{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T09:13:37Z","timestamp":1760346817405},"reference-count":40,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2019,12,1]]},"DOI":"10.1587\/transinf.2019edp7045","type":"journal-article","created":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T16:19:09Z","timestamp":1575303549000},"page":"2577-2586","source":"Crossref","is-referenced-by-count":2,"title":["Attention-Guided Spatial Transformer Networks for Fine-Grained Visual Recognition"],"prefix":"10.1587","volume":"E102.D","author":[{"given":"Dichao","family":"LIU","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"WANG","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jien","family":"KATO","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] M. Rohrbach, S. Amin, M. Andriluka, and B. Schiele, \u201cA database for fine grained activity detection of cooking activities,\u201d , 2012 IEEE Conference on Comput. Vis. Pattern Recognit. (CVPR), pp.1194-1201, IEEE, 2012. 10.1109\/CVPR.2012.6247801","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"2","unstructured":"[2] M. Jaderberg, K. Simonyan, A. Zisserman, and K. Kavukcuoglu, \u201cSpatial transformer networks,\u201d Advances in Neural Information Processing Systems, pp.2017-2025, 2015."},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] B. Singh, T.K. Marks, M. Jones, O. Tuzel, and M. Shao, \u201cA multi-stream bi-directional recurrent neural network for fine-grained action detection,\u201d Proc. IEEE Conference on Comput. Vis. Pattern Recognit., pp.1961-1970, 2016. 10.1109\/CVPR.2016.216","DOI":"10.1109\/CVPR.2016.216"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] A. Cherian and S. Gould, \u201cSecond-order temporal pooling for action recognition,\u201d arXiv preprint arXiv:1704.06925, 2017. 10.1007\/s11263-018-1111-5","DOI":"10.1007\/s11263-018-1111-5"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] G. Ch\u00e9ron, I. Laptev, and C. Schmid, \u201cP-cnn: Pose-based cnn features for action recognition,\u201d Proc. IEEE Int. Conf. Comput. Vis., pp.3218-3226, 2015. 10.1109\/ICCV.2015.368","DOI":"10.1109\/ICCV.2015.368"},{"key":"6","unstructured":"[6] J. Ba, R. Grosse, R. Salakhutdinov, and B. Frey, \u201cLearning wake-sleep recurrent attention models,\u201d Advances in Neural Information Processing Systems, pp.2593-2601, 2015."},{"key":"7","unstructured":"[7] C. Wah, S. Branson, P. Welinder, P. Perona, and S. Belongie, \u201cThe Caltech-UCSD Birds-200-2011 Dataset,\u201d Tech. Rep., 2011."},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] I. Laptev, M. Marszalek, C. Schmid, and B. Rozenfeld, \u201cLearning realistic human actions from movies,\u201d 2008 IEEE Conference on Comput. Vis. Pattern Recognit. (CVPR), pp.1-8, IEEE, 2008. 10.1109\/CVPR.2008.4587756","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] H. Wang, A. Kl\u00e4ser, C. Schmid, and C.L. Liu, \u201cAction recognition by dense trajectories,\u201d 2011 IEEE Conference on Comput. Vis. Pattern Recognit. (CVPR), pp.3169-3176, IEEE, 2011. 10.1109\/CVPR.2011.5995407","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] H. Wang, A. Kl\u00e4ser, C. Schmid, and C.L. Liu, \u201cDense trajectories and motion boundary descriptors for action recognition,\u201d Int. J. Comput. Vis., vol.103, no.1, pp.60-79, May 2013. 10.1007\/s11263-012-0594-8","DOI":"10.1007\/s11263-012-0594-8"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] F. Perronnin and C. Dance, \u201cFisher kernels on visual vocabularies for image categorization,\u201d 2007 IEEE Conference on Comput. Vis. Pattern Recognit. (CVPR), pp.1-8, IEEE, 2007. 10.1109\/CVPR.2007.383266","DOI":"10.1109\/CVPR.2007.383266"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] X. Peng, L. Wang, Y. Qiao, and Q. Peng, \u201cBoosting vlad with supervised dictionary learning and high-order statistics,\u201d European Conference on Computer Vision, pp.660-674, Springer, 2014. 10.1007\/978-3-319-10578-9_43","DOI":"10.1007\/978-3-319-10578-9_43"},{"key":"13","unstructured":"[13] K. Simonyan and A. Zisserman, \u201cVery deep convolutional networks for large-scale image recognition,\u201d arXiv preprint arXiv:1409.1556, 2014."},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d Proc. IEEE Conference on Comput. Vis. Pattern Recognit., pp.770-778, 2016. 10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] A. Karpathy, G. Toderici, S. Shetty, T. Leung, R. Sukthankar, and L. Fei-Fei, \u201cLarge-scale video classification with convolutional neural networks,\u201d Proc. IEEE conference on Comput. Vis. Pattern Recognit., pp.1725-1732, 2014. 10.1109\/CVPR.2014.223","DOI":"10.1109\/CVPR.2014.223"},{"key":"16","unstructured":"[16] Q.V. Le, W.Y. Zou, S.Y. Yeung, and A.Y. Ng, \u201cLearning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis,\u201d 2011 IEEE Conference on Comput. Vis. Pattern Recognit. (CVPR), pp.3361-3368, IEEE, 2011. 10.1109\/CVPR.2011.5995496"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] G.W. Taylor, R. Fergus, Y. LeCun, and C. Bregler, \u201cConvolutional learning of spatio-temporal features,\u201d European Conference on Computer Vision, pp.140-153, Springer, 2010. 10.1007\/978-3-642-15567-3_11","DOI":"10.1007\/978-3-642-15567-3_11"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] Y. Wang, J. Song, L. Wang, L. Van Gool, and O. Hilliges, \u201cTwo-stream sr-cnns for action recognition in videos\u201d BMVC, 2016. 10.5244\/C.30.108","DOI":"10.5244\/C.30.108"},{"key":"19","unstructured":"[19] K. Simonyan and A. Zisserman, \u201cTwo-stream convolutional networks for action recognition in videos,\u201d Advances in neural information processing systems, pp.568-576, 2014."},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] L. Wang, Y. Qiao, and X. Tang, \u201cAction recognition with trajectory-pooled deep-convolutional descriptors,\u201d Proc. IEEE Conference on Comput. Vis. Pattern Recognit., pp.4305-4314, 2015. 10.1109\/CVPR.2015.7299059","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] C. Feichtenhofer, A. Pinz, and A. Zisserman, \u201cConvolutional two-stream network fusion for video action recognition,\u201d Proc. IEEE Conference on Comput. Vis. Pattern Recognit., pp.1933-1941, 2016. 10.1109\/CVPR.2016.213","DOI":"10.1109\/CVPR.2016.213"},{"key":"22","doi-asserted-by":"publisher","unstructured":"[22] Z. Li, K. Gavrilyuk, E. Gavves, M. Jain, and C.G. Snoek, \u201cVideolstm convolves, attends and flows for action recognition,\u201d Computer Vision and Image Understanding, vol.166, pp.41-50, Jan. 2018. 10.1016\/j.cviu.2017.10.011","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] J. Zhang, S. Sclaroff, Z. Lin, X. Shen, B. Price, and R. Mech, \u201cMinimum barrier salient object detection at 80 fps,\u201d Proc. IEEE Int. Conf. Comput. Vis., pp.1404-1412, 2015. 10.1109\/ICCV.2015.165","DOI":"10.1109\/ICCV.2015.165"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] D. Chen, G. Hua, and F. Wen, \u201cSupervised transformer network for efficient face detection,\u201d European Conference on Computer Vision, pp.122-138, Springer, 2016. 10.1007\/978-3-319-46454-1_8","DOI":"10.1007\/978-3-319-46454-1_8"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] A. Recasens, P. Kellnhofer, S. Stent, W. Matusik, and A. Torralba, \u201cLearning to zoom: a saliency-based sampling layer for neural networks,\u201d Proc. European Conference on Computer Vision (ECCV), pp.51-66, 2018. 10.1007\/978-3-030-01240-3_4","DOI":"10.1007\/978-3-030-01240-3_4"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] J. Fu, H. Zheng, and T. Mei, \u201cLook closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition,\u201d Proc. IEEE Conference on Comput. Vis. Pattern Recognit., pp.4438-4446, 2017. 10.1109\/CVPR.2017.476","DOI":"10.1109\/CVPR.2017.476"},{"key":"27","unstructured":"[27] S. Sharma, R. Kiros, and R. Salakhutdinov, \u201cAction recognition using visual attention,\u201d arXiv preprint arXiv:1511.04119, 2015."},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] H. Zheng, J. Fu, T. Mei, and J. Luo, \u201cLearning multi-attention convolutional neural network for fine-grained image recognition,\u201d Proc. IEEE Int. Conf. Comput. Vis., pp.5209-5217, 2017. 10.1109\/ICCV.2017.557","DOI":"10.1109\/ICCV.2017.557"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] M. Sun, Y. Yuan, F. Zhou, and E. Ding, \u201cMulti-attention multi-class constraint for fine-grained image recognition,\u201d Proc. European Conference on Computer Vision (ECCV), pp.805-821, 2018. 10.1007\/978-3-030-01270-0_49","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] 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 Proc. IEEE Int. Conf. Comput. Vis., pp.618-626, 2017. 10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] M. Moghimi, S. Belongie, M. Saberian, J. Yang, N. Vasconcelos, and L.J. Li, \u201cBoosted convolutional neural networks\u201d BMVC, 2016. 10.5244\/C.30.24","DOI":"10.5244\/C.30.24"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] Y. Cui, F. Zhou, J. Wang, X. Liu, Y. Lin, and S.J. Belongie, \u201cKernel pooling for convolutional neural networks,\u201d CVPR, p.7, 2017. 10.1109\/CVPR.2017.325","DOI":"10.1109\/CVPR.2017.325"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] A. Dubey, O. Gupta, P. Guo, R. Raskar, R. Farrell, and N. Naik, \u201cPairwise confusion for fine-grained visual classification,\u201d Proc. European Conference on Computer Vision (ECCV), pp.70-86, 2018. 10.1007\/978-3-030-01258-8_5","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] G. Huang, Z. Liu, L. Van Der Maaten, and K.Q. Weinberger, \u201cDensely connected convolutional networks,\u201d Proc. IEEE Conference on Comput. Vis. Pattern Recognit., pp.4700-4708, 2017. 10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] N. Zhang, J. Donahue, R. Girshick, and T. Darrell, \u201cPart-based r-cnns for fine-grained category detection,\u201d European Conference on Computer Vision, pp.834-849, Springer, 2014. 10.1007\/978-3-319-10590-1_54","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] J. Krause, H. Jin, J. Yang, and L. Fei-Fei, \u201cFine-grained recognition without part annotations,\u201d Proc. IEEE Conference on Comput. Vis. Pattern Recognit., pp.5546-5555, 2015. 10.1109\/CVPR.2015.7299194","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] Y. Gao, O. Beijbom, N. Zhang, and T. Darrell, \u201cCompact bilinear pooling,\u201d Proc. IEEE Conference on Comput. Vis. Pattern Recognit., pp.317-326, 2016. 10.1109\/CVPR.2016.41","DOI":"10.1109\/CVPR.2016.41"},{"key":"38","doi-asserted-by":"crossref","unstructured":"[38] S. Kong and C. Fowlkes, \u201cLow-rank bilinear pooling for fine-grained classification,\u201d 2017 IEEE Conference on Comput. Vis. Pattern Recognit. (CVPR), pp.7025-7034, IEEE, 2017. 10.1109\/CVPR.2017.743","DOI":"10.1109\/CVPR.2017.743"},{"key":"39","doi-asserted-by":"crossref","unstructured":"[39] X. Zhang, H. Xiong, W. Zhou, W. Lin, and Q. Tian, \u201cPicking deep filter responses for fine-grained image recognition,\u201d Proc. IEEE Conference on Comput. Vis. Pattern Recognit., pp.1134-1142, 2016. 10.1109\/CVPR.2016.128","DOI":"10.1109\/CVPR.2016.128"},{"key":"40","doi-asserted-by":"crossref","unstructured":"[40] T.Y. Lin and S. Maji, \u201cImproved bilinear pooling with cnns,\u201d arXiv preprint arXiv:1707.06772, 2017. https:\/\/dx.doi.org\/10.5244\/C.31.117","DOI":"10.5244\/C.31.117"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E102.D\/12\/E102.D_2019EDP7045\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,7]],"date-time":"2019-12-07T03:31:41Z","timestamp":1575689501000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E102.D\/12\/E102.D_2019EDP7045\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,1]]},"references-count":40,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2019]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2019edp7045","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,1]]}}}