{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:25:20Z","timestamp":1786980320620,"version":"build-2736575974"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,1,22]],"date-time":"2022-01-22T00:00:00Z","timestamp":1642809600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,22]],"date-time":"2022-01-22T00:00:00Z","timestamp":1642809600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s00530-022-00889-8","type":"journal-article","created":{"date-parts":[[2022,1,22]],"date-time":"2022-01-22T13:02:31Z","timestamp":1642856551000},"page":"915-924","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":100,"title":["Wavelet-Attention CNN for image classification"],"prefix":"10.1007","volume":"28","author":[{"given":"Xiangyu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-4663","authenticated-orcid":false,"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,22]]},"reference":[{"key":"889_CR1","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"889_CR2","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)"},{"key":"889_CR3","doi-asserted-by":"crossref","unstructured":"Shu, X., Zhang, L., Tang, J., Xie, G.-S., Yan, S.: Computational face reader. In: International Conference on Multimedia Modeling, pp. 114\u2013126 (2016)","DOI":"10.1007\/978-3-319-27671-7_10"},{"issue":"2","key":"889_CR4","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1109\/TMM.2017.2741423","volume":"20","author":"K Kumar","year":"2017","unstructured":"Kumar, K., Shrimankar, D.D.: F-des: fast and deep event summarization. IEEE Trans. Multimed. 20(2), 323\u2013334 (2017)","journal-title":"IEEE Trans. Multimed."},{"key":"889_CR5","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"889_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., Agrawal, A.: Context encoding for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7151\u20137160 (2018)","DOI":"10.1109\/CVPR.2018.00747"},{"key":"889_CR7","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint arXiv:1409.1556"},{"key":"889_CR8","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"889_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"889_CR10","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention (2014). arXiv preprint arXiv:1412.7755"},{"key":"889_CR11","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, pp. 2017\u20132025 (2015)"},{"key":"889_CR12","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"889_CR13","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"889_CR14","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"889_CR15","doi-asserted-by":"crossref","unstructured":"Wang, H., Wu, X., Huang, Z., Xing, E.P.: High-frequency component helps explain the generalization of convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 8684\u20138694 (2020)","DOI":"10.1109\/CVPR42600.2020.00871"},{"key":"889_CR16","doi-asserted-by":"crossref","unstructured":"Li, Q., Shen, L., Guo, S., Lai, Z.: Wavelet integrated cnns for noise-robust image classification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7245\u20137254 (2020)","DOI":"10.1109\/CVPR42600.2020.00727"},{"key":"889_CR17","unstructured":"Tang, J., Shu, X., Yan, R., Zhang, L.: Coherence constrained graph lstm for group activity recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (2019)"},{"issue":"3","key":"889_CR18","doi-asserted-by":"publisher","first-page":"1110","DOI":"10.1109\/TPAMI.2019.2942030","volume":"43","author":"X Shu","year":"2021","unstructured":"Shu, X., Tang, J., Qi, G.-J., Liu, W., Yang, J.: Hierarchical long short-term concurrent memory for human interaction recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(3), 1110\u20131118 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"889_CR19","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1109\/TNNLS.2020.2978942","volume":"32","author":"X Shu","year":"2020","unstructured":"Shu, X., Zhang, L., Sun, Y., Tang, J.: Host-parasite: graph lstm-in-lstm for group activity recognition. IEEE Trans. Neural Netw. Learn. Syst. 32(2), 663\u2013674 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"889_CR20","doi-asserted-by":"crossref","unstructured":"Yan, R., Xie, L., Tang, J., Shu, X., Tian, Q.: Higcin: hierarchical graph-based cross inference network for group activity recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"889_CR21","doi-asserted-by":"crossref","unstructured":"Yan, R., Shu, X., Yuan, C., Tian, Q., Tang, J.: Position-aware participation-contributed temporal dynamic model for group activity recognition. IEEE Transactions on Neural Networks and Learning Systems (2021)","DOI":"10.1109\/TNNLS.2021.3085567"},{"key":"889_CR22","doi-asserted-by":"crossref","unstructured":"Kumar, K., Shrimankar, D.D.: Esumm: event summarization on scale-free networks. IETE Technical Review (2018)","DOI":"10.1080\/02564602.2018.1454347"},{"issue":"7","key":"889_CR23","doi-asserted-by":"publisher","first-page":"11079","DOI":"10.1007\/s11042-020-10157-4","volume":"80","author":"K Kumar","year":"2021","unstructured":"Kumar, K.: Text query based summarized event searching interface system using deep learning over cloud. Multimed. Tools Appl. 80(7), 11079\u201311094 (2021)","journal-title":"Multimed. Tools Appl."},{"issue":"11","key":"889_CR24","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"889_CR25","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"889_CR26","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"889_CR27","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks (2016). arXiv preprint arXiv:1605.07146","DOI":"10.5244\/C.30.87"},{"key":"889_CR28","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"889_CR29","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depth wise separable convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"889_CR30","unstructured":"Larochelle, H., Hinton, G.E.: Learning to combine foveal glimpses with a third-order boltzmann machine. In: Advances in Neural Information Processing Systems, pp. 1243\u20131251 (2010)"},{"key":"889_CR31","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., So\u00a0Kweon, I.: Cbam: convolutional block attention module. In: European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"889_CR32","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In: IEEE International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"889_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: Eca-net: efficient channel attention for deep convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"889_CR34","doi-asserted-by":"crossref","unstructured":"Shu, X., Zhang, L., Qi, G.-J., Liu, W., Tang, J.: Spatiotemporal co-attention recurrent neural networks for human-skeleton motion prediction. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"889_CR35","unstructured":"Shen, Z., Zhang, M., Zhao, H., Yi, S., Li, H.: Efficient attention: Attention with linear complexities (2018). arXiv preprint arXiv:1812.01243"},{"key":"889_CR36","unstructured":"Chen, Y., Kalantidis, Y., Li, J., Yan, S., Feng, J.: A nets: double attention networks (2018). arXiv preprint arXiv:1810.11579"},{"key":"889_CR37","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: Ccnet: Criss-cross attention for semantic segmentation. In: IEEE International Conference on Computer Vision, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"889_CR38","unstructured":"Park, J., Woo, S., Lee, J.-Y., Kweon, I.S.: Bam: Bottleneck attention module (2018). arXiv preprint arXiv:1807.06514"},{"key":"889_CR39","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., Lu, H.: Dual attention network for scene segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"889_CR40","doi-asserted-by":"crossref","unstructured":"Qin, Z., Zhang, P., Wu, F., Li, X.: Fcanet: Frequency channel attention networks (2020). arXiv preprint arXiv:2012.11879","DOI":"10.1109\/ICCV48922.2021.00082"},{"issue":"10","key":"889_CR41","doi-asserted-by":"publisher","first-page":"1288","DOI":"10.1109\/TMI.2003.817812","volume":"22","author":"M Penedo","year":"2003","unstructured":"Penedo, M., Pearlman, W.A., Tahoces, P.G., Souto, M., Vidal, J.J.: Region-based wavelet coding methods for digital mammography. IEEE Trans. Med. Imaging 22(10), 1288\u20131296 (2003)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"12","key":"889_CR42","doi-asserted-by":"publisher","first-page":"2091","DOI":"10.1109\/TIP.2005.859376","volume":"14","author":"MN Do","year":"2005","unstructured":"Do, M.N., Vetterli, M.: The contourlet transform: an efficient directional multiresolution image representation. IEEE Trans. Image Process. 14(12), 2091\u20132106 (2005)","journal-title":"IEEE Trans. Image Process."},{"key":"889_CR43","doi-asserted-by":"crossref","unstructured":"Huang, H., He, R., Sun, Z., Tan, T.: Wavelet-srnet: a wavelet-based cnn for multi-scale face super resolution. In: IEEE International Conference on Computer Vision, pp. 1689\u20131697 (2017)","DOI":"10.1109\/ICCV.2017.187"},{"key":"889_CR44","doi-asserted-by":"crossref","unstructured":"Savareh, B.A., Emami, H., Hajiabadi, M., Azimi, S.M., Ghafoori, M.: Wavelet-enhanced convolutional neural network: a new idea in a deep learning paradigm. Biomed. Eng.\/Biomedizinische Technik 64(2), 195\u2013205 (2019)","DOI":"10.1515\/bmt-2017-0178"},{"key":"889_CR45","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.patcog.2016.11.015","volume":"64","author":"Y Duan","year":"2017","unstructured":"Duan, Y., Liu, F., Jiao, L., Zhao, P., Zhang, L.: Sar image segmentation based on convolutional-wavelet neural network and markov random field. Pattern Recogn. 64, 255\u2013267 (2017)","journal-title":"Pattern Recogn."},{"key":"889_CR46","doi-asserted-by":"crossref","unstructured":"Liu, P., Zhang, H., Zhang, K., Lin, L., Zuo, W.: Multi-level wavelet-cnn for image restoration. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 773\u2013782 (2018)","DOI":"10.1109\/CVPRW.2018.00121"},{"key":"889_CR47","unstructured":"Williams, T., Li, R.: Wavelet pooling for convolutional neural networks. In: International Conference on Learning Representations (2018)"},{"key":"889_CR48","doi-asserted-by":"crossref","unstructured":"Yoo, J., Uh, Y., Chun, S., Kang, B., Ha, J.-W.: Photorealistic style transfer via wavelet transforms. In: IEEE International Conference on Computer Vision, pp. 9036\u20139045 (2019)","DOI":"10.1109\/ICCV.2019.00913"},{"key":"889_CR49","doi-asserted-by":"crossref","unstructured":"Buades, A., Coll, B., Morel, J.-M.: A non-local algorithm for image denoising. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 60\u201365 (2005)","DOI":"10.1109\/CVPR.2005.38"},{"issue":"2","key":"889_CR50","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1109\/61.489353","volume":"11","author":"S Santoso","year":"1996","unstructured":"Santoso, S., Powers, E.J., Grady, W.M., Hofmann, P.: Power quality assessment via wavelet transform analysis. IEEE Trans. Power Deliv. 11(2), 924\u2013930 (1996)","journal-title":"IEEE Trans. Power Deliv."},{"key":"889_CR51","unstructured":"Zhang, R.: Making convolutional networks shift-invariant again. In: International Conference on Machine Learning, pp. 7324\u20137334 (2019)"},{"key":"889_CR52","unstructured":"Yang, L., Zhang, R.-Y., Li, L., Xie, X.: Simam: A simple, parameter-free attention module for convolutional neural networks. In: International Conference on Machine Learning, pp. 11863\u201311874 (2021)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-022-00889-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-022-00889-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-022-00889-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T15:08:48Z","timestamp":1726499328000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-022-00889-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,22]]},"references-count":52,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["889"],"URL":"https:\/\/doi.org\/10.1007\/s00530-022-00889-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,22]]},"assertion":[{"value":"25 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}