{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:10:16Z","timestamp":1778613016390,"version":"3.51.4"},"reference-count":45,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1587\/transfun.2022eap1100","type":"journal-article","created":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T22:10:18Z","timestamp":1670883018000},"page":"924-931","source":"Crossref","is-referenced-by-count":2,"title":["Location First Non-Maximum Suppression for Uncovered Muck Truck Detection"],"prefix":"10.1587","volume":"E106.A","author":[{"given":"Yuxiang","family":"ZHANG","sequence":"first","affiliation":[{"name":"Civil Engineering School, Qingdao University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dehua","family":"LIU","sequence":"additional","affiliation":[{"name":"Qingdao Xizheng Technology Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanpeng","family":"SU","sequence":"additional","affiliation":[{"name":"Qingdao Xizheng Technology Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juncheng","family":"LIU","sequence":"additional","affiliation":[{"name":"Qingdao Xizheng Technology Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] Z.Q. Zhao, P. Zheng, S.t. Xu, and X. Wu, \u201cObject detection with deep learning: A review,\u201d IEEE Trans. Neural Netw. Learning Syst., vol.30, no.11, pp.3212-3232, 2019. 10.1109\/tnnls.2018.2876865","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"2","unstructured":"[2] Z. Zou, Z. Shi, Y. Guo, and J. Ye, \u201cObject detection in 20 years: A survey,\u201d arXiv preprint arXiv:1905.05055, 2019. 10.48550\/arXiv.1905.05055"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] Z. Cai, Z. Duan, and W. Li, \u201cExploiting multi-dimensional task diversity in distributed auctions for mobile crowdsensing,\u201d IEEE Trans. Mobile Comput., vol.20, no.8, pp.2576-2591, 2021. 10.1109\/tmc.2020.2987881","DOI":"10.1109\/TMC.2020.2987881"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] Z. Chen, \u201cThe application of artificial intelligence on the traceability and dispersion of air pollution,\u201d 2021 6th International Conference on Image, Vision and Computing (ICIVC), 2021. 10.1109\/icivc52351.2021.9526926","DOI":"10.1109\/ICIVC52351.2021.9526926"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] J. Gu, Z. Wang, J. Kuen, L. Ma, A. Shahroudy, B. Shuai, T. Liu, X. Wang, G. Wang, J. Cai, and T. Chen, \u201cRecent advances in convolutional neural networks,\u201d Pattern Recognition, vol.77, pp.354-377, 2018. 10.1016\/j.patcog.2017.10.013","DOI":"10.1016\/j.patcog.2017.10.013"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] Y. Liang, Z. Cai, J. Yu, Q. Han, and Y. Li, \u201cDeep learning based inference of private information using embedded sensors in smart devices,\u201d IEEE Netw., vol.32, no.4, pp.8-14, 2018. 10.1109\/mnet.2018.1700349","DOI":"10.1109\/MNET.2018.1700349"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] K.E. Van de Sande, J.R. Uijlings, T. Gevers, and A.W. Smeulders, \u201cSegmentation as selective search for object recognition,\u201d 2011 International Conference on Computer Vision, pp.1879-1886, IEEE, 2011. 10.1109\/iccv.2011.6126456","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] W.S. Noble, \u201cWhat is a support vector machine?,\u201d Nat. Biotechnol., vol.24, no.12, pp.1565-1567, 2006. 10.1038\/nbt1206-1565","DOI":"10.1038\/nbt1206-1565"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] R. Girshick, J. Donahue, T. Darrell, and J. Malik, \u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.580-587, 2014. 10.1109\/cvpr.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] R. Girshick, J. Donahue, T. Darrell, and J. Malik, \u201cRegion-based convolutional networks for accurate object detection and segmentation,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.38, no.1, pp.142-158, 2015. 10.1109\/tpami.2015.2437384","DOI":"10.1109\/TPAMI.2015.2437384"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] R. Girshick, \u201cFast R-CNN,\u201d Proc. IEEE International Conference on Computer Vision, pp.1440-1448, 2015. 10.1109\/iccv.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"12","unstructured":"[12] S. Ren, K. He, R. Girshick, and J. Sun, \u201cFaster R-CNN: Towards real-time object detection with region proposal networks,\u201d Advances in Neural Information Processing Systems, vol.28, 2015."},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, \u201cYou only look once: Unified, real-time object detection,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.779-788, 2016. 10.1109\/cvpr.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] J. Redmon and A. Farhadi, \u201cYOLO9000: Better, faster, stronger,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.7263-7271, 2017. 10.1109\/cvpr.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"15","unstructured":"[15] J. Redmon and A. Farhadi, \u201cYOLOv3: An incremental improvement,\u201d arXiv preprint arXiv:1804.02767, 2018. 10.48550\/arXiv.1804.02767"},{"key":"16","unstructured":"[16] A. Bochkovskiy, C.Y. Wang, and H.Y.M. Liao, \u201cYOLOv4: Optimal speed and accuracy of object detection,\u201d arXiv preprint arXiv:2004.10934, 2020. 10.48550\/arXiv.2004.10934"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, \u201cEnd-to-end object detection with transformers,\u201d European Conference on Computer Vision, pp.213-229, Springer, 2020. 10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"18","unstructured":"[18] X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, \u201cDeformable detr: Deformable transformers for end-to-end object detection,\u201d arXiv preprint arXiv:2010.04159, 2020. 10.48550\/arXiv.2010.04159"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, \u201cSwin transformer: Hierarchical vision transformer using shifted windows,\u201d Proc. IEEE\/CVF International Conference on Computer Vision, pp.10012-10022, 2021. 10.1109\/iccv48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] A. Neubeck and L. Van Gool, \u201cEfficient non-maximum suppression,\u201d 18th International Conference on Pattern Recognition, pp.850-855, 2006. 10.1109\/icpr.2006.479","DOI":"10.1109\/ICPR.2006.479"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] N. Bodla, B. Singh, R. Chellappa, and L.S. Davis, \u201cSoft-NMS \u2014 Improving object detection with one line of code,\u201d Proc. IEEE International Conference on Computer Vision, pp.5561-5569, 2017. 10.1109\/iccv.2017.593","DOI":"10.1109\/ICCV.2017.593"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] B. Jiang, R. Luo, J. Mao, T. Xiao, and Y. Jiang, \u201cAcquisition of localization confidence for accurate object detection,\u201d Proc. European Conference on Computer Vision (ECCV), pp.784-799, 2018. 10.1007\/978-3-030-01264-9_48","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"23","unstructured":"[23] C. Ning, H. Zhou, Y. Song, and J. Tang, \u201cInception single shot MultiBox detector for object detection,\u201d 2017 IEEE International Conference on Multimedia Expo Workshops (ICMEW), pp.549-554, 2017. 10.1109\/icmew.2017.8026312"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] Y. He, C. Zhu, J. Wang, M. Savvides, and X. Zhang, \u201cBounding box regression with uncertainty for accurate object detection,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.2888-2897, 2019. 10.1109\/cvpr.2019.00300","DOI":"10.1109\/CVPR.2019.00300"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] S. Liu, D. Huang, and Y. Wang, \u201cAdaptive NMS: Refining pedestrian detection in a crowd,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.6459-6468, 2019. 10.1109\/cvpr.2019.00662","DOI":"10.1109\/CVPR.2019.00662"},{"key":"26","doi-asserted-by":"publisher","unstructured":"[26] Z. Zheng, P. Wang, W. Liu, J. Li, R. Ye, and D. Ren, \u201cDistance-iou loss: Faster and better learning for bounding box regression,\u201d Proc. AAAI Conference on Artificial Intelligence, pp.12993-13000, 2020. 10.1609\/aaai.v34i07.6999","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"27","doi-asserted-by":"publisher","unstructured":"[27] K. He, X. Zhang, S. Ren, and J. Sun, \u201cSpatial pyramid pooling in deep convolutional networks for visual recognition,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.37, no.9, pp.1904-1916, 2015. 10.1109\/tpami.2015.2389824","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] T.Y. Lin, P. Doll\u00e1r, R. Girshick, K. He, B. Hariharan, and S. Belongie, \u201cFeature pyramid networks for object detection,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.2117-2125, 2017. 10.1109\/cvpr.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] X. Wang, A. Shrivastava, and A. Gupta, \u201cA-fast-RCNN: Hard positive generation via adversary for object detection,\u201d 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.3039-3048, 2017. 10.1109\/cvpr.2017.324","DOI":"10.1109\/CVPR.2017.324"},{"key":"30","doi-asserted-by":"publisher","unstructured":"[30] Z. Cai, Z. Xiong, H. Xu, P. Wang, W. Li, and Y. Pan, \u201cGenerative adversarial networks: A survey toward private and secure applications,\u201d ACM Comput. Surv., vol.54, no.6, pp.1-38, 2021. 10.1145\/3459992","DOI":"10.1145\/3459992"},{"key":"31","unstructured":"[31] J. Glenn, \u201cYOLOv5 in pytorch,\u201d accessed Feb 10, 2022."},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.Y. Fu, and A.C. Berg, \u201cSSD: Single shot MultiBox detector,\u201d European Conference on Computer Vision, pp.21-37, Springer, 2016. 10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"33","unstructured":"[33] Z. Li and F. Zhou, \u201cFSSD: Feature fusion single shot multibox detector,\u201d arXiv preprint arXiv:1712.00960, 2017. 10.48550\/arXiv.1712.00960"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] T.Y. Lin, P. Goyal, R. Girshick, K. He, and P. Doll\u00e1r, \u201cFocal loss for dense object detection,\u201d Proc. IEEE International Conference on Computer Vision, pp.2980-2988, 2017. 10.1109\/iccv.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"35","unstructured":"[35] X. Li, W. Wang, L. Wu, S. Chen, X. Hu, J. Li, J. Tang, and J. Yang, \u201cGeneralized focal loss: Learning qualified and distributed bounding boxes for dense object detection,\u201d Advances in Neural Information Processing Systems, vol.33, pp.21002-21012, 2020."},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] X. Li, W. Wang, X. Hu, J. Li, J. Tang, and J. Yang, \u201cGeneralized focal loss V2: Learning reliable localization quality estimation for dense object detection,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.11632-11641, 2021. 10.1109\/cvpr46437.2021.01146","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"37","doi-asserted-by":"publisher","unstructured":"[37] Z. Wang, X. Xie, J. Yang, and G. Shi, \u201cSoft focal loss: Evaluating sample quality for dense object detection,\u201d Neurocomputing, vol.480, pp.271-280, 2022. 10.1016\/j.neucom.2021.12.102","DOI":"10.1016\/j.neucom.2021.12.102"},{"key":"38","unstructured":"[38] D. Bahdanau, K. Cho, and Y. Bengio, \u201cNeural machine translation by jointly learning to align and translate,\u201d arXiv preprint arXiv:1409.0473, 2014. 10.48550\/arXiv.1409.0473"},{"key":"39","unstructured":"[39] W. Zaremba, I. Sutskever, and O. Vinyals, \u201cRecurrent neural network regularization,\u201d arXiv preprint arXiv:1409.2329, 2014. 10.48550\/arXiv.1409.2329"},{"key":"40","unstructured":"[40] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, \u0141. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d Advances in Neural Information Processing Systems, vol.30, 2017."},{"key":"41","unstructured":"[41] P. Ramachandran, N. Parmar, A. Vaswani, I. Bello, A. Levskaya, and J. Shlens, \u201cStand-alone self-attention in vision models,\u201d Advances in Neural Information Processing Systems, vol.32, 2019."},{"key":"42","doi-asserted-by":"crossref","unstructured":"[42] J. Deng, W. Dong, R. Socher, L.J. Li, K. Li, and L. Fei-Fei, \u201cImageNet: A large-scale hierarchical image database,\u201d 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp.248-255, IEEE, 2009. 10.1109\/cvpr.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"43","doi-asserted-by":"crossref","unstructured":"[43] T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, and C.L. Zitnick, \u201cMicrosoft COCO: Common objects in context,\u201d European Conference on Computer Vision, pp.740-755, Springer, 2014. 10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"44","unstructured":"[44] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby, \u201cAn image is worth 16x16 words: Transformers for image recognition at scale,\u201d arXiv preprint arXiv:2010.11929, 2020. 10.48550\/arXiv.2010.11929"},{"key":"45","doi-asserted-by":"crossref","unstructured":"[45] S. Xie, R. Girshick, P. Doll\u00e1r, Z. Tu, and K. He, \u201cAggregated residual transformations for deep neural networks,\u201d 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.5987-5995, 2017. 10.1109\/cvpr.2017.634","DOI":"10.1109\/CVPR.2017.634"}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E106.A\/6\/E106.A_2022EAP1100\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,3]],"date-time":"2023-06-03T04:04:44Z","timestamp":1685765084000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E106.A\/6\/E106.A_2022EAP1100\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":45,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2022eap1100","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"value":"0916-8508","type":"print"},{"value":"1745-1337","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]},"article-number":"2022EAP1100"}}