{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T10:27:30Z","timestamp":1742984850064,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031820724"},{"type":"electronic","value":"9783031820731"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-82073-1_31","type":"book-chapter","created":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T18:29:11Z","timestamp":1739816951000},"page":"317-326","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Computational Cost Reduction for MobileViT with Token Merging"],"prefix":"10.1007","author":[{"given":"Mitsuhiko","family":"Yasukura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michifumi","family":"Yoshioka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6073-7264","authenticated-orcid":false,"given":"Katsufumi","family":"Inoue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,18]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin Transformer V2: scaling up capacity and resolution. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"31_CR2","unstructured":"Dai, Z., Liu, H., Le, Q.V., and Tan, M.: CoAtNet: marrying convolution and attention for all data sizes. In: Advances in Neural Information Processing Systems, vol. 34, pp. 3965\u20133977 (2021)"},{"key":"31_CR3","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"31_CR4","unstructured":"Mehta, S., Rastegari, M.: MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. In: Proceedings of the International Conference on Learning Representations (2022)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: MobilenetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Wu, J., Leng, C., Wang, Y., Hu, Q., Cheng, J.: Quantized convolutional neural networks for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.521"},{"key":"31_CR7","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv:1503.02531 (2015)"},{"key":"31_CR8","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"31_CR9","unstructured":"Bolya, D., Fu, C.-Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token Merging: Your ViT but faster. In: Proceedings of the International Conference on Learning Representations (ICLR) (2023)"},{"key":"31_CR10","unstructured":"Dosovitskiy, A., et al.: An Image is Worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. In: Proceedings of the International Conference on Learning Representations (2021)"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Howard, A., et al. Searching for MobileNetV3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Mobile-Former: bridging MobileNet and transformer. arXiv:2108.05895 (2021)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"31_CR14","unstructured":"Mehta, S., Rastegari, M.: Separable self-attention for mobile vision transformers. arXiv:2206.02680 (2022)"},{"key":"31_CR15","unstructured":"Wadekar, S.N., Chaurasia, A.: MobileViTv3: mobile-friendly vision transformer with simple and effective fusion of local, global, and input features. arXiv:2209.15159 (2022)"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Bolya, D., Hoffman, J.: Token merging for fast stable diffusion. In: CVPR Workshop on Efficient Deep Learning for Computer Vision (2023)","DOI":"10.1109\/CVPRW59228.2023.00484"},{"issue":"3","key":"31_CR18","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."}],"container-title":["Lecture Notes in Networks and Systems","Distributed Computing and Artificial Intelligence, 21st International Conference"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-82073-1_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T18:29:18Z","timestamp":1739816958000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-82073-1_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031820724","9783031820731"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-82073-1_31","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"18 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Distributed Computing and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salamanca","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"25 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dcai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.dcai-conference.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}