{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T03:10:04Z","timestamp":1769051404952,"version":"3.49.0"},"reference-count":36,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2023,5,1]]},"DOI":"10.1587\/transinf.2022dlp0006","type":"journal-article","created":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T22:23:46Z","timestamp":1682893426000},"page":"590-600","source":"Crossref","is-referenced-by-count":2,"title":["The Comparison of Attention Mechanisms with Different Embedding Modes for Performance Improvement of Fine-Grained Classification"],"prefix":"10.1587","volume":"E106.D","author":[{"given":"Wujian","family":"YE","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, Guangdong University of Technology"}]},{"given":"Run","family":"TAN","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Guangdong University of Technology"}]},{"given":"Yijun","family":"LIU","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Guangdong University of Technology"}]},{"given":"Chin-Chen","family":"CHANG","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, Feng Chia University"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] S. Karen and Z. Andrew, \u201cVery deep convolutional networks for large-scale image recognition,\u201d Computer Science, pp.1-14, 2014."},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d 2016 IEEE Conference on Computer Vision & Pattern Recognition (CVPR), pp.770-778, 2016. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, \u201cRethinking the inception architecture for computer vision,\u201d 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.2818-2826, 2016. 10.1109\/cvpr.2016.308","DOI":"10.1109\/CVPR.2016.308"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, \u201cInception-v4, inception-resnet and the impact of residual connections on learning,\u201d arXiv preprint arXiv:1602.07261, pp.1-12, 2016.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"5","unstructured":"[5] H. Jie, S. Li, S. Gang, and S. Albanie, \u201cSqueeze-and-excitation networks,\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence, pp.7132-7141, 2017."},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] S. Woo, J. Park, J.-Y. Lee, and I.S. Kweon, \u201cCbam: Convolutional block attention module,\u201d European Conference on Computer Vision, vol.11211, pp.3-19, 2018. 10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, and Q. Hu, \u201cEca-net: Efficient channel attention for deep convolutional neural networks,\u201d 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.1-11, 2020. 10.1109\/cvpr42600.2020.01155","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, \u201cGrad-cam: Visual explanations from deep networks via gradient-based localization,\u201d International Journal of Computer Vision, vol.128, no.2, pp.336-359, 2020. https:\/\/doi.org\/10.1007\/s11263-019-01228-7","DOI":"10.1007\/s11263-019-01228-7"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] Z. Wang, X. Wang, and G. Wang, \u201cLearning fine-grained features via a cnn tree for large-scale classification,\u201d Neurocomputing, pp.1-28, 2018. 10.1016\/j.neucom.2017.09.061","DOI":"10.1016\/j.neucom.2017.09.061"},{"key":"10","unstructured":"[10] J.H. Luo and J.X. Wu, \u201cA survey on fine-grained image categorization using deep convolutional features,\u201d Acta Automatica Sinica, vol.43, no.8, pp.1306-1318, 2017."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] N. Zhang, J. Donahue, R. Girshick, and T. Darrell, \u201cPart-based r-cnns for fine-grained category detection,\u201d European conference on computer vision, vol.8689, pp.834-849, 2014. 10.1007\/978-3-319-10590-1_54","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] R. Girshick, J. Donahue, T. Darrell, and J. Malik, \u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp.580-587, 2014. 10.1109\/cvpr.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] J.R.R. Uijlings, K.E.A. Van De Sande, T. Gevers, and A.W.M. Smeulders, \u201cSelective search for object recognition,\u201d International Journal of Computer Vision, vol.104, no.2, pp.154-171, 2013. 10.1007\/s11263-013-0620-5","DOI":"10.1007\/s11263-013-0620-5"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] S. Branson, G Van Horn, S. Belongie, and P. Perona, \u201cBird species categorization using pose normalized deep convolutional nets,\u201d 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp.1-14, 2014.","DOI":"10.5244\/C.28.87"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] D. Lin, X. Shen, C. Lu, and J. Jia, \u201cDeep lac: Deep localization, alignment and classification for fine-grained recognition,\u201d 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp.1666-1674, 2015. 10.1109\/cvpr.2015.7298775","DOI":"10.1109\/CVPR.2015.7298775"},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] S. Li, C.H. Liu, L. Su, B. Xie, Z. Ding, C.L.P. Chen, and D. Wu, \u201cDiscriminative transfer feature and label consistency for cross-domain image classification,\u201d IEEE Transactions on Neural Networks and Learning Systems, vol.31, no.11, pp.4842-4856, 2020. 10.1109\/tnnls.2019.2958152","DOI":"10.1109\/TNNLS.2019.2958152"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] Y. Ding, S. Wen, J. Xie, D. Chang, Z. Ma, Z. Si, and H. Ling, \u201cWeakly supervised attention pyramid convolutional neural network for fine-grained visual classification,\u201d IEEE Transactions on Image Processing, pp.1-10, 2020.","DOI":"10.1109\/TIP.2021.3055617"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] T.-Y. Lin, A. Roychowdhury, and S. Maji, \u201cBilinear cnn models for fine-grained visual recognition,\u201d IEEE International Conference on Computer Vision, pp.1449-1457, 2015. 10.1109\/iccv.2015.170","DOI":"10.1109\/ICCV.2015.170"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] T.-Y. Lin and S. Maji, \u201cImproved bilinear pooling with cnns,\u201d 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp.1-12, 2017. 10.5244\/c.31.117","DOI":"10.5244\/C.31.117"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] P. Li, J. Xie, Q. Wang, and Z. Gao, \u201cTowards faster training of global covariance pooling networks by iterative matrix square root normalization,\u201d IEEE Conference on Computer Vision and Pattern Recognition, pp.947-955, 2018. 10.1109\/cvpr.2018.00105","DOI":"10.1109\/CVPR.2018.00105"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] T.-Y. Lin, S. Maji, and P. Koniusz, \u201cSecond-order democratic aggregation,\u201d European Conference of Computer Vision, vol.11207, pp.639-656, 2018. 10.1007\/978-3-030-01219-9_38","DOI":"10.1007\/978-3-030-01219-9_38"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] Q. Wang, P. Li, and L. Zhang, \u201cG2denet: Global gaussian distribution embedding network and its application to visual recognition,\u201d IEEE Conference on Computer Vision and Pattern Recognition, pp.6507-6516, 2017. 10.1109\/cvpr.2017.689","DOI":"10.1109\/CVPR.2017.689"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] Y. Cui, F. Zhou, J. Wang, X. Liu, Y. Lin, and S. Belongie, \u201cKernel pooling for convolutional neural networks,\u201d IEEE Conference on Computer Vision and Pattern Recognition, pp.3049-3058, 2017. 10.1109\/cvpr.2017.325","DOI":"10.1109\/CVPR.2017.325"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] S. Cai, W. Zuo, and Z. Lei, \u201cHigher-order integration of hierarchical convolutional activations for fine-grained visual categorization,\u201d 2017 IEEE International Conference on Computer Vision (ICCV), pp.511-520, 2017. 10.1109\/iccv.2017.63","DOI":"10.1109\/ICCV.2017.63"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] J. Fu, H. Zheng, and T. Mei, \u201cLook closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition,\u201d 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp.4438-4446, 2017. 10.1109\/cvpr.2017.476","DOI":"10.1109\/CVPR.2017.476"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] H. Zheng, J. Fu, T. Mei, and J. Luo, \u201cLearning multi-attention convolutional neural network for fine-grained image recognition,\u201d 2017 IEEE International Conference on Computer Vision (ICCV), pp.5209-5217, 2017. 10.1109\/iccv.2017.557","DOI":"10.1109\/ICCV.2017.557"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] M. Sun, Y. Yuan, F. Zhou, and E. Ding, \u201cMulti-attention multi-class constraint for fine-grained image recognition,\u201d European Conference on Computer Vision, vol.11220, pp.805-821, 2018. 10.1007\/978-3-030-01270-0_49","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] K. Han, J. Guo, C. Zhang, and M. Zhu, \u201cAttribute-aware attention model for fine-grained representation learning,\u201d ACM Multimedia Conference, pp.2040-2048, 2019. 10.1145\/3240508.3240550","DOI":"10.1145\/3240508.3240550"},{"key":"29","unstructured":"[29] H. Tao and H. Qi, \u201cSee better before looking closer: Weakly supervised data augmentation network for fine-grained visual classification,\u201d 2019 IEEE Conference on Computer Vision and Pattern Recognition, pp.1-9, 2019."},{"key":"30","unstructured":"[30] R. Tan, W. Ye, and Y. Liu, \u201cFine-grained image classification based on dual semantic data augmentation and target location,\u201d Computer Engineering, pp.1-10, 2021."},{"key":"31","doi-asserted-by":"publisher","unstructured":"[31] Y. Zhu, R. Li, Y. Yang, and N. Ye, \u201cLearning cascade attention for fine-grained image classification,\u201d Neural Networks, vol.122, pp.174-182, 2019. 10.1016\/j.neunet.2019.10.009","DOI":"10.1016\/j.neunet.2019.10.009"},{"key":"32","unstructured":"[32] J. Fu, J. Liu, H. Tian, Z. Fang, and H. Lu, \u201cDual attention network for scene segmentation,\u201d arXiv:1809.02983v4, pp.1-10, 2018."},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] Z. Wang, Q. She, and A. Smolic, \u201cAction-net: Multipath excitation for action recognition,\u201d arXiv:2103.07372v1, pp.1-15, 2021.","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"34","unstructured":"[34] H. Zhang, K. Zu, J. Lu, Y. Zou, and D. Meng, \u201cEpsanet: An efficient pyramid squeeze attention block on convolutional neural network,\u201d arXiv:2105.14447, pp.1-12, 2021."},{"key":"35","unstructured":"[35] C. Wah, S. Branson, P. Welinder, P. Perona, and S. Belongie, \u201cThe caltech-ucsd birds-200-2011 dataset,\u201d California Institute of Technology, pp.1-8, 2011."},{"key":"36","unstructured":"[36] S. Maji, E. Rahtu, J. Kannala, M. Blaschko, and A. Vedaldi, \u201cFine-grained visual classification of aircraft,\u201d HAL-INRIA, pp.1-6, 2013."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/5\/E106.D_2022DLP0006\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T14:22:16Z","timestamp":1729347736000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/5\/E106.D_2022DLP0006\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,1]]},"references-count":36,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2022dlp0006","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,1]]},"article-number":"2022DLP0006"}}