{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:23:35Z","timestamp":1740108215285,"version":"3.37.3"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 108-2218-E-415-001"],"award-info":[{"award-number":["MOST 108-2218-E-415-001"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s00138-023-01493-0","type":"journal-article","created":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T16:02:01Z","timestamp":1701878521000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pixel representations, sampling, and label correction for semantic part detection"],"prefix":"10.1007","volume":"35","author":[{"given":"Jiao-Chuan","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You-Lin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3647-2232","authenticated-orcid":false,"given":"Wen-Chieh","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,6]]},"reference":[{"key":"1493_CR1","doi-asserted-by":"crossref","unstructured":"Zhang, N., Donahue, J., Girshick, R.B., Darrell, T.: Part-based R-CNNs for fine-grained category detection. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 834\u2013849 (2014)","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"1493_CR2","doi-asserted-by":"crossref","unstructured":"Berg, T., Belhumeur, P.N.: POOF: Part-based one-vs.-one features for fine-grained categorization, face verification, and attribute estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 955\u2013962 (2013)","DOI":"10.1109\/CVPR.2013.128"},{"key":"1493_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xie, C., Wang, J., Xie, L., Yuille, A.L.: DeepVoting: a robust and explainable deep network for semantic part detection under partial occlusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1372\u20131380 (2018)","DOI":"10.1109\/CVPR.2018.00149"},{"key":"1493_CR4","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Zhao, C., Wang, J., Zhao, X., Wu, Y., Lu, H.: CoupleNet: coupling global structure with local parts for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4146\u20134154 (2017)","DOI":"10.1109\/ICCV.2017.444"},{"key":"1493_CR5","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Malik, J.: Actions and attributes from wholes and parts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2470\u20132478 (2015)","DOI":"10.1109\/ICCV.2015.284"},{"key":"1493_CR6","doi-asserted-by":"crossref","unstructured":"Vedaldi, A., Mahendran, S., Tsogkas, S., Maji, S., Girshick, R., Kannala, J., et\u00a0al.: Understanding objects in detail with fine-grained attributes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3622\u20133629 (2014)","DOI":"10.1109\/CVPR.2014.463"},{"key":"1493_CR7","doi-asserted-by":"crossref","unstructured":"Gonzalez-Garcia, A., Modolo, D., Ferrari, V.: Objects as context for detecting their semantic parts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6907\u20136916 (2018)","DOI":"10.1109\/CVPR.2018.00722"},{"key":"1493_CR8","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, Z., Xie, C., Zhu, J., Xie, L., Yuille, A.L.: Detecting semantic parts on partially occluded objects. In: Proceedings of British Machine Vision Conference (BMVC) (2017)","DOI":"10.5244\/C.31.73"},{"key":"1493_CR9","doi-asserted-by":"crossref","unstructured":"Yao, Q., Gong, X.: Exploiting LSTM for Joint object and semantic part detection. In: Proceedings of Asian Conference of Computer Vision (ACCV), pp. 498\u2013512 (2019)","DOI":"10.1007\/978-3-030-20873-8_32"},{"key":"1493_CR10","unstructured":"Morabia, K., Arora, J., Vijaykumar, T.: Attention-based Joint Detection of Object and Semantic Part. CoRR. 2020; abs\/2007.02419"},{"key":"1493_CR11","unstructured":"Souri, Y., Kasaei, S.: Fast bird part localization for fine-grained categorization. In: The Third Workshop on Fine-Grained Visual Categorization (FGVC3) in Conjunction with CVPR 2015 (2015)"},{"key":"1493_CR12","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"4","key":"1493_CR13","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1109\/TPAMI.2016.2578328","volume":"39","author":"B Hariharan","year":"2017","unstructured":"Hariharan, B., Arbelaez, P., Girshick, R.B., Malik, J.: Object instance segmentation and fine-grained localization using hypercolumns. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 627\u2013639 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1493_CR14","doi-asserted-by":"crossref","unstructured":"Simon, M., Rodner, E.: Neural activation constellations: unsupervised part model discovery with convolutional networks. In: Proceedings of the International Conference on Computer Vision (ICCV). pp. 1143\u20131151 (2015)","DOI":"10.1109\/ICCV.2015.136"},{"key":"1493_CR15","unstructured":"Zhu, Y., Xie, J., Tang, Z., Peng, X., Elgammal, A.: Semantic-guided multi-attention localization for zero-shot learning. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS), vol.\u00a032. pp. 14943\u201314953 (2019)"},{"key":"1493_CR16","doi-asserted-by":"crossref","unstructured":"Mostajabi, M., Yadollahpour, P., Shakhnarovich, G.: Feedforward semantic segmentation with zoom-out features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3376\u20133385 (2015)","DOI":"10.1109\/CVPR.2015.7298959"},{"key":"1493_CR17","doi-asserted-by":"crossref","unstructured":"Maire, M., Yu, S.X., Perona, P.: Reconstructive sparse code transfer for contour detection and semantic labeling. In: Proceedings of 12th Asian Conference on Computer Vision (ACCV), pp. 273\u2013287 (2014)","DOI":"10.1007\/978-3-319-16817-3_18"},{"key":"1493_CR18","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1016\/j.patrec.2019.10.031","volume":"128","author":"J Dietlmeier","year":"2019","unstructured":"Dietlmeier, J., McGuinness, K., Rugonyi, S., Wilson, T., Nuttall, A.L., O\u2019Connor, N.E.: Few-shot hypercolumn-based mitochondria segmentation in cardiac and outer hair cells in focused ion beam-scanning electron microscopy (FIB-SEM) data. Pattern Recogn. Lett. 128, 521\u2013528 (2019)","journal-title":"Pattern Recogn. Lett."},{"key":"1493_CR19","doi-asserted-by":"crossref","unstructured":"Larsson, G., Maire, M., Shakhnarovich, G.: Learning representations for automatic colorization. In: Proceedings of the 14th European Conference on Computer Vision (ECCV), pp. 577\u2013593 (2016)","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"1493_CR20","doi-asserted-by":"crossref","unstructured":"Park, H., Jeong, J., Yoo, Y., Kwak, N.: Superpixel-based semantic segmentation trained by statistical process control. In: Proceedings of 2017 British Machine Vision Conference (BMVC) (2017)","DOI":"10.5244\/C.31.78"},{"key":"1493_CR21","doi-asserted-by":"crossref","unstructured":"Naha, S., Xiao, Q., Banik, P., Reza, M.A., Crandall, D.J.: Pose-guided knowledge transfer for object part segmentation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR Workshops. pp. 3961\u20133955 (2020)","DOI":"10.1109\/CVPRW50498.2020.00461"},{"key":"1493_CR22","doi-asserted-by":"crossref","unstructured":"Tritrong, N., Rewatbowornwong, P., Suwajanakorn, S.: Repurposing GANs for one-shot semantic part segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4475\u20134485 (2021)","DOI":"10.1109\/CVPR46437.2021.00445"},{"key":"1493_CR23","doi-asserted-by":"crossref","unstructured":"Xia, F., Wang, P., Chen, X., Yuille, A.L.: Joint multi-person pose estimation and semantic part segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.644"},{"key":"1493_CR24","doi-asserted-by":"crossref","unstructured":"Li, D., Yang, J., Kreis, K., Torralba, A., Fidler, S.: Semantic segmentation with generative models: semi-supervised learning and strong out-of-domain generalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00820"},{"key":"1493_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Ling, H., Gao, J., Yin, K., Lafleche, J.F., Barriuso, A., et\u00a0al.: DatasetGAN: efficient labeled data factory with minimal human effort. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01001"},{"key":"1493_CR26","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Lu, G., Fang, X., Xie, J., Tai, Y.W., Lu, C.: Weakly and semi supervised human body part parsing via pose-guided knowledge transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00015"},{"key":"1493_CR27","doi-asserted-by":"crossref","unstructured":"Gong, K., Liang, X., Li, Y., Chen, Y., Yang, M., Lin, L.: Instance-level human parsing via part grouping network. In: Proceedings of the 15th European Conference on Computer Vision (ECCV), pp. 805\u2013822 (2018)","DOI":"10.1007\/978-3-030-01225-0_47"},{"key":"1493_CR28","doi-asserted-by":"crossref","unstructured":"Jackson, A., Valstar, M., Tzimiropoulos, G.: A CNN cascade for landmark guided semantic part segmentation. In: Proceedings of ECCV 2016 Workshops, Geometry meets Deep Learning (2016)","DOI":"10.1007\/978-3-319-49409-8_14"},{"key":"1493_CR29","doi-asserted-by":"crossref","unstructured":"Hung, W., Jampani, V., Liu, S., Molchanov, P., Yang, M., Kautz, J.: SCOPS: self-supervised co-part segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 869\u2013878 (2019)","DOI":"10.1109\/CVPR.2019.00096"},{"key":"1493_CR30","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.patcog.2017.05.025","volume":"71","author":"L Nanni","year":"2017","unstructured":"Nanni, L., Ghidoni, S., Brahnam, S.: Handcrafted vs. non-handcrafted features for computer vision classification. Pattern Recogn. 71, 158\u2013172 (2017)","journal-title":"Pattern Recogn."},{"issue":"2","key":"1493_CR31","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"1493_CR32","doi-asserted-by":"crossref","unstructured":"Shih, K.J., Mallya, A., Singh, S., Hoiem, D.: Part localization using multi-proposal consensus for fine-grained categorization. In: Proceedings of the British Machine Vision Conference (BMVC) (2015)","DOI":"10.5244\/C.29.128"},{"issue":"7","key":"1493_CR33","doi-asserted-by":"publisher","first-page":"1785","DOI":"10.1109\/TMM.2019.2954747","volume":"22","author":"C Liu","year":"2020","unstructured":"Liu, C., Xie, H., Zha, Z., Yu, L., Chen, Z., Zhang, Y.: Bidirectional attention\u2013recognition model for fine-grained object classification. IEEE Trans Multimed. 22(7), 1785\u20131795 (2020)","journal-title":"IEEE Trans Multimed."},{"key":"1493_CR34","doi-asserted-by":"publisher","first-page":"104129","DOI":"10.1016\/j.compbiomed.2020.104129","volume":"128","author":"M Salvi","year":"2021","unstructured":"Salvi, M., Acharya, U.R., Molinari, F., Meiburger, K.M.: The impact of pre- and post-image processing techniques on deep learning frameworks: a comprehensive review for digital pathology image analysis. Comput. Biol. Med. 128, 104129 (2021)","journal-title":"Comput. Biol. Med."},{"key":"1493_CR35","doi-asserted-by":"crossref","unstructured":"Bridson, R.: Fast Poisson disk sampling in arbitrary dimensions. In: ACM SIGGRAPH 2007 Sketches, p.\u00a022 (2007)","DOI":"10.1145\/1278780.1278807"},{"key":"1493_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34372-9","volume-title":"Computer Vision: Algorithms and Applications","author":"R Szeliski","year":"2022","unstructured":"Szeliski, R.: Computer Vision: Algorithms and Applications, 2nd edn. Springer, Berlin (2022)","edition":"2"},{"key":"1493_CR37","volume-title":"Computer Vision for Visual Effects","author":"RJ Radke","year":"2013","unstructured":"Radke, R.J.: Computer Vision for Visual Effects. Cambridge University Press, Cambridge (2013)"},{"issue":"3","key":"1493_CR38","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1145\/1015706.1015721","volume":"23","author":"J Sun","year":"2004","unstructured":"Sun, J., Jia, J., Tang, C.K., Shum, H.Y.: Poisson matting. ACM Trans. Graph. 23(3), 315\u2013321 (2004)","journal-title":"ACM Trans. Graph."},{"key":"1493_CR39","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1016\/j.eswa.2019.05.019","volume":"133","author":"C Henry","year":"2019","unstructured":"Henry, C., Lee, S.: Automatic trimap generation and artifact reduction in alpha matte using unknown region detection. Expert Syst. Appl. 133, 242\u2013259 (2019)","journal-title":"Expert Syst. Appl."},{"key":"1493_CR40","doi-asserted-by":"crossref","unstructured":"Hsieh, C., Lee, M.: Automatic trimap generation for digital image matting. In: Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 1\u20135 (2013)","DOI":"10.1109\/APSIPA.2013.6694178"},{"key":"1493_CR41","doi-asserted-by":"crossref","unstructured":"Taniguchi, M., Tezuka, T.: Automatic trimap generation by a multimodal neural network. In: Proceedings of IEEE International Conference on Image Processing (ICIP), pp. 2768\u20132772 (2021)","DOI":"10.1109\/ICIP42928.2021.9506481"},{"key":"1493_CR42","doi-asserted-by":"publisher","first-page":"19332","DOI":"10.1109\/ACCESS.2019.2896084","volume":"7","author":"J Li","year":"2019","unstructured":"Li, J., Yuan, G., Fan, H.: Generating trimap for image matting using color co-fusion. IEEE Access 7, 19332\u201319354 (2019)","journal-title":"IEEE Access"},{"key":"1493_CR43","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1016\/j.imavis.2013.06.002","volume":"31","author":"E Shahrian","year":"2013","unstructured":"Shahrian, E., Rajan, D.: Using texture to complement color in image matting. Image Vis. Comput. 31, 658\u2013672 (2013)","journal-title":"Image Vis. Comput."},{"issue":"2","key":"1493_CR44","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1109\/TNNLS.2014.2369426","volume":"26","author":"Q Zhu","year":"2015","unstructured":"Zhu, Q., Shao, L., Li, X., Wang, L.: Targeting accurate object extraction from an image: a comprehensive study of natural image matting. IEEE Trans. Neural Netw. Learn. Syst. 26(2), 185\u2013207 (2015)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1493_CR45","doi-asserted-by":"crossref","unstructured":"Sengupta, S., Jayaram, V., Curless, B., Seitz, S., Kemelmacher-Shlizerman, I.: Background matting: the world is your green screen. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2288\u20132297 (2020)","DOI":"10.1109\/CVPR42600.2020.00236"},{"key":"1493_CR46","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of 3rd International Conference on Learning Representations (ICLR) (2015)"},{"key":"1493_CR47","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. California Institute of Technology. CNS-TR-2011-001 (2011)"},{"key":"1493_CR48","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.V.: Cats and dogs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"1493_CR49","doi-asserted-by":"crossref","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Proceedings of the 14th European conference on computer vision (ECCV), pp. 391\u2013405 (2014)","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"1493_CR50","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of 26th Advances in Neural Information Processing Systems (NeurIPS), pp. 1097\u20131105 (2012)"},{"key":"1493_CR51","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 630\u2013645 (2016)","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"1493_CR52","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1800\u20131807 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"1493_CR53","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: Proceedings of the thirty-first AAAI conference on artificial intelligence (AAAI), pp. 4278\u20134284 (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1493_CR54","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, Y., Xu, Y., Miao, Z., Li, H.: Does ResNet learn good general purpose features? In: Proceedings of the 2017 International Conference on Artificial Intelligence, Automation and Control Technologies (2017)","DOI":"10.1145\/3080845.3080864"},{"key":"1493_CR55","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.ins.2019.12.084","volume":"517","author":"P Gao","year":"2020","unstructured":"Gao, P., Zhang, Q., Wang, F., Xiao, L., Fujita, H., Zhang, Y.: Learning reinforced attentional representation for end-to-end visual tracking. Inf. Sci. 517, 52\u201367 (2020)","journal-title":"Inf. Sci."},{"issue":"8","key":"1493_CR56","doi-asserted-by":"publisher","first-page":"1885","DOI":"10.1162\/089976699300016007","volume":"11","author":"E Alpaydm","year":"1999","unstructured":"Alpaydm, E.: Combined $$5 \\times 2$$ cv F test for comparing supervised classification learning algorithms. Neural Comput. 11(8), 1885\u20131892 (1999)","journal-title":"Neural Comput."},{"key":"1493_CR57","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1038\/s41598-022-27350-0","volume":"13","author":"NJ Neeteson","year":"2023","unstructured":"Neeteson, N.J., Besler, B.A., Whittier, D.E., Boyd, S.K.: Automatic segmentation of trabecular and cortical compartments in HR-pQCT images using an embedding-predicting U-Net and morphological post-processing. Sci. Rep. 13, 252 (2023)","journal-title":"Sci. Rep."},{"key":"1493_CR58","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1016\/j.cviu.2004.06.003","volume":"97","author":"J Min","year":"2005","unstructured":"Min, J., Bowyer, K.W.: Improved range image segmentation by analyzing surface fit patterns. Comput. Vis. Image Underst. 97, 242\u2013258 (2005)","journal-title":"Comput. Vis. Image Underst."},{"key":"1493_CR59","doi-asserted-by":"publisher","first-page":"e453","DOI":"10.7717\/peerj.453","volume":"2","author":"S van der Walt","year":"2014","unstructured":"van der Walt, S., Sch\u00f6nberger, J.L., Nunez-Iglesias, J., Boulogne, F., Warner, J.D., Yager, N., et al.: scikit-image: image processing in Python. PeerJ. 2, e453 (2014)","journal-title":"PeerJ."},{"key":"1493_CR60","volume-title":"Advanced Video Coding: Principles and Techniques","author":"KN Ngan","year":"1999","unstructured":"Ngan, K.N., Meier, T., Chai, D.: Advanced Video Coding: Principles and Techniques, 1st edn. Elsevier, Amsterdam (1999)","edition":"1"},{"key":"1493_CR61","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45, 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"1493_CR62","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems (NeurIPS), pp. 91\u201399 (2015)"},{"key":"1493_CR63","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: YOLO by Ultralytics. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"1493_CR64","doi-asserted-by":"publisher","first-page":"103514","DOI":"10.1016\/j.dsp.2022.103514","volume":"126","author":"SSA Zaidi","year":"2022","unstructured":"Zaidi, S.S.A., Ansari, M.S., Aslam, A., Kanwal, N., Asghar, M., Lee, B.: A survey of modern deep learning based object detection models. Digit. Signal Process. 126, 103514 (2022)","journal-title":"Digit. Signal Process."},{"issue":"3","key":"1493_CR65","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/JPROC.2023.3238524","volume":"111","author":"Z Zou","year":"2023","unstructured":"Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey. Proc. IEEE 111(3), 257\u2013276 (2023)","journal-title":"Proc. IEEE"},{"key":"1493_CR66","doi-asserted-by":"publisher","first-page":"128837","DOI":"10.1109\/ACCESS.2019.2939201","volume":"7","author":"L Jiao","year":"2019","unstructured":"Jiao, L., Zhang, F., Liu, F., Yang, S., Li, L., Feng, Z., et al.: A survey of deep learning-based object detection. IEEE Access 7, 128837\u2013128868 (2019)","journal-title":"IEEE Access"},{"issue":"11","key":"1493_CR67","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","volume":"30","author":"ZQ Zhao","year":"2019","unstructured":"Zhao, Z.Q., Zheng, P., Xu, S.T., Wu, X.: Object detection with deep learning: a review. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3212\u20133232 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1493_CR68","doi-asserted-by":"crossref","unstructured":"Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., et\u00a0al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.351"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01493-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-023-01493-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-023-01493-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T09:05:32Z","timestamp":1706000732000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-023-01493-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,6]]},"references-count":68,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["1493"],"URL":"https:\/\/doi.org\/10.1007\/s00138-023-01493-0","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"type":"print","value":"0932-8092"},{"type":"electronic","value":"1432-1769"}],"subject":[],"published":{"date-parts":[[2023,12,6]]},"assertion":[{"value":"11 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"10"}}