{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T11:41:52Z","timestamp":1780659712801,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":144,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T00:00:00Z","timestamp":1684454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,5,19]]},"DOI":"10.1145\/3604078.3604126","type":"proceedings-article","created":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T16:46:07Z","timestamp":1698338767000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Deep Learning object detection models: evolution and evaluation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5523-040X","authenticated-orcid":false,"given":"Sara","family":"Bouraya","sequence":"first","affiliation":[{"name":"Mathematics and Computer Science Department, Laboratory of Information Technology and Modeling, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9580-8760","authenticated-orcid":false,"given":"Abdessamad","family":"Belangour","sequence":"additional","affiliation":[{"name":"Mathematics and Computer Science Department, Laboratory of Information Technology and Modeling, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A Survey on Moving Object Detection and Tracking Methods","author":"Pathan I.","unstructured":"I. Pathan and C. Chauhan , \u201c A Survey on Moving Object Detection and Tracking Methods ,\u201d vol. 6, no. 6, pp. 5212\u20135215, 2015. I. Pathan and C. Chauhan, \u201cA Survey on Moving Object Detection and Tracking Methods,\u201d vol. 6, no. 6, pp. 5212\u20135215, 2015."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00434-w"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISA.2015.7388021"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14419\/ijet.v7i2.16.11665"},{"key":"e_1_3_2_1_5_1","first-page":"586","article-title":"Comparative Study of Object Detection Algorithms","author":"Yadav N.","year":"2017","unstructured":"N. Yadav and U. Binay , \u201c Comparative Study of Object Detection Algorithms ,\u201d Int. Res. J. Eng. Technol. , pp. 586 \u2013 591 , 2017 , [Online]. Available: www.irjet.net. N. Yadav and U. Binay, \u201cComparative Study of Object Detection Algorithms,\u201d Int. Res. J. Eng. Technol., pp. 586\u2013591, 2017, [Online]. Available: www.irjet.net.","journal-title":"Int. Res. J. Eng. Technol."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00434-w"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596"},{"issue":"6","key":"e_1_3_2_1_8_1","first-page":"398","article-title":"VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION Karen","volume":"75","author":"Simonyan\u2217 Karen","year":"2018","unstructured":"Karen Simonyan\u2217 & Andrew Zisserman+ , \u201c VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION Karen ,\u201d Am. J. Heal. Pharm. , vol. 75 , no. 6 , pp. 398 \u2013 406 , 2018 . Karen Simonyan\u2217 & Andrew Zisserman+, \u201cVERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION Karen,\u201d Am. J. Heal. Pharm., vol. 75, no. 6, pp. 398\u2013406, 2018.","journal-title":"Am. J. Heal. Pharm."},{"key":"e_1_3_2_1_9_1","volume-title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","author":"Howard A. G.","year":"2012","unstructured":"A. G. Howard and W. Wang , \u201c MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications ,\u201d 2012 . A. G. Howard and W. Wang, \u201cMobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,\u201d 2012."},{"key":"e_1_3_2_1_10_1","first-page":"10790","volume-title":"EfficientDet: Scalable and Efficient Object Detection","author":"Tan M.","unstructured":"M. Tan , R. Pang , and Q. V Le , \u201c EfficientDet: Scalable and Efficient Object Detection ,\u201d pp. 10781\u2013 10790 . M. Tan, R. Pang, and Q. V Le, \u201cEfficientDet: Scalable and Efficient Object Detection,\u201d pp. 10781\u201310790."},{"key":"e_1_3_2_1_11_1","volume-title":"2nd Int. Conf. Learn. Represent. ICLR 2014 - Conf. Track Proc.","author":"Sermanet P.","year":"2014","unstructured":"P. Sermanet , D. Eigen , X. Zhang , M. Mathieu , R. Fergus , and Y. LeCun , \u201c Overfeat: Integrated recognition, localization and detection using convolutional networks ,\u201d 2nd Int. Conf. Learn. Represent. ICLR 2014 - Conf. Track Proc. , 2014 . P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun, \u201cOverfeat: Integrated recognition, localization and detection using convolutional networks,\u201d 2nd Int. Conf. Learn. Represent. ICLR 2014 - Conf. Track Proc., 2014."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_13_1","unstructured":"D. Erhan C. Szegedy A. Toshev and D. Anguelov \u201cScalable Object Detection using Deep Neural Networks.\u201d  D. Erhan C. Szegedy A. Toshev and D. Anguelov \u201cScalable Object Detection using Deep Neural Networks.\u201d"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.135"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.285"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.305"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1006-x"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298854"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_25_1","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"Dai J.","year":"2016","unstructured":"J. Dai , Y. Li , K. He , and J. Sun , \u201c R-FCN: Object detection via region-based fully convolutional networks ,\u201d Adv. Neural Inf. Process. Syst. , pp. 379 \u2013 387 , 2016 . J. Dai, Y. Li, K. He, and J. Sun, \u201cR-FCN: Object detection via region-based fully convolutional networks,\u201d Adv. Neural Inf. Process. Syst., pp. 379\u2013387, 2016.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.98"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.258"},{"key":"e_1_3_2_1_28_1","unstructured":"A. Shrivastava \u201cTraining Region-based Object Detectors with Online Hard Example Mining.\u201d  A. Shrivastava \u201cTraining Region-based Object Detectors with Online Hard Example Mining.\u201d"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.650"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.260"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2601099"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2745563"},{"key":"e_1_3_2_1_34_1","volume-title":"DSSD: Deconvolutional Single Shot Detector","author":"Fu C.-Y.","year":"2017","unstructured":"C.-Y. Fu , W. Liu , A. Ranga , A. Tyagi , and A. C. Berg , \u201c DSSD: Deconvolutional Single Shot Detector ,\u201d 2017 , [Online]. Available: http:\/\/arxiv.org\/abs\/1701.06659. C.-Y. Fu, W. Liu, A. Ranga, A. Tyagi, and A. C. Berg, \u201cDSSD: Deconvolutional Single Shot Detector,\u201d 2017, [Online]. Available: http:\/\/arxiv.org\/abs\/1701.06659."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.557"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.54"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.444"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.69"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.212"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"e_1_3_2_1_44_1","unstructured":"A. Shrivastava \u201cBeyond Skip Connections: Top-Down Modulation for Object Detection.\u201d  A. Shrivastava \u201cBeyond Skip Connections: Top-Down Modulation for Object Detection.\u201d"},{"key":"e_1_3_2_1_45_1","first-page":"9","volume-title":"Light-Head R-CNN: In Defense of Two-Stage Object Detector","author":"Li Z.","year":"2017","unstructured":"Z. Li , C. Peng , G. Yu , X. Zhang , Y. Deng , and J. Sun , \u201c Light-Head R-CNN: In Defense of Two-Stage Object Detector ,\u201d pp. 1\u2013 9 , 2017 , [Online]. Available: http:\/\/arxiv.org\/abs\/1711.07264. Z. Li, C. Peng, G. Yu, X. Zhang, Y. Deng, and J. Sun, \u201cLight-Head R-CNN: In Defense of Two-Stage Object Detector,\u201d pp. 1\u20139, 2017, [Online]. Available: http:\/\/arxiv.org\/abs\/1711.07264."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"X. Chen \u201cSpatial memory for context reasoning in object detection - 2017 - Chen preprint arXiv1704.04224 Gupta\u223c- A - {arXiv} pre.pdf.\u201d  X. Chen \u201cSpatial memory for context reasoning in object detection - 2017 - Chen preprint arXiv1704.04224 Gupta\u223c- A - {arXiv} pre.pdf.\u201d","DOI":"10.1109\/ICCV.2017.440"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00719"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00136"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"e_1_3_2_1_53_1","volume-title":"Zoom Out-and-In Network with Recursive Training for Object Proposal","author":"Li H.","year":"2017","unstructured":"H. Li , Y. Liu , W. Ouyang , and X. Wang , \u201c Zoom Out-and-In Network with Recursive Training for Object Proposal ,\u201d 2017 , [Online]. Available: http:\/\/arxiv.org\/abs\/1702.05711. H. Li, Y. Liu, W. Ouyang, and X. Wang, \u201cZoom Out-and-In Network with Recursive Training for Object Proposal,\u201d 2017, [Online]. Available: http:\/\/arxiv.org\/abs\/1702.05711."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00730"},{"key":"e_1_3_2_1_56_1","first-page":"537","volume-title":"Scale-Transferrable Object Detection","author":"Zhou P.","unstructured":"P. Zhou , B. Ni , C. Geng , J. Hu , and Y. Xu , \u201c Scale-Transferrable Object Detection ,\u201d vol. 1, pp. 528\u2013 537 . P. Zhou, B. Ni, C. Geng, J. Hu, and Y. Xu, \u201cScale-Transferrable Object Detection,\u201d vol. 1, pp. 528\u2013537."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00647"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00352"},{"key":"e_1_3_2_1_59_1","first-page":"12","volume-title":"Br. Mach. Vis. Conf. 2018, BMVC 2018","author":"Bosquet B.","year":"2019","unstructured":"B. Bosquet , M. Mucientes , and V. M. Brea , \u201c StDNet: A convnet for small target detection ,\u201d Br. Mach. Vis. Conf. 2018, BMVC 2018 , pp. 1\u2013 12 , 2019 . B. Bosquet, M. Mucientes, and V. M. Brea, \u201cStDNet: A convnet for small target detection,\u201d Br. Mach. Vis. Conf. 2018, BMVC 2018, pp. 1\u201312, 2019."},{"key":"e_1_3_2_1_60_1","first-page":"10","volume-title":"6th Int. Conf. Learn. Represent. ICLR 2018 - Work. Track Proc., no. NeurIPS","author":"Wang R. J.","year":"2018","unstructured":"R. J. Wang , X. Li , S. Ao , and C. X. Ling , \u201c Pelee: A real-time object detection system on mobile devices ,\u201d 6th Int. Conf. Learn. Represent. ICLR 2018 - Work. Track Proc., no. NeurIPS , pp. 1\u2013 10 , 2018 . R. J. Wang, X. Li, S. Ao, and C. X. Ling, \u201cPelee: A real-time object detection system on mobile devices,\u201d 6th Int. Conf. Learn. Represent. ICLR 2018 - Work. Track Proc., no. NeurIPS, pp. 1\u201310, 2018."},{"key":"e_1_3_2_1_61_1","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"1563","author":"Jiang C.","year":"2018","unstructured":"C. Jiang , X. Liang , H. Xu , and L. Lin , \u201c Hybrid Knowledge Routed Modules for Large-scale Object Detection ,\u201d Adv. Neural Inf. Process. Syst. , vol. 2018-Decem, no. NeurIPS, pp. 1552\u2013 1563 , 2018 . C. Jiang, X. Liang, H. Xu, and L. Lin, \u201cHybrid Knowledge Routed Modules for Large-scale Object Detection,\u201d Adv. Neural Inf. Process. Syst., vol. 2018-Decem, no. NeurIPS, pp. 1552\u20131563, 2018."},{"key":"e_1_3_2_1_62_1","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"330","author":"Yang T.","year":"2018","unstructured":"T. Yang , X. Zhang , Z. Li , W. Zhang , and J. Sun , \u201c Metaanchor: Learning to detect objects with customized anchors ,\u201d Adv. Neural Inf. Process. Syst. , vol. 2018-Decem, no. NeurIPS, pp. 320\u2013 330 , 2018 . T. Yang, X. Zhang, Z. Li, W. Zhang, and J. Sun, \u201cMetaanchor: Learning to detect objects with customized anchors,\u201d Adv. Neural Inf. Process. Syst., vol. 2018-Decem, no. NeurIPS, pp. 320\u2013330, 2018."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"e_1_3_2_1_65_1","volume-title":"SNIPER: Efficient Multi-Scale Training","author":"Singh B.","year":"2018","unstructured":"B. Singh and L. S. Davis , \u201c SNIPER: Efficient Multi-Scale Training ,\u201d no. NeurIPS , 2018 . B. Singh and L. S. Davis, \u201cSNIPER: Efficient Multi-Scale Training,\u201d no. NeurIPS, 2018."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00754"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00960"},{"key":"e_1_3_2_1_68_1","unstructured":"C. F. Mykhailo and S. Alexander \u201cRetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free.\u201d  C. F. Mykhailo and S. Alexander \u201cRetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free.\u201d"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018094"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00093"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00662"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00230"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00720"},{"key":"e_1_3_2_1_76_1","unstructured":"U. T. Austin U. T. Austin and U. T. Austin \u201cBottom-up Object Detection by Grouping Extreme and Center Points.\u201d  U. T. Austin U. T. Austin and U. T. Austin \u201cBottom-up Object Detection by Grouping Extreme and Center Points.\u201d"},{"key":"e_1_3_2_1_77_1","unstructured":"Y. Cao J. Xu S. Lin F. Wei and H. Hu \u201cGCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond.\u201d  Y. Cao J. Xu S. Lin F. Wei and H. Hu \u201cGCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond.\u201d"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00237"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"e_1_3_2_1_80_1","first-page":"12","volume-title":"30th Br. Mach. Vis. Conf. 2019, BMVC 2019","author":"Zhang H.","year":"2020","unstructured":"H. Zhang , H. Chang , B. Ma , S. Shan , and X. Chen , \u201c Cascade retinanet: Maintaining consistency for single-stage object detection ,\u201d 30th Br. Mach. Vis. Conf. 2019, BMVC 2019 , pp. 1\u2013 12 , 2020 . H. Zhang, H. Chang, B. Ma, S. Shan, and X. Chen, \u201cCascade retinanet: Maintaining consistency for single-stage object detection,\u201d 30th Br. Mach. Vis. Conf. 2019, BMVC 2019, pp. 1\u201312, 2020."},{"key":"e_1_3_2_1_81_1","volume-title":"30th Br. Mach. Vis. Conf. 2019, BMVC 2019, no. i","author":"Shen Z.","year":"2020","unstructured":"Z. Shen , \u201c Improving object detection from scratch via gated feature reuse ,\u201d 30th Br. Mach. Vis. Conf. 2019, BMVC 2019, no. i , 2020 . Z. Shen , \u201cImproving object detection from scratch via gated feature reuse,\u201d 30th Br. Mach. Vis. Conf. 2019, BMVC 2019, no. i, 2020."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00978"},{"key":"e_1_3_2_1_83_1","unstructured":"Z. Qin \u201cThunderNet: Towards Real-time Generic Object Detection.\u201d  Z. Qin \u201cThunderNet: Towards Real-time Generic Object Detection.\u201d"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00059"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00252"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00720"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"e_1_3_2_1_88_1","unstructured":"Y. Li Y. Chen N. Wang and Z. Zhang \u201cScale-Aware Trident Networks for Object Detection.\u201d  Y. Li Y. Chen N. Wang and Z. Zhang \u201cScale-Aware Trident Networks for Object Detection.\u201d"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00887"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00712"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00840"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050494"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00970"},{"key":"e_1_3_2_1_94_1","first-page":"1","article-title":"Efficient neural architecture transformation search in channel-level for object detection","volume":"32","author":"Peng J.","year":"2019","unstructured":"J. Peng , M. Sun , Z. Zhang , T. Tan , and J. Yan , \u201c Efficient neural architecture transformation search in channel-level for object detection ,\u201d Adv. Neural Inf. Process. Syst. , vol. 32 , no. NeurIPS, pp. 1 \u2013 11 , 2019 . J. Peng, M. Sun, Z. Zhang, T. Tan, and J. Yan, \u201cEfficient neural architecture transformation search in channel-level for object detection,\u201d Adv. Neural Inf. Process. Syst., vol. 32, no. NeurIPS, pp. 1\u201311, 2019.","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00838"},{"key":"e_1_3_2_1_96_1","unstructured":"L. Deng M. Yang T. Li Y. He and C. Wang \u201cRFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation.\u201d  L. Deng M. Yang T. Li Y. He and C. Wang \u201cRFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation.\u201d"},{"key":"e_1_3_2_1_97_1","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"32","author":"Chen Y.","year":"2019","unstructured":"Y. Chen , T. Yang , X. Zhang , G. Meng , X. Xiao , and J. Sun , \u201c DetNAS: Backbone search for object detection ,\u201d Adv. Neural Inf. Process. Syst. , vol. 32 , no. NeurIPS , 2019 . Y. Chen, T. Yang, X. Zhang, G. Meng, X. Xiao, and J. Sun, \u201cDetNAS: Backbone search for object detection,\u201d Adv. Neural Inf. Process. Syst., vol. 32, no. NeurIPS, 2019."},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00675"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00975"},{"key":"e_1_3_2_1_101_1","first-page":"1","article-title":"Stand-Alone Self-Attention in Vision Models","author":"Ramachandran P.","year":"2019","unstructured":"P. Ramachandran , N. Parmar , A. Levskaya , and J. Shlens , \u201c Stand-Alone Self-Attention in Vision Models ,\u201d no. NeurIPS , pp. 1 \u2013 13 , 2019 . P. Ramachandran, N. Parmar, A. Levskaya, and J. Shlens, \u201cStand-Alone Self-Attention in Vision Models,\u201d no. NeurIPS, pp. 1\u201313, 2019.","journal-title":"no. NeurIPS"},{"key":"e_1_3_2_1_102_1","first-page":"2019","article-title":"CAMOU: Learning physical vehicle camouflages to adversarially attack detectors in the wild","author":"Zhang Y.","year":"2018","unstructured":"Y. Zhang , H. Foroosh , P. David , and B. Gong , \u201c CAMOU: Learning physical vehicle camouflages to adversarially attack detectors in the wild ,\u201d Iclr 2019 , 2018 . Y. Zhang, H. Foroosh, P. David, and B. Gong, \u201cCAMOU: Learning physical vehicle camouflages to adversarially attack detectors in the wild,\u201d Iclr 2019, 2018.","journal-title":"Iclr"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00958"},{"key":"e_1_3_2_1_104_1","unstructured":"J. Wang \u201cSide-Aware Boundary Localization for More Precise Object Detection.\u201d  J. Wang \u201cSide-Aware Boundary Localization for More Precise Object Detection.\u201d"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00658"},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6834"},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6787"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01336"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01196"},{"key":"e_1_3_2_1_110_1","unstructured":"C. Chen Z. Zheng X. Ding Y. Huang and Q. Dou \u201cHarmonizing Transferability and Discriminability for Adapting Object Detectors.\u201d  C. Chen Z. Zheng X. Ding Y. Huang and Q. Dou \u201cHarmonizing Transferability and Discriminability for Adapting Object Detectors.\u201d"},{"key":"e_1_3_2_1_111_1","volume-title":"ScanSSD: Scanning Single Shot Detector for Mathematical Formulas in PDF Document Images","author":"Kukkadapu P.","year":"2019","unstructured":"P. Kukkadapu , M. Mahdavi , and R. Zanibbi , \u201c ScanSSD: Scanning Single Shot Detector for Mathematical Formulas in PDF Document Images ,\u201d 2019 . P. Kukkadapu, M. Mahdavi, and R. Zanibbi, \u201cScanSSD: Scanning Single Shot Detector for Mathematical Formulas in PDF Document Images,\u201d 2019."},{"key":"e_1_3_2_1_112_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01053"},{"key":"e_1_3_2_1_113_1","volume-title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","author":"Bochkovskiy A.","year":"2020","unstructured":"A. Bochkovskiy , C. Y. Wang , and H. Y. M. Liao , \u201c YOLOv4: Optimal Speed and Accuracy of Object Detection ,\u201d arXiv, 2020 . A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, \u201cYOLOv4: Optimal Speed and Accuracy of Object Detection,\u201d arXiv, 2020."},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_115_1","unstructured":"S. Z. Li S. Zhang C. Chi Y. Yao and Z. Lei \u201cBridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection \u201d no. 2.  S. Z. Li S. Zhang C. Chi Y. Yao and Z. Lei \u201cBridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection \u201d no. 2."},{"key":"e_1_3_2_1_116_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_12"},{"key":"e_1_3_2_1_117_1","first-page":"19","volume-title":"Dynamic R-CNN: Towards High Quality Object","author":"Zhang H.","unstructured":"H. Zhang , H. Chang , and B. Ma , \u201c Dynamic R-CNN: Towards High Quality Object ,\u201d pp. 1\u2013 19 . H. Zhang, H. Chang, and B. Ma, \u201cDynamic R-CNN: Towards High Quality Object,\u201d pp. 1\u201319."},{"key":"e_1_3_2_1_118_1","unstructured":"J. Guo \u201cHit-Detector: Hierarchical Trinity Architecture Search for Object Detection \u201d no. c.  J. Guo \u201cHit-Detector: Hierarchical Trinity Architecture Search for Object Detection \u201d no. c."},{"key":"e_1_3_2_1_119_1","volume-title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","author":"Qiao S.","year":"2020","unstructured":"S. Qiao , L.-C. Chen , and A. Yuille , \u201c DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution ,\u201d 2020 , [Online]. Available: http:\/\/arxiv.org\/abs\/2006.02334. S. Qiao, L.-C. Chen, and A. Yuille, \u201cDetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution,\u201d 2020, [Online]. Available: http:\/\/arxiv.org\/abs\/2006.02334."},{"key":"e_1_3_2_1_120_1","volume-title":"PP-YOLO: An effective and efficient implementation of object detector","author":"Long X.","year":"2020","unstructured":"X. Long , \u201c PP-YOLO: An effective and efficient implementation of object detector ,\u201d arXiv, 2020 . X. Long , \u201cPP-YOLO: An effective and efficient implementation of object detector,\u201d arXiv, 2020."},{"key":"e_1_3_2_1_121_1","unstructured":"X. Qin Z. Zhang C. Huang M. Dehghan O. R. Zaiane and M. Jagersand \u201cU 2 -Net: Going Deeper with Nested U-Structure for Salient Object Detection.\u201d  X. Qin Z. Zhang C. Huang M. Dehghan O. R. Zaiane and M. Jagersand \u201cU 2 -Net: Going Deeper with Nested U-Structure for Salient Object Detection.\u201d"},{"key":"e_1_3_2_1_122_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01204-1"},{"key":"e_1_3_2_1_123_1","unstructured":"H. Zhang E. Fromont S. Lefevre and B. Avignon \u201cLocalize to Classify and Classify to Localize:\u201d  H. Zhang E. Fromont S. Lefevre and B. Avignon \u201cLocalize to Classify and Classify to Localize:\u201d"},{"key":"e_1_3_2_1_124_1","first-page":"7398","volume-title":"FoveaBox: Beyound Anchor-Based Object Detection","author":"Kong T.","year":"2020","unstructured":"T. Kong , F. Sun , H. Liu , Y. Jiang , L. Li , and J. Shi , \u201c FoveaBox: Beyound Anchor-Based Object Detection ,\u201d vol. 29, pp. 7389\u2013 7398 , 2020 . T. Kong, F. Sun, H. Liu, Y. Jiang, L. Li, and J. Shi, \u201cFoveaBox: Beyound Anchor-Based Object Detection,\u201d vol. 29, pp. 7389\u20137398, 2020."},{"key":"e_1_3_2_1_125_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01161"},{"key":"e_1_3_2_1_126_1","first-page":"14463","volume-title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","author":"Sun P.","unstructured":"P. Sun , R. Zhang , Y. Jiang , T. Kong , C. Xu , and W. Zhan , \u201c Sparse R-CNN: End-to-End Object Detection with Learnable Proposals ,\u201d pp. 14454\u2013 14463 . P. Sun, R. Zhang, Y. Jiang, T. Kong, C. Xu, and W. Zhan, \u201cSparse R-CNN: End-to-End Object Detection with Learnable Proposals,\u201d pp. 14454\u201314463."},{"key":"e_1_3_2_1_127_1","first-page":"8523","volume-title":"VarifocalNet: An IoU-aware Dense Object Detector","author":"Zhang H.","unstructured":"H. Zhang , Y. Wang , F. Dayoub , and S. Niko , \u201c VarifocalNet: An IoU-aware Dense Object Detector ,\u201d pp. 8514\u2013 8523 . H. Zhang, Y. Wang, F. Dayoub, and S. Niko, \u201cVarifocalNet: An IoU-aware Dense Object Detector,\u201d pp. 8514\u20138523."},{"key":"e_1_3_2_1_128_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01150"},{"key":"e_1_3_2_1_129_1","first-page":"3834","volume-title":"MobileDets: Searching for Object Detection Architectures for Mobile Accelerators","author":"Xiong Y.","unstructured":"Y. Xiong , \u201c MobileDets: Searching for Object Detection Architectures for Mobile Accelerators ,\u201d pp. 3825\u2013 3834 . Y. Xiong , \u201cMobileDets: Searching for Object Detection Architectures for Mobile Accelerators,\u201d pp. 3825\u20133834."},{"key":"e_1_3_2_1_130_1","volume-title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","author":"Liu Z.","year":"2021","unstructured":"Z. Liu , \u201c Swin Transformer: Hierarchical Vision Transformer using Shifted Windows ,\u201d 2021 , [Online]. Available: http:\/\/arxiv.org\/abs\/2103.14030. Z. Liu , \u201cSwin Transformer: Hierarchical Vision Transformer using Shifted Windows,\u201d 2021, [Online]. Available: http:\/\/arxiv.org\/abs\/2103.14030."},{"key":"e_1_3_2_1_131_1","first-page":"11","volume-title":"You Only Learn One Representation: Unified Network for Multiple Tasks","author":"Wang C.","unstructured":"C. Wang , I. Yeh , and H. M. Liao , \u201c You Only Learn One Representation: Unified Network for Multiple Tasks ,\u201d pp. 1\u2013 11 . C. Wang, I. Yeh, and H. M. Liao, \u201cYou Only Learn One Representation: Unified Network for Multiple Tasks,\u201d pp. 1\u201311."},{"key":"e_1_3_2_1_132_1","first-page":"7","volume-title":"PP-YOLOv2: A Practical Object Detector","author":"Huang X.","year":"2021","unstructured":"X. Huang , \u201c PP-YOLOv2: A Practical Object Detector ,\u201d pp. 1\u2013 7 , 2021 , [Online]. Available: http:\/\/arxiv.org\/abs\/2104.10419. X. Huang , \u201cPP-YOLOv2: A Practical Object Detector,\u201d pp. 1\u20137, 2021, [Online]. Available: http:\/\/arxiv.org\/abs\/2104.10419."},{"key":"e_1_3_2_1_133_1","unstructured":"N. Carion and G. Synnaeve \u201cMDETR - Modulated Detection for End-to-End Multi-Modal Understanding.\u201d  N. Carion and G. Synnaeve \u201cMDETR - Modulated Detection for End-to-End Multi-Modal Understanding.\u201d"},{"key":"e_1_3_2_1_134_1","unstructured":"Y. Xin \u201cPAFNet: An Efficient Anchor-Free Object Detector Guidance.\u201d  Y. Xin \u201cPAFNet: An Efficient Anchor-Free Object Detector Guidance.\u201d"},{"key":"e_1_3_2_1_135_1","first-page":"7","volume-title":"YOLOX: Exceeding YOLO Series in 2021","author":"Ge Z.","year":"2021","unstructured":"Z. Ge , S. Liu , F. Wang , Z. Li , and J. Sun , \u201c YOLOX: Exceeding YOLO Series in 2021 ,\u201d pp. 1\u2013 7 , 2021 , [Online]. Available: http:\/\/arxiv.org\/abs\/2107.08430. Z. Ge, S. Liu, F. Wang, Z. Li, and J. Sun, \u201cYOLOX: Exceeding YOLO Series in 2021,\u201d pp. 1\u20137, 2021, [Online]. Available: http:\/\/arxiv.org\/abs\/2107.08430."},{"key":"e_1_3_2_1_136_1","volume-title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","author":"Wang C.-Y.","year":"2020","unstructured":"C.-Y. Wang , A. Bochkovskiy , and H.-Y. M. Liao , \u201c Scaled-YOLOv4: Scaling Cross Stage Partial Network ,\u201d 2020 , [Online]. Available: http:\/\/arxiv.org\/abs\/2011.08036. C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, \u201cScaled-YOLOv4: Scaling Cross Stage Partial Network,\u201d 2020, [Online]. Available: http:\/\/arxiv.org\/abs\/2011.08036."},{"key":"e_1_3_2_1_137_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"e_1_3_2_1_138_1","unstructured":"X. Dai and M. Liu \u201cDynamic Head: Unifying Object Detection Heads with Attentions.\u201d  X. Dai and M. Liu \u201cDynamic Head: Unifying Object Detection Heads with Attentions.\u201d"},{"key":"e_1_3_2_1_139_1","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"32","author":"Vu T.","year":"2019","unstructured":"T. Vu , H. Jang , T. X. Pham , and C. D. Yoo , \u201c Cascade RPN: Delving into high-quality region proposal network with adaptive convolution ,\u201d Adv. Neural Inf. Process. Syst. , vol. 32 , no. NeurIPS , 2019 . T. Vu, H. Jang, T. X. Pham, and C. D. Yoo, \u201cCascade RPN: Delving into high-quality region proposal network with adaptive convolution,\u201d Adv. Neural Inf. Process. Syst., vol. 32, no. NeurIPS, 2019."},{"key":"e_1_3_2_1_140_1","first-page":"3364","volume-title":"LIP: Local Importance-based Pooling","author":"Gao Z.","unstructured":"Z. Gao , L. Wang , and G. Wu , \u201c LIP: Local Importance-based Pooling ,\u201d pp. 3355\u2013 3364 . Z. Gao, L. Wang, and G. Wu, \u201cLIP: Local Importance-based Pooling,\u201d pp. 3355\u20133364."},{"key":"e_1_3_2_1_141_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.2983686"},{"key":"e_1_3_2_1_142_1","volume-title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","author":"Sun C.","year":"2011","unstructured":"C. Sun , A. Shrivastava , S. Singh , and A. Gupta , \u201c Revisiting Unreasonable Effectiveness of Data in Deep Learning Era ,\u201d 2011 . C. Sun, A. Shrivastava, S. Singh, and A. Gupta, \u201cRevisiting Unreasonable Effectiveness of Data in Deep Learning Era,\u201d 2011."},{"key":"e_1_3_2_1_143_1","first-page":"14","volume-title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","author":"Cai Z.","unstructured":"Z. Cai and N. Vasconcelos , \u201c Cascade R-CNN: High Quality Object Detection and Instance Segmentation ,\u201d pp. 1\u2013 14 . Z. Cai and N. Vasconcelos, \u201cCascade R-CNN: High Quality Object Detection and Instance Segmentation,\u201d pp. 1\u201314."},{"key":"e_1_3_2_1_144_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"e_1_3_2_1_145_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019259"}],"event":{"name":"ICDIP 2023: The 15th International Conference on Digital Image Processing","location":"Nanjing China","acronym":"ICDIP 2023"},"container-title":["Proceedings of the 15th International Conference on Digital Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604078.3604126","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604078.3604126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:17Z","timestamp":1750178177000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604078.3604126"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,19]]},"references-count":144,"alternative-id":["10.1145\/3604078.3604126","10.1145\/3604078"],"URL":"https:\/\/doi.org\/10.1145\/3604078.3604126","relation":{},"subject":[],"published":{"date-parts":[[2023,5,19]]},"assertion":[{"value":"2023-10-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}