{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T10:32:16Z","timestamp":1776335536836,"version":"3.51.2"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T00:00:00Z","timestamp":1688688000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T00:00:00Z","timestamp":1688688000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Jiangsu Province Frontier Leading Technology Basic Research Special Project of China","award":["BK20202007"],"award-info":[{"award-number":["BK20202007"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s00371-023-02899-7","type":"journal-article","created":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T20:19:17Z","timestamp":1688761157000},"page":"2015-2034","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Two-stage filtering method to improve the performance of object detection trained by synthetic dataset in heavily cluttered industry scenes"],"prefix":"10.1007","volume":"40","author":[{"given":"Pengzhou","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9888-702X","authenticated-orcid":false,"given":"Yu","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanguan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangliang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Pu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zifan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,7]]},"reference":[{"key":"2899_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-022-01971-8","author":"WF Hu","year":"2022","unstructured":"Hu, W.F., Shao, J.Y., Jiao, Q., Wang, C.X., Cheng, J., Liu, Z.Y., Tan, J.R.: A new differentiable architecture search method for optimizing convolutional neural networks in the digital twin of intelligent robotic grasping. J. Intell. Manuf. (2022). https:\/\/doi.org\/10.1007\/s10845-022-01971-8","journal-title":"J. Intell. Manuf."},{"issue":"9\u201312","key":"2899_CR2","doi-asserted-by":"publisher","first-page":"4095","DOI":"10.1007\/s00170-019-03527-2","volume":"102","author":"J Zubizarreta","year":"2019","unstructured":"Zubizarreta, J., Aguinaga, I., Amundarain, A.: A framework for augmented reality guidance in industry. Int. J. Adv. Manuf. Technol. 102(9\u201312), 4095\u20134108 (2019). https:\/\/doi.org\/10.1007\/s00170-019-03527-2","journal-title":"Int. J. Adv. Manuf. Technol."},{"issue":"10","key":"2899_CR3","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3390\/ma14102575","volume":"14","author":"H Wen","year":"2021","unstructured":"Wen, H., Huang, C., Guo, S.M.: The application of convolutional neural networks (CNNs) to recognize defects in 3D-printed parts. Materials 14(10), 14 (2021). https:\/\/doi.org\/10.3390\/ma14102575","journal-title":"Materials"},{"issue":"2","key":"2899_CR4","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu, L., Ouyang, W.L., Wang, X.G., Fieguth, P., Chen, J., Liu, X.W., Pietikainen, M.: Deep learning for generic object detection: a survey. Int. J. Comput. Vis. 128(2), 261\u2013318 (2020). https:\/\/doi.org\/10.1007\/s11263-019-01247-4","journal-title":"Int. J. Comput. Vis."},{"key":"2899_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02210-6","author":"WH Hu","year":"2022","unstructured":"Hu, W.H., Wang, T., Wang, Y.S., Chen, Z.Y., Huang, G.H.: LE-MSFE-DDNet: a defect detection network based on low-light enhancement and multi-scale feature extraction. Vis. Comput. (2022). https:\/\/doi.org\/10.1007\/s00371-021-02210-6","journal-title":"Vis. Comput."},{"issue":"1","key":"2899_CR6","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s00371-018-1588-5","volume":"36","author":"YB Huang","year":"2020","unstructured":"Huang, Y.B., Qiu, C.Y., Yuan, K.: Surface defect saliency of magnetic tile. Vis. Comput. 36(1), 85\u201396 (2020). https:\/\/doi.org\/10.1007\/s00371-018-1588-5","journal-title":"Vis. Comput."},{"key":"2899_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-022-02597-w","author":"J Sun","year":"2022","unstructured":"Sun, J., Yan, S.B., Song, X.W.: QCNet: query context network for salient object detection of automatic surface inspection. Vis. Comput. (2022). https:\/\/doi.org\/10.1007\/s00371-022-02597-w","journal-title":"Vis. Comput."},{"issue":"1","key":"2899_CR8","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98\u2013136 (2015). https:\/\/doi.org\/10.1007\/s11263-014-0733-5","journal-title":"Int. J. Comput. Vis."},{"key":"2899_CR9","doi-asserted-by":"publisher","first-page":"1336","DOI":"10.1016\/j.jmapro.2021.02.034","volume":"64","author":"D Peddireddy","year":"2021","unstructured":"Peddireddy, D., Fu, X.Y., Shankar, A., Wang, H.B., Joung, B.G., Aggarwal, V., Sutherland, J.W., Jun, M.B.G.: Identifying manufacturability and machining processes using deep 3D convolutional networks. J. Manuf. Process. 64, 1336\u20131348 (2021). https:\/\/doi.org\/10.1016\/j.jmapro.2021.02.034","journal-title":"J. Manuf. Process."},{"issue":"5","key":"2899_CR10","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s00138-021-01237-y","volume":"32","author":"T Pengzhou","year":"2021","unstructured":"Pengzhou, T., Yu, G., Han, L., Zhen, W., Guanguan, Z., Jun, P.: Image dataset creation and networks improvement method based on CAD model and edge operator for object detection in the manufacturing industry. Mach. Vis. Appl. 32(5), 111 (2021). https:\/\/doi.org\/10.1007\/s00138-021-01237-y","journal-title":"Mach. Vis. Appl."},{"key":"2899_CR11","doi-asserted-by":"publisher","unstructured":"Sampaio, I.G.B., Machaca, L., Viterbo, J., Guerin, J.: A novel method for object detection using deep learning and CAD models. In: 23rd International Conference on Enterprise Information Systems (ICEIS), pp. 75\u201382. (2021). https:\/\/doi.org\/10.5220\/0010451100750082","DOI":"10.5220\/0010451100750082"},{"key":"2899_CR12","doi-asserted-by":"publisher","unstructured":"Lee, W.C., Huang, S.H., IEEE: Generating datasets from 3D CAD models for object detection. In: 30th IEEE International Symposium on Industrial Electronics (ISIE). (2021). https:\/\/doi.org\/10.1109\/isie45552.2021.9576247","DOI":"10.1109\/isie45552.2021.9576247"},{"issue":"3","key":"2899_CR13","doi-asserted-by":"publisher","first-page":"7201","DOI":"10.1109\/LRA.2022.3180403","volume":"7","author":"X Yang","year":"2022","unstructured":"Yang, X., Fan, X., Wang, J., Lee, K.: Image translation based synthetic data generation for industrial object detection and pose estimation. IEEE Robot. Autom. Lett. 7(3), 7201\u20137208 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"3","key":"2899_CR14","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z.H., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"key":"2899_CR15","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollar, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: 13th European Conference on Computer Vision (ECCV), pp. 740\u2013755. (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"7","key":"2899_CR16","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., Duerig, T., Ferrari, V.: The open images dataset V4 unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vis. 128(7), 1956\u20131981 (2020). https:\/\/doi.org\/10.1007\/s11263-020-01316-z","journal-title":"Int. J. Comput. Vis."},{"key":"2899_CR17","doi-asserted-by":"crossref","unstructured":"Wu, Z., Wang, L., Wang, W., Shi, T., Chen, C., Hao, A., Li, S.: Synthetic data supervised salient object detection. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5557\u20135565. (2022)","DOI":"10.1145\/3503161.3547930"},{"key":"2899_CR18","unstructured":"Lenn, J., Liu, C., Adam, H., Yu, L., Changyu, L., Prashant, R., Trevor, S.: ultralytics\/yolov5: Initial Release (v1.0). (2020)"},{"key":"2899_CR19","doi-asserted-by":"crossref","unstructured":"Liu, D.F., Cui, Y.M., Cao, Z.W., Chen, Y.J.: A large-scale simulation dataset: boost the detection accuracy for special weather conditions. In: International Joint Conference on Neural Networks (IJCNN) held as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI). (2020)","DOI":"10.1109\/IJCNN48605.2020.9206716"},{"key":"2899_CR20","doi-asserted-by":"publisher","unstructured":"Dwibedi, D., Misra, I., Hebert, M., IEEE: Cut, paste and learn: surprisingly easy synthesis for instance detection. In: 16th IEEE International Conference on Computer Vision (ICCV), pp. 1310\u20131319. (2017). https:\/\/doi.org\/10.1109\/iccv.2017.146","DOI":"10.1109\/iccv.2017.146"},{"key":"2899_CR21","doi-asserted-by":"crossref","unstructured":"Jo, H., Na, Y.H., Song, J.B., IEEE: Data augmentation using synthesized images for object detection. In: 17th International Conference on Control, Automation and Systems (ICCAS), pp. 1035\u20131038. (2017)","DOI":"10.23919\/ICCAS.2017.8204369"},{"key":"2899_CR22","doi-asserted-by":"crossref","unstructured":"Georgakis, G., Mousavian, A., Berg, A.C., Kosecka, J.: Synthesizing training data for object detection in indoor scenes. In: 13th Conference on Robotics\u2014Science and Systems. (2017)","DOI":"10.15607\/RSS.2017.XIII.043"},{"key":"2899_CR23","doi-asserted-by":"publisher","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A., IEEE: Synthetic data for text localisation in natural images. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2315\u20132324 (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.254","DOI":"10.1109\/cvpr.2016.254"},{"key":"2899_CR24","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.autcon.2020.103198","volume":"115","author":"S Bang","year":"2020","unstructured":"Bang, S., Baek, F., Park, S., Kim, W., Kim, H.: Image augmentation to improve construction resource detection using generative adversarial networks, cut-and-paste, and image transformation techniques. Autom. Constr. 115, 11 (2020). https:\/\/doi.org\/10.1016\/j.autcon.2020.103198","journal-title":"Autom. Constr."},{"issue":"6","key":"2899_CR25","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1111\/cgf.14047","volume":"39","author":"A Tsirikoglou","year":"2020","unstructured":"Tsirikoglou, A., Eilertsen, G., Unger, J.: A Survey of Image Synthesis Methods for Visual Machine Learning. Comput. Graph. Forum. 39(6), 426\u2013451 (2020). https:\/\/doi.org\/10.1111\/cgf.14047","journal-title":"Comput. Graph. Forum."},{"key":"2899_CR26","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.jmsy.2020.02.010","volume":"55","author":"ZH Lai","year":"2020","unstructured":"Lai, Z.H., Tao, W.J., Leu, M.C., Yin, Z.Z.: Smart augmented reality instructional system for mechanical assembly towards worker-centered intelligent manufacturing. J. Manuf. Syst. 55, 69\u201381 (2020). https:\/\/doi.org\/10.1016\/j.jmsy.2020.02.010","journal-title":"J. Manuf. Syst."},{"key":"2899_CR27","doi-asserted-by":"publisher","unstructured":"Cohen, J., Crispim, C., Grange-Faivre, C., Tougne, L.: CAD-based learning for egocentric object detection in industrial context. In: 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP)\/15th International Conference on Computer Vision Theory and Applications (VISAPP), pp. 644\u2013651. (2020). https:\/\/doi.org\/10.5220\/0008975506440651","DOI":"10.5220\/0008975506440651"},{"key":"2899_CR28","doi-asserted-by":"publisher","unstructured":"Peng, X.C., Sun, B.C., Ali, K., Saenko, K., IEEE: Learning deep object detectors from 3D models. In: IEEE International Conference on Computer Vision, pp. 1278\u20131286. (2015). https:\/\/doi.org\/10.1109\/iccv.2015.151","DOI":"10.1109\/iccv.2015.151"},{"key":"2899_CR29","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.robot.2017.06.003","volume":"95","author":"HR Zhang","year":"2017","unstructured":"Zhang, H.R., Cao, Q.X.: Texture-less object detection and 6D pose estimation in RGB-D images. Robot. Auton. Syst. 95, 64\u201379 (2017). https:\/\/doi.org\/10.1016\/j.robot.2017.06.003","journal-title":"Robot. Auton. Syst."},{"issue":"23","key":"2899_CR30","doi-asserted-by":"publisher","first-page":"7901","DOI":"10.3390\/s21237901","volume":"21","author":"L Eversberg","year":"2021","unstructured":"Eversberg, L., Lambrecht, J.: Generating images with physics-based rendering for an industrial object detection task: realism versus domain randomization. Sensors 21(23), 7901 (2021)","journal-title":"Sensors"},{"issue":"1","key":"2899_CR31","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11263-014-0748-y","volume":"119","author":"JX Xiao","year":"2016","unstructured":"Xiao, J.X., Ehinger, K.A., Hays, J., Torralba, A., Oliva, A.: SUN database: exploring a large collection of scene categories. Int. J. Comput. Vis. 119(1), 3\u201322 (2016). https:\/\/doi.org\/10.1007\/s11263-014-0748-y","journal-title":"Int. J. Comput. Vis."},{"key":"2899_CR32","doi-asserted-by":"publisher","unstructured":"Sarkar, K., Varanasi, K., Stricker, D.: Trained 3D models for CNN based object recognition. In: 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP), pp. 130\u2013137. (2017). https:\/\/doi.org\/10.5220\/0006272901300137","DOI":"10.5220\/0006272901300137"},{"key":"2899_CR33","doi-asserted-by":"publisher","unstructured":"Hinterstoisser, S., Lepetit, V., Wohlhart, P., Konolige, K.: On pre-trained image features and synthetic images for deep learning. In: 15th European Conference on Computer Vision (ECCV), pp. 682\u2013697. (2018). https:\/\/doi.org\/10.1007\/978-3-030-11009-3_42","DOI":"10.1007\/978-3-030-11009-3_42"},{"key":"2899_CR34","unstructured":"Bochkovskiy, A., Chien-Yao, W., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv (USA), pp. 17 (2020)"},{"issue":"7\u20138","key":"2899_CR35","doi-asserted-by":"publisher","first-page":"2259","DOI":"10.1007\/s00170-020-06185-x","volume":"111","author":"CHG Li","year":"2020","unstructured":"Li, C.H.G., Huang, Y.H.: Deep-trained illumination-robust precision positioning for real-time manipulation of embedded objects. Int. J. Adv. Manuf. Technol. 111(7\u20138), 2259\u20132276 (2020). https:\/\/doi.org\/10.1007\/s00170-020-06185-x","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"2899_CR36","doi-asserted-by":"publisher","unstructured":"Kennedy, J., Eberhart, R., IEEE: Particle swarm optimization. In: 1995 IEEE International Conference on Neural Networks (ICNN 95), pp. 1942\u20131948. (1995). https:\/\/doi.org\/10.1109\/icnn.1995.488968","DOI":"10.1109\/icnn.1995.488968"},{"key":"2899_CR37","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)\/Workshop on Machine Learning Methods for High-Level Cognitive Capabilities in Robotics, pp. 23\u201330. (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"2899_CR38","doi-asserted-by":"publisher","unstructured":"Tremblay, J., Prakash, A., Acuna, D., Brophy, M., Jampani, V., Anil, C., To, T., Cameracci, E., Boochoon, S., Birchfield, S., IEEE: training deep networks with synthetic data: bridging the reality gap by domain randomization. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1082\u20131090. (2018). https:\/\/doi.org\/10.1109\/cvprw.2018.00143","DOI":"10.1109\/cvprw.2018.00143"},{"key":"2899_CR39","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A., IEEE: you only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788. (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.91","DOI":"10.1109\/cvpr.2016.91"},{"issue":"4","key":"2899_CR40","doi-asserted-by":"publisher","first-page":"16","DOI":"10.3390\/agriculture12040485","volume":"12","author":"Y Gu","year":"2022","unstructured":"Gu, Y., Wang, S.C., Yan, Y., Tang, S.J., Zhao, S.D.: Identification and analysis of emergency behavior of cage-reared laying ducks based on YoloV5. Agric. Basel. 12(4), 16 (2022). https:\/\/doi.org\/10.3390\/agriculture12040485","journal-title":"Agric. Basel."},{"key":"2899_CR41","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.imavis.2019.04.007","volume":"87","author":"RC Chen","year":"2019","unstructured":"Chen, R.C.: Automatic license plate recognition via sliding-window darknet-YOLO deep learning. Image Vis. Comput. 87, 47\u201356 (2019). https:\/\/doi.org\/10.1016\/j.imavis.2019.04.007","journal-title":"Image Vis. Comput."},{"key":"2899_CR42","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.compag.2020.105742","volume":"178","author":"DH Wu","year":"2020","unstructured":"Wu, D.H., Lv, S.C., Jiang, M., Song, H.B.: Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments. Comput. Electron. Agric. 178, 12 (2020). https:\/\/doi.org\/10.1016\/j.compag.2020.105742","journal-title":"Comput. Electron. Agric."},{"key":"2899_CR43","doi-asserted-by":"publisher","first-page":"167448","DOI":"10.1109\/access.2020.3021660","volume":"8","author":"M Sharif","year":"2020","unstructured":"Sharif, M., Amin, J., Siddiqa, A., Khan, H.U., Malik, M.S.A., Anjum, M.A., Kadry, S.: Recognition of different types of leukocytes using YOLOv2 and optimized bag-of-features. IEEE Access. 8, 167448\u2013167459 (2020). https:\/\/doi.org\/10.1109\/access.2020.3021660","journal-title":"IEEE Access."},{"issue":"6","key":"2899_CR44","doi-asserted-by":"publisher","first-page":"460","DOI":"10.2316\/j.2020.206-0479","volume":"35","author":"P Liu","year":"2020","unstructured":"Liu, P., Song, C.L., Li, J.M., Yang, S.M., Chen, X.Y., Liu, C.F., Fu, Q.: Detection of transmission line against external force damage based on improved YOLOv3. Int. J. Robot. Autom. 35(6), 460\u2013468 (2020). https:\/\/doi.org\/10.2316\/j.2020.206-0479","journal-title":"Int. J. Robot. Autom."},{"key":"2899_CR45","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp. 764\u2013773. (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"2899_CR46","doi-asserted-by":"publisher","unstructured":"Sanghyun, W., Jongchan, P., Joon-Young, L., In So, K.: CBAM: convolutional block attention module. Computer vision\u2014ECCV 2018. In: 15th European Conference. Proceedings: Lecture Notes in Computer Science (LNCS 11211), pp. 3\u201319. (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2899_CR47","doi-asserted-by":"publisher","unstructured":"Zhang, Q.L., Yang, Y.B., IEEE: SA-NET: shuffle attention for deep convolutional neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2235\u20132239. (2021). https:\/\/doi.org\/10.1109\/icassp39728.2021.9414568","DOI":"10.1109\/icassp39728.2021.9414568"},{"key":"2899_CR48","doi-asserted-by":"publisher","unstructured":"Zhu, X.K., Lyu, S.C., Wang, X., Zhao, Q., Soc, I.C.: TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. In: 18th IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2778\u20132788. (2021). https:\/\/doi.org\/10.1109\/iccvw54120.2021.00312","DOI":"10.1109\/iccvw54120.2021.00312"},{"issue":"2","key":"2899_CR49","first-page":"251","volume":"51","author":"L Guo","year":"2022","unstructured":"Guo, L., Wang, Q., Xue, W., Guo, J.: A small object detection algorithm based on improved YOLOv5. J. Univ. Electron. Sci. Technol. China 51(2), 251\u2013258 (2022)","journal-title":"J. Univ. Electron. Sci. Technol. China"},{"key":"2899_CR50","unstructured":"Leng, Z., Tan, M., Liu, C., Cubuk, E.D., Shi, X., Cheng, S., Anguelov, D.: Polyloss: a polynomial expansion perspective of classification loss functions. arXiv preprint arXiv:2204.12511. (2022)"},{"key":"2899_CR51","doi-asserted-by":"publisher","unstructured":"Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1150\u20131157. (1999). https:\/\/doi.org\/10.1109\/iccv.1999.790410","DOI":"10.1109\/iccv.1999.790410"},{"issue":"1","key":"2899_CR52","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/jproc.2020.3004555","volume":"109","author":"FZ Zhuang","year":"2021","unstructured":"Zhuang, F.Z., Qi, Z.Y., Duan, K.Y., Xi, D.B., Zhu, Y.C., Zhu, H.S., Xiong, H., He, Q.: A comprehensive survey on transfer learning. Proc. IEEE 109(1), 43\u201376 (2021). https:\/\/doi.org\/10.1109\/jproc.2020.3004555","journal-title":"Proc. IEEE"},{"key":"2899_CR53","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Dollar, P., Girshick, R., He, K.M., Hariharan, B., Belongie, S., IEEE: Feature pyramid networks for object detection. In: 30th IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944. (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.106","DOI":"10.1109\/cvpr.2017.106"},{"issue":"1","key":"2899_CR54","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"PT De Boer","year":"2005","unstructured":"De Boer, P.T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross-entropy method. Ann. Oper. Res. 134(1), 19\u201367 (2005). https:\/\/doi.org\/10.1007\/s10479-005-5724-z","journal-title":"Ann. Oper. Res."},{"key":"2899_CR55","doi-asserted-by":"publisher","unstructured":"Wei, L., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Cheng-Yang, F., Berg, A.C.: SSD: single shot multibox detector. Computer vision\u2014ECCV 2016. In: 14th European Conference. Proceedings: LNCS 9905, pp. 21\u201337. (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2899_CR56","doi-asserted-by":"publisher","unstructured":"Hodan, T., Haluza, P., Obdrzalek, S., Matas, J., Lourakis, M., Zabulis, X., IEEE: T-LESS: an RGB-D dataset for 6D pose estimation of texture-less objects. In: 17th IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 880\u2013888. (2017). https:\/\/doi.org\/10.1109\/wacv.2017.103","DOI":"10.1109\/wacv.2017.103"},{"key":"2899_CR57","doi-asserted-by":"publisher","unstructured":"Hu, J., Shen, L., Sun, G., IEEE: Squeeze-and-excitation networks. In: 31st IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7132\u20137141. (2018). https:\/\/doi.org\/10.1109\/cvpr.2018.00745","DOI":"10.1109\/cvpr.2018.00745"},{"issue":"6","key":"2899_CR58","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/tpami.2016.2577031","volume":"39","author":"SQ Ren","year":"2017","unstructured":"Ren, S.Q., He, K.M., 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."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02899-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-02899-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02899-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,18]],"date-time":"2024-02-18T23:17:07Z","timestamp":1708298227000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-02899-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,7]]},"references-count":58,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["2899"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-02899-7","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,7]]},"assertion":[{"value":"6 May 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, and there is no professional or other personal interest of any nature or kind in any product, service and\/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled,\u201d Two-stage filtering method to improve the performance of object detection trained by synthetic dataset in heavily cluttered industry scenes.\u201d","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}