{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T06:18:43Z","timestamp":1769062723228,"version":"3.49.0"},"reference-count":39,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2023,3,1]]},"DOI":"10.1587\/transinf.2022edp7111","type":"journal-article","created":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T22:20:11Z","timestamp":1677622811000},"page":"401-409","source":"Crossref","is-referenced-by-count":11,"title":["DFAM-DETR: Deformable Feature Based Attention Mechanism DETR on Slender Object Detection"],"prefix":"10.1587","volume":"E106.D","author":[{"given":"Feng","family":"WEN","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Shenyang Ligong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mei","family":"WANG","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shenyang Ligong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojie","family":"HU","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shenyang Ligong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.770-778, 2016. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] L. Jiao, F. Zhang, F. Liu, S. Yang, L. Li, Z. Feng, and R. Qu, \u201cA survey of deep learning-based object detection,\u201d IEEE access, vol.7, pp.128837-128868, 2019. 10.1109\/access.2019.2939201","DOI":"10.1109\/ACCESS.2019.2939201"},{"key":"3","unstructured":"[3] Y. Zhao, Y. Rao, S. Dong, and J. Zhang, \u201cSurvey on deep learning object detection,\u201d Journal of Chinese imagegraphics, vol.25, no.4, p.26, 2020."},{"key":"4","unstructured":"[4] J. Dai, Y. Li, K. He, and J. Sun, \u201cR-fcn: Object detection via region-based fully convolutional networks,\u201d Advances in Neural Information Processing Systems, vol.29, 2016."},{"key":"5","unstructured":"[5] 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."},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] 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":"7","unstructured":"[7] J. Redmon and A. Farhadi, \u201cYolov3: An incremental improvement,\u201d arXiv preprint arXiv:1804.02767, 2018."},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] 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":"9","doi-asserted-by":"crossref","unstructured":"[9] 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":"10","unstructured":"[10] C.Y. Fu, W. Liu, A. Ranga, A. Tyagi, and A.C. Berg, \u201cDssd: Deconvolutional single shot detector,\u201d arXiv preprint arXiv:1701.06659, 2017."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] 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":"12","doi-asserted-by":"crossref","unstructured":"[12] M. Tan, R. Pang, and Q.V. Le, \u201cEfficientdet: Scalable and efficient object detection,\u201d Proc. IEEE\/CVF conference on computer vision and pattern recognition, pp.10781-10790, 2020. 10.1109\/cvpr42600.2020.01079","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] Z. Tian, C. Shen, H. Chen, and T. He, \u201cFcos: Fully convolutional one-stage object detection,\u201d Proc. IEEE\/CVF international conference on computer vision, pp.9627-9636, 2019. 10.1109\/iccv.2019.00972","DOI":"10.1109\/ICCV.2019.00972"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] H. Law and J. Deng, \u201cCornernet: Detecting objects as paired keypoints,\u201d Proc. European conference on computer vision (ECCV), pp.765-781, 2018. 10.1007\/978-3-030-01264-9_45","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] 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":"16","doi-asserted-by":"crossref","unstructured":"[16] Z. Cai and N. Vasconcelos, \u201cCascade r-cnn: Delving into high quality object detection,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.6154-6162, 2018. 10.1109\/cvpr.2018.00644","DOI":"10.1109\/CVPR.2018.00644"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] 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":"18","unstructured":"[18] 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":"19","doi-asserted-by":"crossref","unstructured":"[19] B. Zoph, E.D. Cubuk, G. Ghiasi, T.-Y. Lin, J. Shlens, and Q.V. Le, \u201cLearning data augmentation strategies for object detection,\u201d European conference on computer vision, pp.566-583, Springer, 2020. 10.1007\/978-3-030-58583-9_34","DOI":"10.1007\/978-3-030-58583-9_34"},{"key":"20","unstructured":"[20] L. Huang, Y. Yang, Y. Deng, and Y.D. Yu, \u201cUnifying landmark localization with end to end object detection,\u201d arXiv preprint arXiv:1509.04874, 2015."},{"key":"21","unstructured":"[21] P.R. Florence, L. Manuelli, and R. Tedrake, \u201cDense object nets: Learning dense visual object descriptors by and for robotic manipulation,\u201d arXiv preprint arXiv:1806.08756, 2018."},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] Z. Yang, S. Liu, H. Hu, L. Wang, and S. Lin, \u201cReppoints: Point set representation for object detection,\u201d Proc. IEEE\/CVF International Conference on Computer Vision, pp.9657-9666, 2019. 10.1109\/iccv.2019.00975","DOI":"10.1109\/ICCV.2019.00975"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] 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":"24","unstructured":"[24] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., \u201cAn image is worth 16x16 words: Transformers for image recognition at scale,\u201d arXiv preprint arXiv:2010.11929, 2020."},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] 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":"26","unstructured":"[26] X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, \u201cDeformable detr: Deformable transformers for end-to-end object detection,\u201d International Conference on Learning Representations, 2021."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] J. Dai, H. Qi, Y. Xiong, Y. Li, G. Zhang, H. Hu, and Y. Wei, \u201cDeformable convolutional networks,\u201d Proc. IEEE international conference on computer vision, pp.764-773, 2017. 10.1109\/iccv.2017.89","DOI":"10.1109\/ICCV.2017.89"},{"key":"28","unstructured":"[28] Z. Wan, Y. Chen, S. Deng, K. Chen, C. Yao, and J. Luo, \u201cSlender object detection: Diagnoses and improvements,\u201d arXiv preprint arXiv:2011.08529, 2020."},{"key":"29","unstructured":"[29] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, L. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d Advances in Neural Information Processing Systems, vol.30, 2017."},{"key":"30","unstructured":"[30] K. Han, Y. Wang, H. Chen, X. Chen, J. Guo, Z. Liu, Y. Tang, A. Xiao, C. Xu, Y. Xu, et al., \u201cA survey on visual transformer,\u201d arXiv e-prints, pp.arXiv-2012, 2020."},{"key":"31","doi-asserted-by":"publisher","unstructured":"[31] Y. Zhang, X. Shi, S. Mi, and X. Yang, \u201cImage captioning with transformer and knowledge graph,\u201d Pattern Recognition Letters, vol.143, pp.43-49, 2021. 10.1016\/j.patrec.2020.12.020","DOI":"10.1016\/j.patrec.2020.12.020"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] C. Yang, Q. Wang, J. Du, J. Zhang, C. Wu, and J. Wang, \u201cA transformer-based radical analysis network for chinese character recognition,\u201d 2020 25th International Conference on Pattern Recognition (ICPR), pp.3714-3719, IEEE, 2021. 10.1109\/icpr48806.2021.9412439","DOI":"10.1109\/ICPR48806.2021.9412439"},{"key":"33","doi-asserted-by":"publisher","unstructured":"[33] W. Liu, Y. Song, D. Chen, S. He, Y. Yu, T. Yan, G.P. Hancke, and R.W. Lau, \u201cDeformable object tracking with gated fusion,\u201d IEEE Trans. Image Process., vol.28, no.8, pp.3766-3777, 2019. 10.1109\/tip.2019.2902784","DOI":"10.1109\/TIP.2019.2902784"},{"key":"34","doi-asserted-by":"publisher","unstructured":"[34] Z. Liu, B. Yang, G. Duan, and J. Tan, \u201cVisual defect inspection of metal part surface via deformable convolution and concatenate feature pyramid neural networks,\u201d IEEE Trans. Instrum. Meas., vol.69, no.12, pp.9681-9694, 2020. 10.1109\/tim.2020.3001695","DOI":"10.1109\/TIM.2020.3001695"},{"key":"35","doi-asserted-by":"publisher","unstructured":"[35] J. Chen, Y. Chen, W. Li, G. Ning, M. Tong, and A. Hilton, \u201cChannel and spatial attention based deep object co-segmentation,\u201d Knowledge-Based Systems, vol.211, p.106550, 2021. 10.1016\/j.knosys.2020.106550","DOI":"10.1016\/j.knosys.2020.106550"},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] H.W. Kuhn, \u201cThe hungarian method for the assignment problem,\u201d Naval research logistics quarterly, vol.2, no.1-2, pp.83-97, 1955. 10.1002\/nav.3800020109","DOI":"10.1002\/nav.3800020109"},{"key":"37","unstructured":"[37] K. Da, \u201cA method for stochastic optimization,\u201d arXiv preprint arXiv:1412.6980, 2014."},{"key":"38","doi-asserted-by":"crossref","unstructured":"[38] J. Deng, \u201cA large-scale hierarchical image database,\u201d Proc. IEEE Computer Vision and Pattern Recognition, 2009.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"39","doi-asserted-by":"publisher","unstructured":"[39] A. Krizhevsky, I. Sutskever, and G.E. Hinton, \u201cImagenet classifica-tion with deep convolutional neural networks,\u201d Communications of the ACM, vol.60, no.6, pp.84-90, 2017. 10.1145\/3065386","DOI":"10.1145\/3065386"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/3\/E106.D_2022EDP7111\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,4]],"date-time":"2023-03-04T04:15:52Z","timestamp":1677903352000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/3\/E106.D_2022EDP7111\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,1]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2022edp7111","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,1]]},"article-number":"2022EDP7111"}}