{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:28:35Z","timestamp":1743132515455,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781858"},{"type":"electronic","value":"9783031781865"}],"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"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78186-5_18","type":"book-chapter","created":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T14:18:24Z","timestamp":1732889904000},"page":"266-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SUMMNet: Using Transformer as\u00a0a\u00a0Summary of\u00a0ConvNet for\u00a0Image Classification"],"prefix":"10.1007","author":[{"given":"Yaqi","family":"Li","sequence":"first","affiliation":[]},{"given":"Qingbei","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Zhongtao","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,30]]},"reference":[{"key":"18_CR1","unstructured":"Guo, Q., Wu, X., Yang, X., Xu, T., Si, T.: A new hybrid neural architecture of convolution and transformer for visual recognition, 2023. https:\/\/github.com\/QingbeiGuo\/HybridFormer.git"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Han, J., Ding, G.: Scaling up your kernels to 31x31: revisiting large kernel design in cnns. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11963\u201311975 (2022)","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"18_CR3","unstructured":"Liu, S., et al.: More convnets in the 2020s: scaling up kernels beyond 51x51 using sparsity. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Chen, H., Chu, X., Ren, Y., Zhao, X., Huang, K.: Pelk: parameter-efficient large kernel convnets with peripheral convolution. arXiv preprint arXiv:2403.07589 (2024)","DOI":"10.1109\/CVPR52733.2024.00531"},{"key":"18_CR5","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR), pp. 13713\u201313722 (2020)"},{"key":"18_CR6","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"18_CR7","unstructured":"Zhou, D., et al.: Deepvit: towards deeper vision transformer. arXiv preprint arXiv:2103.11886 (2021)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Going deeper with image transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 32\u201342 (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"18_CR9","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 (ICCV), pp. 558\u2013567 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"18_CR10","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 (ICCV), pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"18_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 (ICCV), pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"18_CR12","unstructured":"Chen, C.F., Panda, R., Fan, Q.: Regionvit: regional-to-local attention for vision transformers. arXiv preprint arXiv:2106.02689 (2021)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Grainger, R., Paniagua, T., Song, X., Cuntoor, N., Lee, M.W., Wu, T.: Paca-vit: learning patch-to-cluster attention in vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18568\u201318578 (2023)","DOI":"10.1109\/CVPR52729.2023.01781"},{"key":"18_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2023.3282631","volume":"45","author":"K Li","year":"2023","unstructured":"Li, K., et al.: Uniformer: unifying convolution and self-attention for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45, 1\u201318 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR15","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 (ICCV), pp. 12259\u201312269 (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"18_CR16","unstructured":"Yang, C., et al.: Moat: alternating mobile convolution and attention brings strong vision models. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"18_CR17","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 (CVPR), pp. 10819\u201310829 (2022)","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"18_CR19","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR20","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. In: Handbook of Systemic Autoimmune Diseases, vol. 1, no. 4 (2009)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.V.: Cats and dogs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3498\u20133505. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"18_CR23","first-page":"9355","volume":"34","author":"X Chu","year":"2021","unstructured":"Chu, X., et al.: Twins: revisiting the design of spatial attention in vision transformers. Adv. Neural. Inf. Process. Syst. 34, 9355\u20139366 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR24","unstructured":"Wang, W., et al.: Crossformer: a versatile vision transformer hinging on cross-scale attention. arxiv 2021 (2022)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Pan, Z., Zhuang, B., He, H., Liu, J., Cai, J.: Less is more: pay less attention in vision transformers. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 36, pp. 2035\u20132043 (2022)","DOI":"10.1609\/aaai.v36i2.20099"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Mvitv2: improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4804\u20134814 (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4794\u20134803 (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Long, S., Zhao, Z., Pi, J., Wang, S., Wang, J.: Beyond attentive tokens: incorporating token importance and diversity for efficient vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10334\u201310343 (2023)","DOI":"10.1109\/CVPR52729.2023.00996"},{"key":"18_CR30","unstructured":"Li, S., et al.: Moganet: multi-order gated aggregation network. In: International Conference on Learning Representations (2024)"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, S., Liu, H., Lin, S., He, K.: You only need less attention at each stage in vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6057\u20136066 (2024)","DOI":"10.1109\/CVPR52733.2024.00579"},{"issue":"4","key":"18_CR32","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/s41095-023-0364-2","volume":"9","author":"M-H Guo","year":"2023","unstructured":"Guo, M.-H., Cheng-Ze, L., Liu, Z.-N., Cheng, M.-M., Shi-Min, H.: Visual attention network. Comput. Visual Media 9(4), 733\u2013752 (2023)","journal-title":"Comput. Visual Media"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Hassani, A., Walton, S., Li, J., Li, S., Shi, H.: Neighborhood attention transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6185\u20136194 (2023)","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: International Conference on Machine Learning (2017)","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision(ICCV), pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 34, pp. 13001\u201313008 (2020)","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"18_CR37","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"18_CR39","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 (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78186-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T15:13:41Z","timestamp":1732893221000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78186-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,30]]},"ISBN":["9783031781858","9783031781865"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78186-5_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}