP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10959324\/10959149\/10959589.pdf?arnumber=10959589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T17:35:13Z","timestamp":1744997713000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10959589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,27]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/icvisp64524.2024.10959589","relation":{},"subject":[],"published":{"date-parts":[[2024,12,27]]}}}