{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:33:44Z","timestamp":1742913224725,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031578694"},{"type":"electronic","value":"9783031578700"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-57870-0_27","type":"book-chapter","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T04:01:52Z","timestamp":1712635312000},"page":"302-312","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RsViT \u2013 A Scalable Vision Transformer Backbone for\u00a0Diffusion Model"],"prefix":"10.1007","author":[{"given":"Thanawin","family":"Sakpuaram","sequence":"first","affiliation":[]},{"given":"Chantana","family":"Chantrapornchai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,10]]},"reference":[{"key":"27_CR1","doi-asserted-by":"publisher","unstructured":"Bao, F., et al.: \u201cAll are worth words: a ViT backbone for diffusion models\". In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA, USA: IEEE Computer Society, June 2023, pp. 22669\u201322679 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02171.","DOI":"10.1109\/CVPR52729.2023.02171."},{"key":"27_CR2","unstructured":"Cao, H., et al.: \u201cExploring Vision Transformers as Diffusion Learners\". arXiv:2212.13771 (2022). https:\/\/ui.adsabs.harvard.edu\/abs\/2022arXiv221213771C"},{"key":"27_CR3","doi-asserted-by":"publisher","unstructured":"Deng, J., et al.: \u201cImageNet: a large-scale hierarchical image database\". In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248-255 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848.","DOI":"10.1109\/CVPR.2009.5206848."},{"key":"27_CR4","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR5","unstructured":"Dosovitskiy, A., et al.: \u201cAn image is worth 16x16 words: transformers for image recognition at scale\". arXiv:2010.11929 (2020). https:\/\/ui.adsabs.harvard.edu\/abs\/2020arXiv201011929D"},{"key":"27_CR6","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR7","first-page":"23593","volume":"35","author":"B Kawar","year":"2022","unstructured":"Kawar, B., et al.: Denoising diffusion restoration models. Adv. Neural. Inf. Process. Syst. 35, 23593\u201323606 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR8","unstructured":"Liu, Z., et al.: \u201cSwin transformer: hierarchical vision transformer using shifted windows\". In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012-10022"},{"issue":"8","key":"27_CR9","doi-asserted-by":"publisher","first-page":"10346","DOI":"10.1109\/TPAMI.2023.3238179","volume":"45","author":"O \u00d6zdenizci","year":"2023","unstructured":"\u00d6zdenizci, O., Legenstein, R.: Restoring vision in adverse weather conditions with patch-based denoising diffusion models. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 10346\u201310357 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"27_CR10","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1007\/s40747-021-00527-2","volume":"8","author":"D Qiu","year":"2022","unstructured":"Qiu, D., Yang, B.: Text summarization based on multi-head self-attention mechanism and pointer network. Complex Intell. Syst. 8(1), 555\u2013567 (2022)","journal-title":"Complex Intell. Syst."},{"key":"27_CR11","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"MICCAI 2015 Part III","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds.) MICCAI 2015 Part III. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"27_CR12","unstructured":"AMBESH SHEKHAR. ImageNet100. Dataset (2021). https:\/\/www.kaggle.com\/datasets\/ambityga\/imagenet100"},{"key":"27_CR13","unstructured":"Song, J., Meng, C., Ermon, S.: \u201cDenoising diffusion implicit models\". arXiv:2010.02502 (2020). https:\/\/ui.adsabs.harvard.edu\/abs\/2020arXiv201002502S"},{"key":"27_CR14","unstructured":"Vaswani, A., et al.: \u201cAttention is all you need\". In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"27_CR15","doi-asserted-by":"publisher","unstructured":"Voita, E et al.: \u201cAnalyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned\". In: Korhonen, A., Traum, D., M\u2018arquez, L (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Ed. by . Florence, Italy: Association for Computational Linguistics, July 2019, pp. 5797-5808. https:\/\/doi.org\/10.18653\/v1\/P19-1580, https:\/\/aclanthology.org\/P19-1580","DOI":"10.18653\/v1\/P19-1580"},{"key":"27_CR16","unstructured":"Yang, X., et al.: \u201cYour VIT is secretly a hybrid discriminative-generative diffusion model\". arXiv preprint arXiv:2208.07791 (2022)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Zamir, S., et al.: \u201cRestormer: efficient transformer for high-resolution image restoration\". In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5728\u20135739 (2022)","DOI":"10.1109\/CVPR52688.2022.00564"}],"container-title":["Lecture Notes on Data Engineering and Communications Technologies","Advanced Information Networking and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-57870-0_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T04:11:09Z","timestamp":1712635869000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-57870-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031578694","9783031578700"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-57870-0_27","relation":{},"ISSN":["2367-4512","2367-4520"],"issn-type":[{"type":"print","value":"2367-4512"},{"type":"electronic","value":"2367-4520"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"10 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AINA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Information Networking and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kitakyushu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 April 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aina2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/voyager.ce.fit.ac.jp\/conf\/aina\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}