{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T12:41:12Z","timestamp":1699533672643},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T00:00:00Z","timestamp":1667347200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T00:00:00Z","timestamp":1667347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Science and Technology Research Project of Wuhu City","award":["2020yf48"],"award-info":[{"award-number":["2020yf48"]}]},{"name":"Research Foundation of the Institute of Environment-friendly Materials and Occupational Health","award":["ALW2021YF04"],"award-info":[{"award-number":["ALW2021YF04"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s00371-022-02712-x","type":"journal-article","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T20:23:37Z","timestamp":1667420617000},"page":"6073-6084","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ACKSNet: adaptive center keypoint selection for object detection"],"prefix":"10.1007","volume":"39","author":[{"given":"Xingzhu","family":"Liang","sequence":"first","affiliation":[]},{"given":"Lixin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Xinyun","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Qing","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,2]]},"reference":[{"key":"2712_CR1","doi-asserted-by":"publisher","unstructured":"Cao, J., Cholakkal, H., Anwer, R.M., Khan, F.S., Pang, Y., Shao, L.: D2Det: towards high quality object detection and instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11485\u201311494 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01150","DOI":"10.1109\/CVPR42600.2020.01150"},{"key":"2712_CR2","doi-asserted-by":"publisher","unstructured":"Fan, Q., Zhuo, W., Tang, C.-K., Tai, Y.-W.: Few-shot object detection with attention-RPN and multi-relation detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4013\u20134022 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00407","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"2712_CR3","doi-asserted-by":"publisher","unstructured":"Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6054\u20136063 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00615","DOI":"10.1109\/ICCV.2019.00615"},{"key":"2712_CR4","doi-asserted-by":"publisher","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020). https:\/\/doi.org\/10.48550\/arXiv.2004.10934","DOI":"10.48550\/arXiv.2004.10934"},{"issue":"8","key":"2712_CR5","doi-asserted-by":"publisher","first-page":"2433","DOI":"10.1007\/s00371-020-01997-0","volume":"37","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Hu, Z., Hao, R.: Joint information fusion and multi-scale network model for pedestrian detection. Vis. Comput. 37(8), 2433\u20132442 (2021). https:\/\/doi.org\/10.1007\/s00371-020-01997-0","journal-title":"Vis. Comput."},{"key":"2712_CR6","doi-asserted-by":"publisher","unstructured":"Chen, J., Wu, Q., Liu, D., Xu, T.: Foreground-background imbalance problem in deep object detectors: a review. In: 2020 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), pp. 285\u2013290 (2020). IEEE. https:\/\/doi.org\/10.1109\/MIPR49039.2020.00066","DOI":"10.1109\/MIPR49039.2020.00066"},{"issue":"3","key":"2712_CR7","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1007\/s11263-019-01204-1","volume":"128","author":"H Law","year":"2020","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. Int. J. Comput. Vis. 128(3), 642\u2013656 (2020). https:\/\/doi.org\/10.1007\/s11263-019-01204-1","journal-title":"Int. J. Comput. Vis."},{"key":"2712_CR8","doi-asserted-by":"publisher","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6569\u20136578 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00667","DOI":"10.1109\/ICCV.2019.00667"},{"key":"2712_CR9","doi-asserted-by":"publisher","unstructured":"Zhou, X., Zhuo, J., Krahenbuhl, P.: Bottom-up object detection by grouping extreme and center points. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 850\u2013859 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00094","DOI":"10.1109\/CVPR.2019.00094"},{"issue":"6","key":"2712_CR10","doi-asserted-by":"publisher","first-page":"2223","DOI":"10.1007\/s00371-021-02280-6","volume":"38","author":"M Saeidi","year":"2022","unstructured":"Saeidi, M., Arabsorkhi, A.: A novel backbone architecture for pedestrian detection based on the human visual system. Vis. Comput. 38(6), 2223\u20132237 (2022). https:\/\/doi.org\/10.1007\/s00371-021-02280-6","journal-title":"Vis. Comput."},{"key":"2712_CR11","doi-asserted-by":"publisher","unstructured":"Dong, Z., Li, G., Liao, Y., Wang, F., Ren, P., Qian, C.: CentripetalNet: pursuing high-quality keypoint pairs for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10519\u201310528 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01053","DOI":"10.1109\/CVPR42600.2020.01053"},{"key":"2712_CR12","doi-asserted-by":"publisher","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping. arXiv preprint arXiv:1611.05424 (2016). https:\/\/doi.org\/10.48550\/arXiv.1611.05424","DOI":"10.48550\/arXiv.1611.05424"},{"key":"2712_CR13","doi-asserted-by":"publisher","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: European Conference on Computer Vision, pp. 483\u2013499 (2016). Springer. https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"2712_CR14","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"2712_CR15","doi-asserted-by":"publisher","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759\u20139768 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00978","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"2712_CR16","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2712_CR17","doi-asserted-by":"publisher","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.308","DOI":"10.1109\/CVPR.2016.308"},{"key":"2712_CR18","doi-asserted-by":"publisher","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"issue":"2","key":"2712_CR19","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/s00371-020-01794-9","volume":"37","author":"H Ben Fredj","year":"2021","unstructured":"Ben Fredj, H., Bouguezzi, S., Souani, C.: Face recognition in unconstrained environment with CNN. Vis. Comput. 37(2), 217\u2013226 (2021). https:\/\/doi.org\/10.1007\/s00371-020-01794-9","journal-title":"Vis. Comput."},{"issue":"6","key":"2712_CR20","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2712_CR21","doi-asserted-by":"publisher","unstructured":"Qin, Z., Li, Z., Zhang, Z., Bao, Y., Yu, G., Peng, Y., Sun, J.: ThunderNet: towards real-time generic object detection on mobile devices. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6718\u20136727 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00682","DOI":"10.1109\/ICCV.2019.00682"},{"key":"2712_CR22","doi-asserted-by":"publisher","unstructured":"Xie, X., Cheng, G., Wang, J., Yao, X., Han, J.: Oriented R-CNN for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3520\u20133529 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00350","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"2712_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02157-8","author":"K Roy","year":"2021","unstructured":"Roy, K., Sahay, R.R.: A robust multi-scale deep learning approach for unconstrained hand detection aided by skin segmentation. Vis. Comput. (2021). https:\/\/doi.org\/10.1007\/s00371-021-02157-8","journal-title":"Vis. Comput."},{"key":"2712_CR24","doi-asserted-by":"publisher","unstructured":"Li, H., Wu, Z., Zhu, C., Xiong, C., Socher, R., Davis, L.S.: Learning from noisy anchors for one-stage object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10588\u201310597 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01060","DOI":"10.1109\/CVPR42600.2020.01060"},{"issue":"1","key":"2712_CR25","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s00371-019-01787-3","volume":"37","author":"L Wei","year":"2021","unstructured":"Wei, L., Cui, W., Hu, Z., Sun, H., Hou, S.: A single-shot multi-level feature reused neural network for object detection. Vis. Comput. 37(1), 133\u2013142 (2021). https:\/\/doi.org\/10.1007\/s00371-019-01787-3","journal-title":"Vis. Comput."},{"key":"2712_CR26","doi-asserted-by":"publisher","unstructured":"Huang, X., Wang, X., Lv, W., Bai, X., Long, X., Deng, K., Dang, Q., Han, S., Liu, Q., Hu, X., et al.: PP-YOLOV2: a practical object detector. arXiv preprint arXiv:2104.10419 (2021). https:\/\/doi.org\/10.48550\/arXiv.2104.10419","DOI":"10.48550\/arXiv.2104.10419"},{"key":"2712_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02357-2","author":"T Zhang","year":"2022","unstructured":"Zhang, T., Li, Z., Sun, Z., Zhu, L.: A fully convolutional anchor-free object detector. Vis. Comput. (2022). https:\/\/doi.org\/10.1007\/s00371-021-02357-2","journal-title":"Vis. Comput."},{"issue":"2","key":"2712_CR28","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154\u2013171 (2013). https:\/\/doi.org\/10.1007\/s11263-013-0620-5","journal-title":"Int. J. Comput. Vis."},{"key":"2712_CR29","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2018.2844175","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"2712_CR30","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"2712_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2020.05.027","volume":"409","author":"D Liu","year":"2020","unstructured":"Liu, D., Cui, Y., Chen, Y., Zhang, J., Fan, B.: Video object detection for autonomous driving: motion-aid feature calibration. Neurocomputing 409, 1\u201311 (2020). https:\/\/doi.org\/10.1016\/j.neucom.2020.05.027","journal-title":"Neurocomputing"},{"issue":"3","key":"2712_CR32","doi-asserted-by":"publisher","first-page":"1742","DOI":"10.3390\/app12031742","volume":"12","author":"J Xiao","year":"2022","unstructured":"Xiao, J., Xu, J., Tian, C., Han, P., You, L., Zhang, S.: A serial attention frame for multi-label waste bottle classification. Appl. Sci. 12(3), 1742 (2022). https:\/\/doi.org\/10.3390\/app12031742","journal-title":"Appl. Sci."},{"key":"2712_CR33","doi-asserted-by":"publisher","unstructured":"Huang, L., Yang, Y., Deng, Y., Yu, Y.: DenseBox: unifying landmark localization with end to end object detection. arXiv preprint arXiv:1509.04874 (2015). https:\/\/doi.org\/10.48550\/arXiv.1509.04874","DOI":"10.48550\/arXiv.1509.04874"},{"key":"2712_CR34","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"issue":"99","key":"2712_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2020.3032166","volume":"5","author":"Z Tian","year":"2020","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: a simple and strong anchor-free object detector. IEEE Trans. Pattern Anal. Mach. Intell. 5(99), 1 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2020.3032166","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2712_CR36","doi-asserted-by":"publisher","unstructured":"Liu, D., Cui, Y., Tan, W., Chen, Y.: SG-Net: spatial granularity network for one-stage video instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9816\u20139825 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00969","DOI":"10.1109\/CVPR46437.2021.00969"},{"key":"2712_CR37","doi-asserted-by":"publisher","unstructured":"Cui, Y., Yan, L., Cao, Z., Liu, D.: TF-Blender: temporal feature blender for video object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8138\u20138147 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00803","DOI":"10.1109\/ICCV48922.2021.00803"},{"key":"2712_CR38","doi-asserted-by":"publisher","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet++ for object detection. arXiv preprint arXiv:2204.08394 (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.08394","DOI":"10.48550\/arXiv.2204.08394"},{"key":"2712_CR39","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229 (2020). Springer. https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2712_CR40","doi-asserted-by":"publisher","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: arXiv (2017). https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"2712_CR41","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1016\/j.patrec.2022.06.006","volume":"160","author":"K Huang","year":"2022","unstructured":"Huang, K., Tian, C., Su, J., Lin, J.C.-W.: Transformer-based cross reference network for video salient object detection. Pattern Recognit. Lett. 160, 122\u2013127 (2022). https:\/\/doi.org\/10.1016\/j.patrec.2022.06.006","journal-title":"Pattern Recognit. Lett."},{"key":"2712_CR42","doi-asserted-by":"publisher","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., Shum, H.-Y.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.03605","DOI":"10.48550\/arXiv.2203.03605"},{"key":"2712_CR43","doi-asserted-by":"publisher","unstructured":"Liu, S., Li, F., Zhang, H., Yang, X., Qi, X., Su, H., Zhu, J., Zhang, L.: DAB-DETR: dynamic anchor boxes are better queries for DETR. arXiv preprint arXiv:2201.12329 (2022). https:\/\/doi.org\/10.48550\/arXiv.2201.12329","DOI":"10.48550\/arXiv.2201.12329"},{"key":"2712_CR44","doi-asserted-by":"publisher","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DETR: accelerate DETR training by introducing query denoising. arXiv preprint arXiv:2203.01305 (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.01305","DOI":"10.48550\/arXiv.2203.01305"},{"key":"2712_CR45","doi-asserted-by":"publisher","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, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2712_CR46","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"2712_CR47","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A.: Automatic differentiation in PyTorch (2017)"},{"key":"2712_CR48","doi-asserted-by":"publisher","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). https:\/\/doi.org\/10.48550\/arXiv.1412.6980","DOI":"10.48550\/arXiv.1412.6980"},{"key":"2712_CR49","doi-asserted-by":"publisher","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS\u2014improving object detection with one line of code. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5561\u20135569 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.593","DOI":"10.1109\/ICCV.2017.593"},{"key":"2712_CR50","doi-asserted-by":"publisher","unstructured":"Shrivastava, A., Sukthankar, R., Malik, J., Gupta, A.: Beyond skip connections: top-down modulation for object detection. arXiv preprint arXiv:1612.06851 (2016). https:\/\/doi.org\/10.48550\/arXiv.1612.06851","DOI":"10.48550\/arXiv.1612.06851"},{"key":"2712_CR51","doi-asserted-by":"publisher","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra R-CNN: towards balanced learning for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 821\u2013830 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00091","DOI":"10.1109\/CVPR.2019.00091"},{"key":"2712_CR52","doi-asserted-by":"publisher","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z.: Single-shot refinement neural network for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4203\u20134212 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00442","DOI":"10.1109\/CVPR.2018.00442"},{"key":"2712_CR53","doi-asserted-by":"publisher","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00644","DOI":"10.1109\/CVPR.2018.00644"},{"key":"2712_CR54","doi-asserted-by":"publisher","unstructured":"Lu, X., Li, B., Yue, Y., Li, Q., Yan, J.: Grid R-CNN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7363\u20137372 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00754","DOI":"10.1109\/CVPR.2019.00754"},{"key":"2712_CR55","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018). https:\/\/doi.org\/10.48550\/arXiv.1804.02767","DOI":"10.48550\/arXiv.1804.02767"},{"key":"2712_CR56","doi-asserted-by":"publisher","unstructured":"Zhu, C., Chen, F., Shen, Z., Savvides, M.: Soft anchor-point object detection. In: European Conference on Computer Vision, pp. 91\u2013107 (2020). Springer. https:\/\/doi.org\/10.1007\/978-3-030-58545-7_6","DOI":"10.1007\/978-3-030-58545-7_6"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02712-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-022-02712-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02712-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T12:02:58Z","timestamp":1699531378000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-022-02712-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,2]]},"references-count":56,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["2712"],"URL":"https:\/\/doi.org\/10.1007\/s00371-022-02712-x","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,2]]},"assertion":[{"value":"20 October 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}