{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T10:59:09Z","timestamp":1771757949363,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T00:00:00Z","timestamp":1694044800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T00:00:00Z","timestamp":1694044800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001236"],"award-info":[{"award-number":["62001236"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of the Jiangsu Higher Education Institutions of China","award":["20KJA520003"],"award-info":[{"award-number":["20KJA520003"]}]},{"DOI":"10.13039\/501100010014","name":"Six Talent Peaks Project in Jiangsu Province","doi-asserted-by":"publisher","award":["JY-051"],"award-info":[{"award-number":["JY-051"]}],"id":[{"id":"10.13039\/501100010014","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s11063-023-11402-1","type":"journal-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T16:02:35Z","timestamp":1694102555000},"page":"11905-11919","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Transformer-Based Fused Attention Combined with CNNs for Image Classification"],"prefix":"10.1007","volume":"55","author":[{"given":"Jielin","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxiang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,7]]},"reference":[{"key":"11402_CR1","doi-asserted-by":"publisher","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 3431\u20133440. https:\/\/doi.org\/10.1109\/CVPR.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"11402_CR2","doi-asserted-by":"publisher","unstructured":"Zhou Y, Zheng X, Ouyang W, et\u00a0al (2022) A strip dilated convolutional network for semantic segmentation. Neural Process Lett 1\u201321. https:\/\/doi.org\/10.1007\/s11063-022-11048-5","DOI":"10.1007\/s11063-022-11048-5"},{"key":"11402_CR3","doi-asserted-by":"publisher","unstructured":"Xiang X, Meng F, Lv N, et\u00a0al (2022) Engineering vehicles detection for warehouse surveillance system based on modified yolov4-tiny. Neural Process Lett 1\u201317. https:\/\/doi.org\/10.1007\/s11063-022-10982-8","DOI":"10.1007\/s11063-022-10982-8"},{"key":"11402_CR4","unstructured":"Ren S, He K, Girshick R, et\u00a0al (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst (NeurIPS) 28"},{"key":"11402_CR5","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et\u00a0al (2020) An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of international conference on learning representations (ICLR)"},{"key":"11402_CR6","doi-asserted-by":"publisher","unstructured":"Sun C, Shrivastava A, Singh S, et\u00a0al (2017) Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 843\u2013852. https:\/\/doi.org\/10.1109\/ICCV.2017.97","DOI":"10.1109\/ICCV.2017.97"},{"key":"11402_CR7","doi-asserted-by":"publisher","unstructured":"Liu Z, Lin Y, Cao Y, et\u00a0al (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 10012\u201310022. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"11402_CR8","volume-title":"Learning multiple layers of features from tiny images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky A, Hinton G et al (2009) Learning multiple layers of features from tiny images. ON, Canada, Toronto"},{"key":"11402_CR9","unstructured":"Le Y, Yang X (2015) Tiny imagenet visual recognition challenge. CS 231N 7(7):3"},{"issue":"60","key":"11402_CR10","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"6","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 6(60):84\u201390. https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun ACM"},{"key":"11402_CR11","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of international conference on learning representations (ICLR)"},{"key":"11402_CR12","doi-asserted-by":"publisher","unstructured":"Szegedy C, Liu W, Jia Y, et\u00a0al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1-9. https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"11402_CR13","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the international conference on machine learning (ICML), pp 448\u2013456"},{"key":"11402_CR14","doi-asserted-by":"publisher","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, et\u00a0al (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 2818-2826. https:\/\/doi.org\/10.1109\/CVPR.2016.308","DOI":"10.1109\/CVPR.2016.308"},{"key":"11402_CR15","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, et\u00a0al (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the AAAI conference on artificial intelligence, 31(1)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"11402_CR16","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, et\u00a0al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 770-778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"11402_CR17","doi-asserted-by":"publisher","unstructured":"Xie S, Girshick R, Doll\u00e1r P, et\u00a0al (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 5987-5995. https:\/\/doi.org\/10.1109\/CVPR.2017.634","DOI":"10.1109\/CVPR.2017.634"},{"key":"11402_CR18","doi-asserted-by":"publisher","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L, et\u00a0al (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 2261-2269. https:\/\/doi.org\/10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"11402_CR19","doi-asserted-by":"publisher","unstructured":"Ding X, Zhang X, Ma N, et\u00a0al (2021) Repvgg: Making vgg-style convnets great again. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 13728-13737. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01352","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"11402_CR20","doi-asserted-by":"publisher","unstructured":"Liu Z, Mao H, Wu CY, et\u00a0al (2022) A convnet for the 2020s. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 11966-11976. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01167","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"11402_CR21","unstructured":"Tan M, Le Q (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the international conference on machine learning (ICML), pp 6105\u20136114"},{"key":"11402_CR22","doi-asserted-by":"publisher","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 7132-7141. https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"11402_CR23","doi-asserted-by":"publisher","unstructured":"Wang Q, Wu B, Zhu P, et\u00a0al (2020) Eca-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 11531-11539. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01155","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"11402_CR24","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY, et\u00a0al (2018) Cbam: Convolutional block attention module. In: Proceedings of the european conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"11402_CR25","doi-asserted-by":"publisher","unstructured":"Li X, Wang W, Hu X, et\u00a0al (2019) Selective kernel networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 510-519. https:\/\/doi.org\/10.1109\/CVPR.2019.00060","DOI":"10.1109\/CVPR.2019.00060"},{"key":"11402_CR26","unstructured":"Guo MH, Lu CZ, Hou Q, et\u00a0al (2022) Segnext: Rethinking convolutional attention design for semantic segmentation. Preprint at arXiv:2209.08575"},{"key":"11402_CR27","doi-asserted-by":"publisher","unstructured":"Zhu B, Hofstee P, Lee J, et\u00a0al (2021) An attention module for convolutional neural networks. In: Proceedings of 30th international conference on artificial neural networks, Bratislava, Slovakia, pp 167-168. https:\/\/doi.org\/10.1007\/978-3-030-86362-3_14","DOI":"10.1007\/978-3-030-86362-3_14"},{"key":"11402_CR28","unstructured":"Vaswani A, Shazeer N, Parmar N, et\u00a0al (2017) Attention is all you need. Adv Neural Inf Process Syst (NeurIPS) 30"},{"key":"11402_CR29","unstructured":"Devlin J, Chang MW, Lee K, et\u00a0al (2018) Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the conference on empirical methods in natural language processing (EMNLP)"},{"key":"11402_CR30","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst (NeurIPS) 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst (NeurIPS)"},{"key":"11402_CR31","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115:211\u2013252","journal-title":"Int J Comput Vis"},{"key":"11402_CR32","unstructured":"Touvron H, Cord M, Douze M, et\u00a0al (2021) Training data-efficient image transformers & distillation through attention. In: Proceedings of the international conference on machine learning (ICML), pp 10347\u201310357"},{"key":"11402_CR33","doi-asserted-by":"publisher","unstructured":"Yuan L, Chen Y, Wang T, et\u00a0al (2021) Tokens-to-token vit: Training vision transformers from scratch on imagenet. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 538-547. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00060","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"11402_CR34","first-page":"15908","volume":"34","author":"K Han","year":"2021","unstructured":"Han K, Xiao A, Wu E et al (2021) Transformer in transformer. Adv Neural Inf Process Syst (NeurIPS) 34:15908\u201315919","journal-title":"Adv Neural Inf Process Syst (NeurIPS)"},{"key":"11402_CR35","doi-asserted-by":"publisher","unstructured":"Yuan K, Guo S, Liu Z, et\u00a0al (2021) Incorporating convolution designs into visual transformers. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 559-568. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00062","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"11402_CR36","doi-asserted-by":"publisher","unstructured":"Srinivas A, Lin TY, Parmar N, et\u00a0al (2021) Bottleneck transformers for visual recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 16514-16524. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01625","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"11402_CR37","doi-asserted-by":"publisher","unstructured":"Guo J, Han K, Wu H, et\u00a0al (2022) Cmt: Convolutional neural networks meet vision transformers. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 12165-12175. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01186","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"11402_CR38","unstructured":"Li J, Xia X, Li W, et\u00a0al (2022) Next-vit: Next generation vision transformer for efficient deployment in realistic industrial scenarios. Preprint at arXiv:2207.05501v4"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11402-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-023-11402-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-023-11402-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T09:17:21Z","timestamp":1703668641000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-023-11402-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,7]]},"references-count":38,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["11402"],"URL":"https:\/\/doi.org\/10.1007\/s11063-023-11402-1","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,7]]},"assertion":[{"value":"20 August 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The author declares that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}