{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:53:19Z","timestamp":1782280399956,"version":"3.54.5"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T00:00:00Z","timestamp":1751500800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T00:00:00Z","timestamp":1751500800000},"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":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s11554-025-01719-6","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T23:01:31Z","timestamp":1751497291000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":101,"title":["ELA: efficient location attention for deep convolution neural networks"],"prefix":"10.1007","volume":"22","author":[{"given":"Wei","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weina","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,3]]},"reference":[{"key":"1719_CR1","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 Proceedings of the IEEE\/CVF international conference on computer vision workshops, pages 0\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"1719_CR2","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"1719_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wang, Y., Yang, T., Zhang, X., Cheng, J., Sun, J.: You only look one-level feature. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pages 13039\u201313048 (2021)","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"1719_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhong, F., Luo, Q., Zhang, X., Zheng, Y.: Edgevit: Efficient visual modeling for edge computing. In International Conference on Wireless Algorithms, Systems, and Applications, pages 393\u2013405. Springer (2022)","DOI":"10.1007\/978-3-031-19211-1_33"},{"key":"1719_CR5","unstructured":"Choromanski, K., Likhosherstov, V., Dohan, D., Song, X., Gane, A., Sarlos, T., Hawkins, P., Davis, J., Mohiuddin, A., Kaiser, L., et\u00a0al.: Rethinking attention with performers. arXiv preprint arXiv:2009.14794 (2020)"},{"key":"1719_CR6","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.neunet.2023.12.003","volume":"171","author":"Y Cui","year":"2024","unstructured":"Cui, Y., Knoll, A.: Dual-domain strip attention for image restoration. Neural Netw. 171, 429\u2013439 (2024)","journal-title":"Neural Netw."},{"key":"1719_CR7","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 2009 IEEE conference on computer vision and pattern recognition, pages 248\u2013255. Ieee (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1719_CR8","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"1719_CR9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T.: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1719_CR10","doi-asserted-by":"crossref","unstructured":"Everingham, M., Eslami, SM\u00a0Ali., Gool, L.V., Williams, C.KI., Winn, J., Zisserman, A.: The pascal visual object classes challenge: A retrospective. International journal of computer vision, 111: 98\u2013136 (2015)","DOI":"10.1007\/s11263-014-0733-5"},{"key":"1719_CR11","doi-asserted-by":"crossref","unstructured":"Gao, Z., Xie, J., Wang, Q., Li, P.: Global second-order pooling convolutional networks. In Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pages 3024\u20133033 (2019)","DOI":"10.1109\/CVPR.2019.00314"},{"key":"1719_CR12","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"1719_CR13","unstructured":"Gu, A, Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"1719_CR14","unstructured":"Guo, M.-H, Lu, C.Z., Liu, Z.-N., Cheng, M.-M., Hu, S.-M: Visual attention network (2022). URL https:\/\/arxiv.org\/abs\/2202.09741"},{"key":"1719_CR15","doi-asserted-by":"crossref","unstructured":"Hamilton, J.\u00a0D: State-space models. Handbook of econometrics, 4: 3039\u20133080 (1994)","DOI":"10.1016\/S1573-4412(05)80019-4"},{"key":"1719_CR16","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, pages 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1719_CR17","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhang, L., Cheng, M.-M., Feng, J.: Strip pooling: Rethinking spatial pooling for scene parsing. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pages 4003\u20134012 (2020)","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"1719_CR18","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pages 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"1719_CR19","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"1719_CR20","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G: Squeeze-and-excitation networks, 7132\u20137141. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, UT (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1719_CR21","unstructured":"Kitaev, N., Kaiser, \u0141., Levskaya, A.: Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451 (2020)"},{"key":"1719_CR22","unstructured":"Li, X., Hu, X., Yang, J.: Spatial group-wise enhance: Improving semantic feature learning in convolutional networks. arXiv preprint arXiv:1905.09646 (2019a)"},{"key":"1719_CR23","doi-asserted-by":"crossref","unstructured":"Li, X, Wang, W., Hu, X., Yang, J.: Selective kernel networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pages 510\u2013519 (2019b)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"1719_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C\u00a0L.: Microsoft coco: Common objects in context. In Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1719_CR25","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: Eapt. efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"1719_CR26","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, pages 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"1719_CR27","unstructured":"Lyu, C., Zhang, W., Huang, H., Zhou, Y., Wang, Y., Liu, Y., Zhang, S., Chen, K: Rtmdet: An empirical study of designing real-time object detectors (2022). URL https:\/\/arxiv.org\/abs\/2212.07784"},{"key":"1719_CR28","doi-asserted-by":"crossref","unstructured":"Maaz, M., Shaker, A., Cholakkal, H., Khan, S., Zamir, S.W., Anwer, R.M., Khan. , F.S.:dgenext: efficiently amalgamated cnn-transformer architecture for mobile vision applications. In European Conference on Computer Vision, pages 3\u201320. Springer (2022)","DOI":"10.1007\/978-3-031-25082-8_1"},{"key":"1719_CR29","doi-asserted-by":"crossref","unstructured":"Mothe, S, Kankanala, S: Multi-stage residual network with two fold attention mechanisms for low-light image enhancement. The Visual Computer, pages 1\u201316 (2025)","DOI":"10.1007\/s00371-025-03835-7"},{"issue":"2","key":"1719_CR30","doi-asserted-by":"publisher","first-page":"227","DOI":"10.3102\/1076998619872761","volume":"45","author":"B Pang","year":"2020","unstructured":"Pang, B., Nijkamp, E., Wu, Y.N.: Deep learning with tensorflow: A review. Journal of Educational and Behavioral Statistics 45(2), 227\u2013248 (2020)","journal-title":"Journal of Educational and Behavioral Statistics"},{"key":"1719_CR31","unstructured":"Park, J., Woo, S., Lee, J.-Y., Kweon, I.S.: Bam: Bottleneck attention module. arXiv preprint arXiv:1807.06514 (2018)"},{"key":"1719_CR32","volume-title":"and Soumith Chintala","author":"A Paszke","year":"2019","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A.: and Soumith Chintala. An imperative style, high-performance deep learning library, Pytorch (2019)"},{"key":"1719_CR33","doi-asserted-by":"publisher","unstructured":"Preechakul, K., Sriswasdi, S., Kijsirikul, B., Chuangsuwanich, E.: Improved image classification explainability with high-accuracy heatmaps. iScience 25 (3): 103933 (2022). ISSN 2589-0042. https:\/\/doi.org\/10.1016\/j.isci.2022.103933. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2589004222002036","DOI":"10.1016\/j.isci.2022.103933"},{"key":"1719_CR34","doi-asserted-by":"crossref","unstructured":"Qian, S., Ning, C., Hu, Y.: Mobilenetv3 for image classification. In 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), pages 490\u2013497. IEEE (2021)","DOI":"10.1109\/ICBAIE52039.2021.9389905"},{"key":"1719_CR35","doi-asserted-by":"crossref","unstructured":"Qin, D., Leichner, C., Delakis, M., Fornoni, M., Luo, S., Yang, F., Wang, W., Banbury, C., Ye, C., Akin, B., et\u00a0al. :Mobilenetv4-universal models for the mobile ecosystem. arXiv preprint arXiv:2404.10518 (2024)","DOI":"10.1007\/978-3-031-73661-2_5"},{"key":"1719_CR36","unstructured":"Qu, H., Ning, L., An, R., Fan, W., Derr, T., Liu, H., Xu, X., Li, Q.: A survey of mamba. arXiv preprint arXiv:2408.01129 (2024)"},{"key":"1719_CR37","unstructured":"Rahman, Md\u00a0M., Tutul, A.\u00a0A., Nath, A., Laishram, L., Jung, S.\u00a0K., Hammond, T.: Mamba in vision: A comprehensive survey of techniques and applications. arXiv preprint arXiv:2410.03105 (2024)"},{"key":"1719_CR38","unstructured":"Romero, D.\u00a0W., Knigge, D.\u00a0M., Gu A., Bekkers, E\u00a0J., Gavves, E., Tomczak, J\u00a0M ., Hoogendoorn, M: Towards a general purpose cnn for long range dependencies in $$n$$ d. (2022)"},{"key":"1719_CR39","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C: Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1719_CR40","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.\u00a0R., 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, pages 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"1719_CR41","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.\u00a0N, Kaiser, \u0141., Polosukhin, I: Attention is all you need. Advances in neural information processing systems, 30 (2017)"},{"key":"1719_CR42","unstructured":"Wan, Q., Huang, Z., Lu, J., Yu, G., Zhang, L: Seaformer: Squeeze-enhanced axial transformer for mobile semantic segmentation. arXiv preprint arXiv:2301.13156 (2023)"},{"key":"1719_CR43","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A.,Liao, H.-Y.M.: Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 7464\u20137475 (2023a)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1719_CR44","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 Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pages 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"1719_CR45","doi-asserted-by":"crossref","unstructured":"Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., Li, H., et\u00a0al.: Internimage: Exploring large-scale vision foundation models with deformable convolutions. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 14408\u201314419 (2023b)","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"1719_CR46","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.\u00a0S.: Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV), pages 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1719_CR47","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K: Group normalization. In Proceedings of the European conference on computer vision (ECCV), pages 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"1719_CR48","unstructured":"Xu, R., Yang, S., Wang, Y., Du, B., Chen, H: A survey on vision mamba: Models, applications and challenges. arXiv preprint arXiv:2404.18861 (2024)"},{"key":"1719_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121338","volume":"237","author":"S Yan","year":"2024","unstructured":"Yan, S., Shao, H., Wang, J., Zheng, X., Liu, B.: Liconvformer: A lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attention. Expert Syst. Appl. 237, 121338 (2024)","journal-title":"Expert Syst. Appl."},{"key":"1719_CR50","unstructured":"Yang, C., Chen, Z., Espinosa, M., Ericsson, L., Wang, Z., Liu, J., Crowley, E.\u00a0J: Plainmamba: Improving non-hierarchical mamba in visual recognition. arXiv preprint arXiv:2403.17695 (2024)"},{"key":"1719_CR51","doi-asserted-by":"crossref","unstructured":"Yuan, K., Chen, Y., Huang, X., Zhang, Y., Pan, P., Xu, Y., Yin, W.: Decentlam: Decentralized momentum sgd for large-batch deep training. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pages 3029\u20133039 (2021)","DOI":"10.1109\/ICCV48922.2021.00302"},{"issue":"1","key":"1719_CR52","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.vrih.2022.07.006","volume":"5","author":"M Zhang","year":"2023","unstructured":"Zhang, M., Tian, X.: Transformer architecture based on mutual attention for image-anomaly detection. Virtual Reality & Intelligent Hardware 5(1), 57\u201367 (2023)","journal-title":"Virtual Reality & Intelligent Hardware"},{"key":"1719_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, Q.-L, Yang, Y.-B: Sa-net: Shuffle attention for deep convolutional neural networks. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2235\u20132239. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414568"},{"key":"1719_CR54","doi-asserted-by":"publisher","first-page":"4183","DOI":"10.1109\/TMM.2023.3321394","volume":"26","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Zhang, T., Cunyu, W., Tao, R.: Multi-scale spatiotemporal feature fusion network for video saliency prediction. IEEE Trans. Multimedia 26, 4183\u20134193 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"1719_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wu, C., Zhang, T., Zheng, Y.: Full-scale feature aggregation and grouping feature reconstruction based uav image target detection. IEEE Transactions on Geoscience and Remote Sensing (2024)","DOI":"10.1109\/TGRS.2024.3392794"},{"issue":"1","key":"1719_CR56","doi-asserted-by":"publisher","first-page":"013005","DOI":"10.1117\/1.JEI.34.1.013005","volume":"34","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Wang, S., Zhang, Y., Puze, Yu.: Asymmetric light-aware progressive decoding network for rgb-thermal salient object detection. J. Electron. Imaging 34(1), 013005\u2013013005 (2025)","journal-title":"J. Electron. Imaging"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01719-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-025-01719-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01719-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T16:59:50Z","timestamp":1757350790000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-025-01719-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,3]]},"references-count":56,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["1719"],"URL":"https:\/\/doi.org\/10.1007\/s11554-025-01719-6","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,3]]},"assertion":[{"value":"7 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing financial interests or personal relationships that could have influenced this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"140"}}