{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T16:54:34Z","timestamp":1790960074343,"version":"4.1.0"},"reference-count":81,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s11263-023-01855-1","type":"journal-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T05:01:35Z","timestamp":1691125295000},"page":"3170-3192","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["PIDray: A Large-Scale X-ray Benchmark for Real-World Prohibited Item Detection"],"prefix":"10.1007","volume":"131","author":[{"given":"Libo","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lutao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruyi","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"issue":"108","key":"1855_CR1","first-page":"245","volume":"122","author":"S Akcay","year":"2022","unstructured":"Akcay, S., & Breckon, T. (2022). Towards automatic threat detection: A survey of advances of deep learning within x-ray security imaging. Pattern Recognition, 122(108), 245.","journal-title":"Pattern Recognition"},{"key":"1855_CR2","doi-asserted-by":"crossref","unstructured":"Akcay, S., & Breckon, T.P. (2017). An evaluation of region based object detection strategies within x-ray baggage security imagery. In IEEE International Conference on Image Processing (ICIP), pp. 1337\u20131341.","DOI":"10.1109\/ICIP.2017.8296499"},{"issue":"9","key":"1855_CR3","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1109\/TIFS.2018.2812196","volume":"13","author":"S Akcay","year":"2018","unstructured":"Akcay, S., Kundegorski, M. E., Willcocks, C. G., et al. (2018). Using deep convolutional neural network architectures for object classification and detection within x-ray baggage security imagery. IEEE Transactions on Information Forensics and Security, 13(9), 2203\u20132215.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"1855_CR4","doi-asserted-by":"crossref","unstructured":"Ben-Baruch, E., Ridnik, T., Friedman, I., et\u00a0al. (2021). Multi-label classification with partial annotations using class-aware selective loss. arXiv preprint arXiv:2110.10955.","DOI":"10.1109\/CVPR52688.2022.00472"},{"key":"1855_CR5","doi-asserted-by":"crossref","unstructured":"Cai, J., Wang, Y., & Hwang, J.N. (2021). Ace: Ally complementary experts for solving long-tailed recognition in one-shot. In IEEE International Conference on Computer Vision (ICCV), pp. 112\u2013121.","DOI":"10.1109\/ICCV48922.2021.00018"},{"key":"1855_CR6","unstructured":"Cai, Y., Du, D., Zhang, L., et\u00a0al. (2020). Guided attention network for object detection and counting on drones. In ACM International Conference on Multimedia (ACM MM), pp. 709\u2013717."},{"key":"1855_CR7","doi-asserted-by":"crossref","unstructured":"Cai, Z., & Vasconcelos, N. (2018). Cascade r-cnn: Delving into high quality object detection. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR), pp. 6154\u20136162.","DOI":"10.1109\/CVPR.2018.00644"},{"issue":"5","key":"1855_CR8","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2019","unstructured":"Cai, Z., & Vasconcelos, N. (2019). Cascade r-cnn: High quality object detection and instance segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(5), 1483\u20131498.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1855_CR9","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., et\u00a0al. (2019). Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops.","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"1855_CR10","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et\u00a0al. (2020). End-to-end object detection with transformers. In European Conference on Computer Vision (ECCV), Springer, pp. 213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1855_CR11","unstructured":"Chen, K., Cao, Y., Loy, C.C., et\u00a0al. (2020). Feature pyramid grids. arXiv preprint arXiv:2004.03580."},{"key":"1855_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Z., Yang, C., Li, Q., et\u00a0al (2021) Disentangle your dense object detector. In ACM International Conference on Multimedia (ACM MM), pp. 4939\u20134948.","DOI":"10.1145\/3474085.3475351"},{"key":"1855_CR13","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jia, M., Lin, T.Y., et\u00a0al. (2019). Class-balanced loss based on effective number of samples. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 9268\u20139277.","DOI":"10.1109\/CVPR.2019.00949"},{"key":"1855_CR14","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., et\u00a0al .(2019). Centernet: Keypoint triplets for object detection. InIEEE International Conference on Computer Vision (ICCV). pp. 6569\u20136578.","DOI":"10.1109\/ICCV.2019.00667"},{"issue":"2","key":"1855_CR15","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L., Williams, C. K., et al. (2010). The pascal visual object classes (VOC) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"1855_CR16","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., et al. (2010). The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88, 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"1855_CR17","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., et\u00a0al. (2021). Tood: Task-aligned one-stage object detection. In IEEE International Conference on Computer Vision (ICCV), pp. 3490\u20133499.","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"1855_CR18","unstructured":"Fu, C.Y., Liu, W., Ranga, A., et\u00a0al (2017) Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659."},{"key":"1855_CR19","doi-asserted-by":"publisher","first-page":"5920","DOI":"10.1109\/TIP.2021.3088605","volume":"30","author":"BB Gao","year":"2021","unstructured":"Gao, B. B., & Zhou, H. Y. (2021). Learning to discover multi-class attentional regions for multi-label image recognition. IEEE Transactions on Image Processing, 30, 5920\u20135932.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1855_CR20","doi-asserted-by":"crossref","unstructured":"Gao, Z., Xie, J., Wang, Q., et\u00a0al. (2019). Global second-order pooling convolutional networks. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 3024\u20133033.","DOI":"10.1109\/CVPR.2019.00314"},{"key":"1855_CR21","unstructured":"Ge, Z., Liu, S., Wang, F., et\u00a0al. (2021). YOLOX: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430."},{"key":"1855_CR22","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., & Le, Q.V. (2019). Nas-fpn: Learning scalable feature pyramid architecture for object detection. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 7036\u20137045.","DOI":"10.1109\/CVPR.2019.00720"},{"key":"1855_CR23","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast r-cnn. In IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"1855_CR24","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., et\u00a0al. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR)., pp. 580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"1855_CR25","doi-asserted-by":"crossref","unstructured":"Gong, Y., Yu, X., Ding, Y., et\u00a0al. (2021). Effective fusion factor in fpn for tiny object detection. In IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1160\u20131168.","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"1855_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al (2016) Deep residual learning for image recognition. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1855_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., et\u00a0al. (2017). Mask r-cnn. In IEEE International Conference on Computer Vision (ICCV). pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1855_CR28","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1855_CR29","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., et\u00a0al. (2019). Ccnet: Criss-cross attention for semantic segmentation. In IEEE International Conference on Computer Vision (ICCV). pp. 603\u2013612.","DOI":"10.1109\/ICCV.2019.00069"},{"key":"1855_CR30","doi-asserted-by":"crossref","unstructured":"Ji, R., Du, D., Zhang, L., et\u00a0al. (2020a). Learning semantic neural tree for human parsing. In European Conference on Computer Vision (ECCV). pp. 205\u2013221.","DOI":"10.1007\/978-3-030-58601-0_13"},{"key":"1855_CR31","doi-asserted-by":"crossref","unstructured":"Ji, R., Wen, L., Zhang, L., et\u00a0al. (2020b). Attention convolutional binary neural tree for fine-grained visual categorization. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 10465\u201310474.","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"1855_CR32","unstructured":"Kang, B., Xie, S., Rohrbach, M., et\u00a0al. (2019). Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217."},{"key":"1855_CR33","doi-asserted-by":"crossref","unstructured":"Law, H., & Deng, J. (2018). Cornernet: Detecting objects as paired keypoints. In European Conference on Computer Vision (ECCV). pp. 734\u2013750.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"1855_CR34","unstructured":"Lewis, D.\u00a0Griffin JTAAMatthew\u00a0Caldwell. (2019). Compass-xp."},{"key":"1855_CR35","doi-asserted-by":"crossref","unstructured":"Li, C., Du, D., Zhang, L., et\u00a0al, (2020). Spatial attention pyramid network for unsupervised domain adaptation. In European Conference on Computer Vision (ECCV). pp. 481\u2013497.","DOI":"10.1007\/978-3-030-58601-0_29"},{"key":"1855_CR36","doi-asserted-by":"crossref","unstructured":"Li, S., Gong, K., Liu, C.H., et\u00a0al. (2021). Metasaug: Meta semantic augmentation for long-tailed visual recognition. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 5212\u20135221.","DOI":"10.1109\/CVPR46437.2021.00517"},{"key":"1855_CR37","doi-asserted-by":"crossref","unstructured":"Li, S., He, C., Li, R., et\u00a0al (2022a) A dual weighting label assignment scheme for object detection. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 9387\u20139396.","DOI":"10.1109\/CVPR52688.2022.00917"},{"key":"1855_CR38","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao, H., Girshick, R., et\u00a0al. (2022b). Exploring plain vision transformer backbones for object detection. arXiv preprint arXiv:2203.16527.","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"1855_CR39","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire. M., Belongie. S., et\u00a0al. (2014). Microsoft coco: Common objects in context. In European Conference on Computer Vision (ECCV). pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1855_CR40","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., et\u00a0al. (2017a). Feature pyramid networks for object detection. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"1855_CR41","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., et\u00a0al. (2017b). Focal loss for dense object detection. In IEEE International Conference on Computer Vision (ICCV). pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1855_CR42","doi-asserted-by":"crossref","unstructured":"Liu, J., Leng, J., Ying, L. (2019a). Deep convolutional neural network based object detector for x-ray baggage security imagery. In IEEE International Conference on Tools with Artificial Intelligence (ICTAI). pp. 1757\u20131761.","DOI":"10.1109\/ICTAI.2019.00262"},{"key":"1855_CR43","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., et\u00a0al. (2018). Path aggregation network for instance segmentation. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 8759\u20138768.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"1855_CR44","unstructured":"Liu, S., Huang, D., & Wang, Y. (2019b). Learning spatial fusion for single-shot object detection. arXiv preprint arXiv:1911.09516."},{"key":"1855_CR45","unstructured":"Liu, S., Zhang, L., Yang, X., et\u00a0al. (2021). Query2label: A simple transformer way to multi-label classification. arXiv preprint arXiv:2107.10834."},{"key":"1855_CR46","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., et\u00a0al. (2016). Ssd: Single shot multibox detector. In European Conference on Computer Vision (ECCV). pp. 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1855_CR47","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101."},{"issue":"4","key":"1855_CR48","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1007\/s10921-015-0315-7","volume":"34","author":"D Mery","year":"2015","unstructured":"Mery, D., Riffo, V., Zscherpel, U., et al. (2015). Gdxray: The database of x-ray images for nondestructive testing. Journal of Nondestructive Evaluation, 34(4), 42.","journal-title":"Journal of Nondestructive Evaluation"},{"key":"1855_CR49","doi-asserted-by":"publisher","first-page":"145620","DOI":"10.1109\/ACCESS.2020.3015014","volume":"8","author":"D Mery","year":"2020","unstructured":"Mery, D., Saavedra, D., & Prasad, M. (2020). X-ray baggage inspection with computer vision: A survey. IEEE Access, 8, 145620\u2013145633.","journal-title":"IEEE Access"},{"key":"1855_CR50","doi-asserted-by":"crossref","unstructured":"Miao, C., Xie, L., Wan, F., et\u00a0al. (2019). Sixray: A large-scale security inspection x-ray benchmark for prohibited item discovery in overlapping images. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 2119\u20132128.","DOI":"10.1109\/CVPR.2019.00222"},{"key":"1855_CR51","unstructured":"Mnih, V., Heess, N., Graves, A., et\u00a0al. (2014). Recurrent models of visual attention. Advances in Neural Information Processing Systems In Proceeings of Neural Information Processing Systems (NIPS). 27."},{"key":"1855_CR52","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., et\u00a0al. (2019). Libra r-cnn: Towards balanced learning for object detection. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 821\u2013830.","DOI":"10.1109\/CVPR.2019.00091"},{"key":"1855_CR53","doi-asserted-by":"crossref","unstructured":"Qin, Z., Zhang, P., Wu, F., et\u00a0al. (2021), Fcanet: Frequency channel attention networks. In IEEE International Conference on Computer Vision (ICCV). pp. 783\u2013792.","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"1855_CR54","doi-asserted-by":"crossref","unstructured":"Redmon, J., & Farhadi, A. (2017). Yolo9000: better, faster, stronger. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 7263\u20137271.","DOI":"10.1109\/CVPR.2017.690"},{"key":"1855_CR55","unstructured":"Redmon, J., Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767."},{"key":"1855_CR56","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., et\u00a0al. (2016). You only look once: Unified, real-time object detection. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"1855_CR57","unstructured":"Ren, S., He, K., Girshick, R., et\u00a0al. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Annual Conference on Neural Information Processing Systems (NIPS). pp. 91\u201399."},{"key":"1855_CR58","doi-asserted-by":"crossref","unstructured":"Ridnik, T., Lawen, H., Noy, A., et\u00a0al. (2020). Tresnet: High performance gpu-dedicated architecture. 2003.13630.","DOI":"10.1109\/WACV48630.2021.00144"},{"key":"1855_CR59","doi-asserted-by":"crossref","unstructured":"Ridnik, T., Ben-Baruch, E., Zamir, N., et\u00a0al. (2021a). Asymmetric loss for multi-label classification. In IEEE International Conference on Computer Vision (ICCV). pp. 82\u201391.","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"1855_CR60","unstructured":"Ridnik, T., Sharir, G., Ben-Cohen, A., et\u00a0al. (2021b). Ml-decoder: Scalable and versatile classification head. arXiv preprint arXiv:2111.12933."},{"key":"1855_CR61","doi-asserted-by":"publisher","first-page":"7803","DOI":"10.1007\/s00521-020-05521-2","volume":"33","author":"D Saavedra","year":"2021","unstructured":"Saavedra, D., Banerjee, S., & Mery, D. (2021). Detection of threat objects in baggage inspection with x-ray images using deep learning. Neural Computing and Applications, 33, 7803\u20137819.","journal-title":"Neural Computing and Applications"},{"key":"1855_CR62","unstructured":"Sermanet, P., Eigen, D., Zhang, X., et\u00a0al. (2013). Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229."},{"key":"1855_CR63","doi-asserted-by":"crossref","unstructured":"Smith, L.N., & Topin, N. (2019). Super-convergence: Very fast training of neural networks using large learning rates. In Artificial Intelligence and Machine Learning for Multi-domain Operations Applications. pp. 369\u2013386.","DOI":"10.1117\/12.2520589"},{"key":"1855_CR64","doi-asserted-by":"crossref","unstructured":"Tao, R., Wei, Y., Jiang, X., et\u00a0al. (2021a). Towards real-world x-ray security inspection: A high-quality benchmark and lateral inhibition module for prohibited items detection. In IEEE ICCV.","DOI":"10.1109\/ICCV48922.2021.01074"},{"key":"1855_CR65","unstructured":"Tao, R., Wei, Y., Li, H., et\u00a0al. (2021b). Over-sampling de-occlusion attention network for prohibited items detection in noisy x-ray images. arXiv preprint arXiv:2103.00809."},{"key":"1855_CR66","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., et\u00a0al. (2019). Fcos: Fully convolutional one-stage object detection. In IEEE International Conference on Computer Vision (ICCV) pp. 9627\u20139636.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"1855_CR67","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al. (2017). Attention is all you need. NIPS 30 5998\u20136008."},{"issue":"8","key":"1855_CR68","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3549932","volume":"55","author":"D Velayudhan","year":"2022","unstructured":"Velayudhan, D., Hassan, T., Damiani, E., et al. (2022). Recent advances in baggage threat detection: A comprehensive and systematic survey. ACM Computing Surveys, 55(8), 1\u201338.","journal-title":"ACM Computing Surveys"},{"key":"1855_CR69","doi-asserted-by":"crossref","unstructured":"Wang, B., Zhang, L., Wen, L., et\u00a0al. (2021). Towards real-world prohibited item detection: A large-scale x-ray benchmark. In IEEE International Conference on Computer Vision (ICCV), pp. 5412\u20135421.","DOI":"10.1109\/ICCV48922.2021.00536"},{"key":"1855_CR70","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, K., Xu, R., et\u00a0al. (2019a). Carafe: Content-aware reassembly of features. In IEEE International Conference on Computer Vision (ICCV). pp. 3007\u20133016.","DOI":"10.1109\/ICCV.2019.00310"},{"key":"1855_CR71","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., et\u00a0al. (2020). Eca-net: Efficient channel attention for deep convolutional neural networks. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR).","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"1855_CR72","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta. A., et al. (2018) Non-local neural networks. In: IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR).","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1855_CR73","doi-asserted-by":"crossref","unstructured":"Wang, Y., Gan, W., Yang, J., et\u00a0al. (2019b). Dynamic curriculum learning for imbalanced data classification. In: IEEE International Conference on Computer Vision (ICCV). pp. 5017\u20135026.","DOI":"10.1109\/ICCV.2019.00512"},{"key":"1855_CR74","unstructured":"Wang, Y., Pan, X., Song, S., et\u00a0al. (2019c). Implicit semantic data augmentation for deep networks. Advances in Neural Information Processing Systems 32"},{"key":"1855_CR75","doi-asserted-by":"crossref","unstructured":"Wei, Y., Tao, R., Wu, Z., et\u00a0al. (2020). Occluded prohibited items detection: An x-ray security inspection benchmark and de-occlusion attention module. In Proceedings of the 28th ACM International Conference on Multimedia. pp. 138\u2013146.","DOI":"10.1145\/3394171.3413828"},{"key":"1855_CR76","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., et\u00a0al. (2018). Cbam: Convolutional block attention module. In European Conference on Computer Vision (ECCV)., pp. 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1855_CR77","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., et\u00a0al. (2021). Cvt: Introducing convolutions to vision transformers. In IEEE International Conference on Computer Vision (ICCV), pp. 22\u201331.","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"1855_CR78","doi-asserted-by":"crossref","unstructured":"Xiang, L., Ding, G., & Han, J. (2020). Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification. In European Conference on Computer Vision (ECCV), Springer, pp. 247\u2013263.","DOI":"10.1007\/978-3-030-58558-7_15"},{"key":"1855_CR79","doi-asserted-by":"crossref","unstructured":"Yin, X., Yu, X., Sohn, K., et\u00a0al. (2019). Feature transfer learning for face recognition with under-represented data. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR). pp. 5704\u20135713.","DOI":"10.1109\/CVPR.2019.00585"},{"key":"1855_CR80","doi-asserted-by":"crossref","unstructured":"Zhou, B., Cui, Q., Wei, X.S., et\u00a0al. (2020). Bbn: Bilateral-branch network with cumulative learning for long-tailed visual recognition. In IEEE International Conference on Computer Vision and Pattern Recognition Conference (CVPR), pp. 9719\u20139728.","DOI":"10.1109\/CVPR42600.2020.00974"},{"key":"1855_CR81","doi-asserted-by":"crossref","unstructured":"Zhu, K., Wu, J. (2021). Residual attention: A simple but effective method for multi-label recognition. In IEEE International Conference on Computer Vision (ICCV), pp. 184\u2013193.","DOI":"10.1109\/ICCV48922.2021.00025"}],"updated-by":[{"DOI":"10.1007\/s11263-023-01889-5","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T00:00:00Z","timestamp":1692230400000}}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01855-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01855-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01855-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T10:07:41Z","timestamp":1698401261000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01855-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":81,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["1855"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01855-1","relation":{"correction":[{"id-type":"doi","id":"10.1007\/s11263-023-01889-5","asserted-by":"object"}]},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"7 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2023","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s11263-023-01889-5","URL":"https:\/\/doi.org\/10.1007\/s11263-023-01889-5","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}