{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T05:06:47Z","timestamp":1733029607005,"version":"3.30.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031781278","type":"print"},{"value":"9783031781285","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T00:00:00Z","timestamp":1732924800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T00:00:00Z","timestamp":1732924800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T00:00:00Z","timestamp":1732924800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T00:00:00Z","timestamp":1732924800000},"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\/978-3-031-78128-5_20","type":"book-chapter","created":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T07:41:38Z","timestamp":1732952498000},"page":"302-318","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TinyConv-PVT: A Deeper Fusion Model of\u00a0CNN and\u00a0Transformer for\u00a0Tiny Dataset"],"prefix":"10.1007","author":[{"given":"Yi","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Bowei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Yi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,30]]},"reference":[{"key":"20_CR1","first-page":"23818","volume":"34","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Sangineto, E., Bi, W., Sebe, N., Lepri, B., Nadai, M.: Efficient training of visual transformers with small datasets. Adv. Neural. Inf. Process. Syst. 34, 23818\u201323830 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR2","first-page":"12116","volume":"34","author":"M Raghu","year":"2021","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? Adv. Neural. Inf. Process. Syst. 34, 12116\u201312128 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR3","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.patrec.2021.04.024","volume":"148","author":"Y Jin","year":"2021","unstructured":"Jin, Y., Han, D., Ko, H.: Trseg: transformer for semantic segmentation. Pattern Recogn. Lett. 148, 29\u201335 (2021)","journal-title":"Pattern Recogn. Lett."},{"key":"20_CR4","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.patrec.2022.05.006","volume":"159","author":"J Heo","year":"2022","unstructured":"Heo, J., Wang, Y., Park, J.: Occlusion-aware spatial attention transformer for occluded object recognition. Pattern Recogn. Lett. 159, 70\u201376 (2022)","journal-title":"Pattern Recogn. Lett."},{"key":"20_CR5","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"20_CR6","unstructured":"Hassani, A., Walton, S., Shah, N., Abuduweili, A., Li, J., Shi, H.: Escaping the big data paradigm with compact transformers. arXiv preprint arXiv:2104.05704 (2021)"},{"key":"20_CR7","unstructured":"Lee, S.H., Lee, S., Song, B.C.: Vision transformer for small-size datasets. arXiv preprint arXiv:2112.13492 (2021)"},{"key":"20_CR8","doi-asserted-by":"publisher","unstructured":"Pan, J., et al.: Edgevits: competing light-weight cnns on mobile devices with vision transformers. In: European Conference on Computer Vision, pp. 294\u2013311. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_18","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Riformer: keep your vision backbone effective but removing token mixer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14443\u201314452 (2023)","DOI":"10.1109\/CVPR52729.2023.01388"},{"key":"20_CR10","unstructured":"Ryoo, M.S., Piergiovanni, A.J., Arnab, A., Dehghani, M., Angelova, A.: Tokenlearner: what can 8 learned tokens do for images and videos? arXiv preprint arXiv:2106.11297 (2021)"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.:. Tokens-to-token vit: training vision transformers from scratch on imagenet. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 558\u2013567 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Cvt: Introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"20_CR14","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"d\u2019Ascoli, S., Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G., Sagun, L.: Convit: improving vision transformers with soft convolutional inductive biases. In: International Conference on Machine Learning, pp. 2286\u20132296. PMLR (2021)","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T.-Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16519\u201316529 (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Guo, J., Han, K., Wu, H., Tang, Y., Chen, X., Wang, Y., Xu, C.: Cmt: convolutional neural networks meet vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision And Pattern Recognition, pp. 12175\u201312185 (2022)","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"20_CR18","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.patrec.2023.03.028","volume":"169","author":"X Fan","year":"2023","unstructured":"Fan, X., Liu, H.: Flexformer: flexible transformer for efficient visual recognition. Pattern Recogn. Lett. 169, 95\u2013101 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"20_CR19","doi-asserted-by":"publisher","unstructured":"Sun, P., et al.: Swformer: sparse window transformer for 3d object detection in point clouds. In: European Conference on Computer Vision, pp. 426\u2013442. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_25","DOI":"10.1007\/978-3-031-20080-9_25"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: Maskgit: masked generative image transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"20_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104760","volume":"137","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Yan, L., Feng, Z., Xia, Y., Xiao, B.: Visual tracking using transformer with a combination of convolution and attention. Image Vis. Comput. 137, 104760 (2023)","journal-title":"Image Vis. Comput."},{"key":"20_CR22","unstructured":"Mehta, S., Rastegari, M.: Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178 (2021)"},{"key":"20_CR23","unstructured":"Islam, M.A., Jia, S., Bruce, N.D.B.: How much position information do convolutional neural networks encode? arXiv preprint arXiv:2001.08248 (2020)"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Graham, B., et al.: Levit: a vision transformer in convnet\u2019s clothing for faster inference. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12259\u201312269 (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"20_CR25","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., Aguera y\u00a0Arcas, B.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273\u20131282. PMLR (2017)"},{"key":"20_CR26","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"issue":"4","key":"20_CR27","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1109\/TMI.2021.3125459","volume":"41","author":"C Zhu","year":"2021","unstructured":"Zhu, C., Chen, W., Peng, T., Wang, Y., Jin, M.: Hard sample aware noise robust learning for histopathology image classification. IEEE Trans. Med. Imaging 41(4), 881\u2013894 (2021)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"20_CR29","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, pp. 11936\u201311945 (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"issue":"3","key":"20_CR31","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., et al.: Pvt v2: improved baselines with pyramid vision transformer. Comput. Vis. Media 8(3), 415\u2013424 (2022)","journal-title":"Comput. Vis. Media"},{"issue":"6","key":"20_CR32","doi-asserted-by":"publisher","first-page":"2127","DOI":"10.1007\/s13042-022-01750-0","volume":"14","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Zhang, Y.: Conv-pvt: a fusion architecture of convolution and pyramid vision transformer. Int. J. Mach. Learn. Cybern. 14(6), 2127\u20132136 (2023)","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"20_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"20_CR36","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256. JMLR Workshop and Conference Proceedings (2010)"},{"key":"20_CR37","unstructured":"Huang, T., Huang, L., You, S., Wang, F., Qian, C., Xu, C.: Lightvit: Towards light-weight convolution-free vision transformers. arXiv preprint arXiv:2207.05557 (2022)"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: Metaformer is actually what you need for vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10819\u201310829 (2022)","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"20_CR40","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Topformer: token pyramid transformer for mobile semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12083\u201312093 (2022)","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"20_CR42","first-page":"20014","volume":"34","author":"A Ali","year":"2021","unstructured":"Ali, A., et al.: Xcit: cross-covariance image transformers. Adv. Neural. Inf. Process. Syst. 34, 20014\u201320027 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78128-5_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T08:05:30Z","timestamp":1732953930000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78128-5_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,30]]},"ISBN":["9783031781278","9783031781285"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78128-5_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,30]]},"assertion":[{"value":"30 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}