{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:21:01Z","timestamp":1774552861558,"version":"3.50.1"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["62102320"],"award-info":[{"award-number":["62102320"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s00530-024-01590-8","type":"journal-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T13:31:22Z","timestamp":1733232682000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Hierarchical and progressive learning with key point sensitive loss for sonar image classification"],"prefix":"10.1007","volume":"30","author":[{"given":"Xin","family":"Chen","sequence":"first","affiliation":[]},{"given":"Huanjie","family":"Tao","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Ping","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Yishi","family":"Deng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"1590_CR1","doi-asserted-by":"publisher","unstructured":"Nguyen, H.-T., Lee, E.-H., Lee, S.: Study on the classification performance of underwater sonar image classification based on convolutional neural networks for detecting a submerged human body. Sensors. 20(1), 94 (2020). https:\/\/doi.org\/10.3390\/s20010094","DOI":"10.3390\/s20010094"},{"key":"1590_CR2","doi-asserted-by":"publisher","first-page":"109363","DOI":"10.1016\/j.patcog.2023.109363","volume":"138","author":"Q Ma","year":"2023","unstructured":"Ma, Q., Jiang, L., Yu, W.: Lambertian-based adversarial attacks on deep-learning-based underwater side-scan sonar image classification. Pattern Recogn. 138, 109363 (2023). https:\/\/doi.org\/10.1016\/j.patcog.2023.109363","journal-title":"Pattern Recogn."},{"key":"1590_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2020.3045649","volume":"60","author":"ID Gerg","year":"2022","unstructured":"Gerg, I.D., Monga, V.: Structural prior driven regularized deep learning for sonar image classification. IEEE Trans. Geosci. Remote Sens. 60, 1\u201316 (2022). https:\/\/doi.org\/10.1109\/TGRS.2020.3045649","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1590_CR4","doi-asserted-by":"publisher","unstructured":"Cheng, Z., Huo, G., Li, H.: A multi-domain collaborative transfer learning method with multi-scale repeated attention mechanism for underwater side-scan sonar image classification. Remote Sens. 14(2), 355 (2022). https:\/\/doi.org\/10.3390\/rs14020355","DOI":"10.3390\/rs14020355"},{"key":"1590_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3322787","volume":"61","author":"Y Yu","year":"2023","unstructured":"Yu, Y., Zhao, J., Huang, C., Zhao, X.: Treat noise as Domain Shift: Noise feature disentanglement for underwater perception and Maritime surveys in side-scan sonar images. IEEE Trans. Geosci. Remote Sens. 61, 1\u201315 (2023). https:\/\/doi.org\/10.1109\/TGRS.2023.3322787","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1590_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3246527","volume":"72","author":"A Vishwakarma","year":"2023","unstructured":"Vishwakarma, A.: Denoising and Inpainting of Sonar images using Convolutional sparse representation. IEEE Trans. Instrum. Meas. 72, 1\u20139 (2023). https:\/\/doi.org\/10.1109\/TIM.2023.3246527","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"1590_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3327045","volume":"61","author":"Z Ma","year":"2023","unstructured":"Ma, Z., Li, S., Ding, J., Zou, B.: MHGAN: A multi-headed Generative Adversarial Network for Underwater Sonar Image Super-resolution. IEEE Trans. Geosci. Remote Sens. 61, 1\u201316 (2023). https:\/\/doi.org\/10.1109\/TGRS.2023.3327045","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1590_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3363875","volume":"62","author":"C Huang","year":"2024","unstructured":"Huang, C., Zhao, J., Zhang, H., Yu, Y.: Seg2Sonar: A full-class Sample Synthesis Method Applied to Underwater Sonar Image Target Detection, Recognition, and segmentation tasks. IEEE Trans. Geosci. Remote Sens. 62, 1\u201319 (2024). https:\/\/doi.org\/10.1109\/TGRS.2024.3363875","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1590_CR9","doi-asserted-by":"crossref","unstructured":"Preciado-Grijalva, A., Wehbe, B., Firvida, M.B., Valdenegro-Toro, M.: Self-supervised learning for sonar image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1499\u20131508 (2022)","DOI":"10.1109\/CVPRW56347.2022.00156"},{"key":"1590_CR10","doi-asserted-by":"publisher","unstructured":"Du, X., Sun, Y., Song, Y., Sun, H., Yang, L.: A comparative study of different CNN models and transfer learning effect for underwater object classification in side-scan sonar images. Remote Sens. 15(3), 593 (2023). https:\/\/doi.org\/10.3390\/rs15030593","DOI":"10.3390\/rs15030593"},{"key":"1590_CR11","doi-asserted-by":"publisher","unstructured":"Li, C., Ye, X., Xi, J., Jia, Y.: A texture feature removal network for sonar image classification and detection. Remote Sens. 15(3), 616 (2023). https:\/\/doi.org\/10.3390\/rs15030616","DOI":"10.3390\/rs15030616"},{"key":"1590_CR12","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1109\/JOE.2022.3221127","volume":"49","author":"TT Chungath","year":"2024","unstructured":"Chungath, T.T., Nambiar, A.M., Mittal, A.: Transfer learning and few-shot learning based deep neural network models for underwater sonar image classification with a few samples. IEEE J. Oceanic Eng. 49, 294\u2013310 (2024). https:\/\/doi.org\/10.1109\/JOE.2022.3221127","journal-title":"IEEE J. Oceanic Eng."},{"key":"1590_CR13","doi-asserted-by":"publisher","unstructured":"Dai, Z., Liang, H., Duan, T.: Small-sample sonar image classification based on deep learning. J. Mar. Sci. Eng. 10(12), 1820 (2022). https:\/\/doi.org\/10.3390\/jmse10121820","DOI":"10.3390\/jmse10121820"},{"key":"1590_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2023.3318051","volume":"20","author":"H Xu","year":"2023","unstructured":"Xu, H., Bai, Z., Zhang, X., Ding, Q.: MFSANet: Zero-shot side-scan Sonar Image Recognition based on style transfer. IEEE Geosci. Remote Sens. Lett. 20, 1\u20135 (2023). https:\/\/doi.org\/10.1109\/LGRS.2023.3318051","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"1590_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3371051","volume":"62","author":"Z Yang","year":"2024","unstructured":"Yang, Z., Zhao, J., Yu, Y., Huang, C.: A sample augmentation method for side-scan Sonar full-class images that can be used for detection and segmentation. IEEE Trans. Geosci. Remote Sens. 62, 1\u201311 (2024). https:\/\/doi.org\/10.1109\/TGRS.2024.3371051","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1590_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3211847","volume":"60","author":"W Jiao","year":"2022","unstructured":"Jiao, W., Zhang, J.: Sonar images classification while facing long-tail and few-shot. IEEE Trans. Geosci. Remote Sens. 60, 1\u201320 (2022). https:\/\/doi.org\/10.1109\/TGRS.2022.3211847","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1590_CR17","doi-asserted-by":"publisher","first-page":"123495","DOI":"10.1016\/j.eswa.2024.123495","volume":"249","author":"W Jiao","year":"2024","unstructured":"Jiao, W., Zhang, J., Zhang, C.: Open-set recognition with long-tail sonar images. Expert Syst. Appl. 249, 123495 (2024). https:\/\/doi.org\/10.1016\/j.eswa.2024.123495","journal-title":"Expert Syst. Appl."},{"key":"1590_CR18","doi-asserted-by":"publisher","first-page":"47407","DOI":"10.1109\/ACCESS.2020.2978880","volume":"8","author":"G Huo","year":"2020","unstructured":"Huo, G., Wu, Z., Li, J.: Underwater object classification in Sidescan Sonar images using deep transfer learning and semi-synthetic Training Data. IEEE Access. 8, 47407\u201347418 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2978880","journal-title":"IEEE Access."},{"key":"1590_CR19","doi-asserted-by":"crossref","unstructured":"Reed, C.J., Yue, X., Nrusimha, A., Ebrahimi, S., Vijaykumar, V., Mao, R., Li, B., Zhang, S., Guillory, D., Metzger, S., Keutzer, K., Darrell, T.: Self-Supervised Pre-training Improves Self-Supervised Pre-training. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). pp. 2584\u20132594 (2022)","DOI":"10.1109\/WACV51458.2022.00112"},{"key":"1590_CR20","doi-asserted-by":"publisher","first-page":"9521","DOI":"10.1109\/TPAMI.2021.3126668","volume":"44","author":"R Du","year":"2022","unstructured":"Du, R., Xie, J., Ma, Z., Chang, D., Song, Y.-Z., Guo, J.: Progressive learning of category-consistent Multi-granularity features for fine-grained visual classification. IEEE Trans. Pattern Anal. Mach. Intell. 44, 9521\u20139535 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3126668","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1590_CR21","doi-asserted-by":"publisher","first-page":"4812","DOI":"10.1109\/TPAMI.2022.3196044","volume":"45","author":"M Li","year":"2023","unstructured":"Li, M., Cheung, Y.-M., Hu, Z.: Key Point Sensitive loss for long-tailed visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45, 4812\u20134825 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3196044","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1590_CR22","doi-asserted-by":"crossref","unstructured":"Chen, T., Liu, S., Chang, S., Cheng, Y., Amini, L., Wang, Z.: Adversarial robustness: From self-supervised pre-training to fine-tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 699\u2013708 (2020)","DOI":"10.1109\/CVPR42600.2020.00078"},{"key":"1590_CR23","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s00530-022-00977-9","volume":"29","author":"Z Yang","year":"2023","unstructured":"Yang, Z., Xie, L., Zhou, W., Huo, X., Wei, L., Lu, J., Tian, Q., Tang, S.: VoxSeP: Semi-positive voxels assist self-supervised 3D medical segmentation. Multimedia Syst. 29, 33\u201348 (2023). https:\/\/doi.org\/10.1007\/s00530-022-00977-9","journal-title":"Multimedia Syst."},{"key":"1590_CR24","doi-asserted-by":"crossref","unstructured":"Tang, Y., Yang, D., Li, W., Roth, H.R., Landman, B., Xu, D., Nath, V., Hatamizadeh, A.: Self-supervised pre-training of swin transformers for 3D medical image analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20730\u201320740 (2022)","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"1590_CR25","doi-asserted-by":"publisher","first-page":"10795","DOI":"10.1109\/TPAMI.2023.3268118","volume":"45","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Kang, B., Hooi, B., Yan, S., Feng, J.: Deep long-tailed learning: A Survey. IEEE Trans. Pattern Anal. Mach. Intell. 45, 10795\u201310816 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3268118","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1590_CR26","doi-asserted-by":"crossref","unstructured":"Cai, J., Wang, Y., Hwang, J.-N.: ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 112\u2013121 (2021)","DOI":"10.1109\/ICCV48922.2021.00018"},{"key":"1590_CR27","doi-asserted-by":"publisher","first-page":"1405","DOI":"10.1007\/s00530-023-01055-4","volume":"29","author":"W Li","year":"2023","unstructured":"Li, W., Yang, X., Li, Z.: MLCB-Net: A multi-level class balancing network for domain adaptive semantic segmentation. Multimedia Syst. 29, 1405\u20131416 (2023). https:\/\/doi.org\/10.1007\/s00530-023-01055-4","journal-title":"Multimedia Syst."},{"key":"1590_CR28","doi-asserted-by":"crossref","unstructured":"Huang, C., Li, Y., Loy, C.C., Tang, X.: Learning deep representation for imbalanced classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5375\u20135384 (2016)","DOI":"10.1109\/CVPR.2016.580"},{"key":"1590_CR29","doi-asserted-by":"publisher","first-page":"5721","DOI":"10.1109\/TIP.2023.3321461","volume":"32","author":"KP Alexandridis","year":"2023","unstructured":"Alexandridis, K.P., Luo, S., Nguyen, A., Deng, J., Zafeiriou, S.: Inverse image frequency for long-tailed image recognition. IEEE Trans. Image Process. 32, 5721\u20135736 (2023). https:\/\/doi.org\/10.1109\/TIP.2023.3321461","journal-title":"IEEE Trans. Image Process."},{"key":"1590_CR30","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/s00530-024-01291-2","volume":"30","author":"R Hu","year":"2024","unstructured":"Hu, R., Song, Y., Liu, Y., Zhu, Y., Feng, N., Qiu, C., Han, K., Teng, Q., Haq, I.U., Liu, Z.: Imbalance multiclass problem: A robust feature enhancement-based framework for liver lesion classification. Multimedia Syst. 30, 104 (2024). https:\/\/doi.org\/10.1007\/s00530-024-01291-2","journal-title":"Multimedia Syst."},{"key":"1590_CR31","doi-asserted-by":"publisher","first-page":"109534","DOI":"10.1016\/j.patcog.2023.109534","volume":"140","author":"J Li","year":"2023","unstructured":"Li, J., Wang, Q.-F., Huang, K., Yang, X., Zhang, R., Goulermas, J.Y.: Towards better long-tailed oracle character recognition with adversarial data augmentation. Pattern Recogn. 140, 109534 (2023). https:\/\/doi.org\/10.1016\/j.patcog.2023.109534","journal-title":"Pattern Recogn."},{"key":"1590_CR32","unstructured":"Kang, B., Xie, S., Rohrbach, M., Yan, Z., Gordo, A., Feng, J., Kalantidis, Y.: Decoupling Representation and Classifier for Long-Tailed Recognition, (2020). https:\/\/arxiv.org\/abs\/1910.09217"},{"key":"1590_CR33","doi-asserted-by":"crossref","unstructured":"Tang, Z., Yang, H., Chen, C.Y.-C.: Weakly supervised posture mining for fine-grained classification. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23735\u201323744 (2023)","DOI":"10.1109\/CVPR52729.2023.02273"},{"key":"1590_CR34","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1007\/s00530-022-00899-6","volume":"28","author":"S Wang","year":"2022","unstructured":"Wang, S., Wang, Z., Wang, N., Wang, H., Li, H.: From coarse to fine: Multi-level feature fusion network for fine-grained image retrieval. Multimedia Syst. 28, 1515\u20131528 (2022). https:\/\/doi.org\/10.1007\/s00530-022-00899-6","journal-title":"Multimedia Syst."},{"key":"1590_CR35","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1109\/TIP.2021.3135477","volume":"31","author":"M Liu","year":"2022","unstructured":"Liu, M., Zhang, C., Bai, H., Zhang, R., Zhao, Y.: Cross-part learning for fine-grained image classification. IEEE Trans. Image Process. 31, 748\u2013758 (2022). https:\/\/doi.org\/10.1109\/TIP.2021.3135477","journal-title":"IEEE Trans. Image Process."},{"key":"1590_CR36","doi-asserted-by":"publisher","first-page":"109761","DOI":"10.1016\/j.patcog.2023.109761","volume":"143","author":"H Tao","year":"2023","unstructured":"Tao, H., Duan, Q., Lu, M., Hu, Z.: Learning discriminative feature representation with pixel-level supervision for forest smoke recognition. Pattern Recogn. 143, 109761 (2023). https:\/\/doi.org\/10.1016\/j.patcog.2023.109761","journal-title":"Pattern Recogn."},{"key":"1590_CR37","doi-asserted-by":"publisher","first-page":"14047","DOI":"10.1109\/JIOT.2023.3339476","volume":"11","author":"H Tao","year":"2024","unstructured":"Tao, H.: Smoke Recognition in Satellite Imagery via an attention pyramid network with bidirectional Multilevel Multigranularity Feature Aggregation and Gated Fusion. IEEE Internet Things J. 11, 14047\u201314057 (2024). https:\/\/doi.org\/10.1109\/JIOT.2023.3339476","journal-title":"IEEE Internet Things J."},{"key":"1590_CR38","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.neunet.2023.11.033","volume":"170","author":"H Tao","year":"2024","unstructured":"Tao, H., Duan, Q.: Hierarchical attention network with progressive feature fusion for facial expression recognition. Neural Netw. 170, 337\u2013348 (2024). https:\/\/doi.org\/10.1016\/j.neunet.2023.11.033","journal-title":"Neural Netw."},{"key":"1590_CR39","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/978-3-031-20053-3_4","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Zhou, L., Zhang, P., Bai, X., Gu, L., Yu, X., Zhou, J., Hancock, E.R.: Where to focus: Investigating hierarchical attention relationship for fine-grained visual classification. In: Proceedings of the European Conference on Computer Vision, pp. 57\u201373 (2022)"},{"key":"1590_CR40","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s00530-024-01341-9","volume":"30","author":"N Feng","year":"2024","unstructured":"Feng, N., Tang, Y., Song, Z., Yu, J., Chen, Y.-P.P., Yang, W.: MA-VLAD: A fine-grained local feature aggregation scheme for action recognition. Multimedia Syst. 30, 139 (2024). https:\/\/doi.org\/10.1007\/s00530-024-01341-9","journal-title":"Multimedia Syst."},{"key":"1590_CR41","unstructured":"Valdenegro-Toro, M.: Deep Neural Networks for Marine Debris Detection in Sonar Images, (2019). http:\/\/arxiv.org\/abs\/1905.05241"},{"key":"1590_CR42","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jia, M., Lin, T.-Y., Song, Y., Belongie, S.: Class-balanced loss based on effective number of samples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9268\u20139277 (2019)","DOI":"10.1109\/CVPR.2019.00949"},{"key":"1590_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3106915","volume":"60","author":"J Ai","year":"2022","unstructured":"Ai, J., Mao, Y., Luo, Q., Jia, L., Xing, M.: SAR Target classification using the multikernel-size Feature Fusion-based convolutional neural network. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2022). https:\/\/doi.org\/10.1109\/TGRS.2021.3106915","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1590_CR44","unstructured":"McKay, J., Gerg, I., Monga, V., Raj, R.G.: What\u2019s mine is yours. OCEANS 2017 - Anchorage, pp. 1\u20137 (2017)"},{"key":"1590_CR45","doi-asserted-by":"crossref","unstructured":"Mahajan, D., Girshick, R., Ramanathan, V., He, K., Paluri, M., Li, Y., Bharambe, A., van der Maaten, L.: Exploring the limits of weakly supervised pre-training. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 181\u2013196 (2018)","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"1590_CR46","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1590_CR47","doi-asserted-by":"crossref","unstructured":"Alshammari, S., Wang, Y.-X., Ramanan, D., Kong, S.: Long-tailed recognition via weight balancing. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6887\u20136897 (2022)","DOI":"10.1109\/CVPR52688.2022.00677"},{"key":"1590_CR48","doi-asserted-by":"crossref","unstructured":"Aimar, E.S., Jonnarth, A., Felsberg, M., Kuhlmann, M.: Balanced product of calibrated experts for long-tailed recognition. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19967\u201319977 (2023)","DOI":"10.1109\/CVPR52729.2023.01912"},{"key":"1590_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Jiang, C., Hu, W., Zhang, F., Liu, J.: MDCS: More diverse experts with consistency self-distillation for long-tailed recognition. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11563\u201311574 (2023)","DOI":"10.1109\/ICCV51070.2023.01065"},{"key":"1590_CR50","doi-asserted-by":"crossref","unstructured":"Li, J., Meng, Z., Shi, D., Song, R., Diao, X., Wang, J., Xu, H.: FCC: Feature clusters compression for long-tailed visual recognition. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24080\u201324089 (2023)","DOI":"10.1109\/CVPR52729.2023.02306"},{"key":"1590_CR51","doi-asserted-by":"publisher","first-page":"14656","DOI":"10.1109\/JSEN.2024.3375372","volume":"24","author":"Y Chen","year":"2024","unstructured":"Chen, Y., Liang, H., Jiao, S.: NAS-MFF: NAS-Guided Multiscale Feature Fusion Network with Pareto optimization for Sonar images classification. IEEE Sens. J. 24, 14656\u201314667 (2024). https:\/\/doi.org\/10.1109\/JSEN.2024.3375372","journal-title":"IEEE Sens. J."},{"key":"1590_CR52","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1590_CR53","unstructured":"Park, J., Woo, S., Lee, J.-Y., Kweon, I.S.: BAM: Bottleneck Attention Module, (2018). http:\/\/arxiv.org\/abs\/1807.06514"},{"key":"1590_CR54","doi-asserted-by":"crossref","unstructured":"Qin, Z., Zhang, P., Wu, F., Li, X.: FcaNet: Frequency channel attention networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 783\u2013792 (2021)","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"1590_CR55","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-Excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1590_CR56","doi-asserted-by":"publisher","first-page":"3048","DOI":"10.1109\/TMM.2021.3068576","volume":"23","author":"X Ma","year":"2021","unstructured":"Ma, X., Guo, J., Sansom, A., McGuire, M., Kalaani, A., Chen, Q., Tang, S., Yang, Q., Fu, S.: Spatial pyramid attention for deep convolutional neural networks. IEEE Trans. Multimedia. 23, 3048\u20133058 (2021). https:\/\/doi.org\/10.1109\/TMM.2021.3068576","journal-title":"IEEE Trans. Multimedia"},{"key":"1590_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zu, K., Lu, J., Zou, Y., Meng, D.: EPSANet: An efficient pyramid squeeze attention block on convolutional neural network. In: Proceedings of the Asian Conference on Computer Vision, pp. 1161\u20131177 (2022)","DOI":"10.1007\/978-3-031-26313-2_33"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01590-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01590-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01590-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T09:23:53Z","timestamp":1734341033000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01590-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":57,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["1590"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01590-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"24 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2024","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 interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"380"}}