{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T15:54:05Z","timestamp":1762876445284,"version":"3.37.3"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"26","license":[{"start":{"date-parts":[[2023,6,25]],"date-time":"2023-06-25T00:00:00Z","timestamp":1687651200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,25]],"date-time":"2023-06-25T00:00:00Z","timestamp":1687651200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"The Science and Technology Development Fund (FDCT) of Macau","award":["Grant No. 0071\/2022\/A."],"award-info":[{"award-number":["Grant No. 0071\/2022\/A."]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s00521-023-08782-9","type":"journal-article","created":{"date-parts":[[2023,6,25]],"date-time":"2023-06-25T10:01:38Z","timestamp":1687687298000},"page":"19297-19313","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Bounding convolutional network for refining object locations"],"prefix":"10.1007","volume":"35","author":[{"given":"Shenyong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2664-4413","authenticated-orcid":false,"given":"Wenmin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honglei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shixiong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,25]]},"reference":[{"key":"8782_CR1","unstructured":"Szegedy C, Toshev A, Erhan D (2013) Deep neural networks for object detection. l2013 - research. Google"},{"key":"8782_CR2","doi-asserted-by":"crossref","unstructured":"Li Y, Qi H, Dai J, Ji X, Wei Y (2017) Fully convolutional instance-aware semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2359\u20132367","DOI":"10.1109\/CVPR.2017.472"},{"issue":"6","key":"8782_CR3","doi-asserted-by":"publisher","first-page":"2065","DOI":"10.1007\/s00521-020-05081-5","volume":"33","author":"A Kompella","year":"2021","unstructured":"Kompella A, Kulkarni RV (2021) A semi-supervised recurrent neural network for video salient object detection. Neural Comput Appl 33(6):2065\u20132083","journal-title":"Neural Comput Appl"},{"key":"8782_CR4","doi-asserted-by":"crossref","unstructured":"Chawla A, Yin H, Molchanov P, Alvarez J (2021) Data-free knowledge distillation for object detection. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 3289\u20133298","DOI":"10.1109\/WACV48630.2021.00333"},{"key":"8782_CR5","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"issue":"9","key":"8782_CR6","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8782_CR7","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"8782_CR8","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28:91\u201399","journal-title":"Adv Neural Inf Process Syst"},{"key":"8782_CR9","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"8782_CR10","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: Single shot multibox detector. In: European conference on computer vision, Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"8782_CR11","unstructured":"Zhou X, Wang D, Kr\u00e4henb\u00fchl P (2019) Objects as points. arXiv preprint arXiv:1904.07850"},{"key":"8782_CR12","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"8782_CR13","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8782_CR14","doi-asserted-by":"crossref","unstructured":"Yu F, Wang D, Shelhamer E, Darrell T (2018) Deep layer aggregation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2403\u20132412","DOI":"10.1109\/CVPR.2018.00255"},{"key":"8782_CR15","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"issue":"2","key":"8782_CR16","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW (2013) Selective search for object recognition. Int J Comput Vision 104(2):154\u2013171","journal-title":"Int J Comput Vision"},{"key":"8782_CR17","doi-asserted-by":"crossref","unstructured":"Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: 2008 IEEE conference on computer vision and pattern recognition, pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"8782_CR18","unstructured":"Wang X, Chen K, Huang Z, Yao C, Liu W (2017) Point linking network for object detection. arXiv preprint arXiv:1706.03646"},{"key":"8782_CR19","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: Detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"8782_CR20","doi-asserted-by":"crossref","unstructured":"Zhou X, Zhuo J, Krahenbuhl P (2019) Bottom-up object detection by grouping extreme and center points. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 850\u2013859","DOI":"10.1109\/CVPR.2019.00094"},{"key":"8782_CR21","doi-asserted-by":"crossref","unstructured":"Qiu H, Ma Y, Li Z, Liu S, Sun J (2020) Borderdet: Border feature for dense object detection. In: European conference on computer vision, Springer, pp 549\u2013564","DOI":"10.1007\/978-3-030-58452-8_32"},{"key":"8782_CR22","doi-asserted-by":"crossref","unstructured":"Yang Z, Liu S, Hu H, Wang L, Lin S (2019) Reppoints: point set representation for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 9657\u20139666","DOI":"10.1109\/ICCV.2019.00975"},{"key":"8782_CR23","unstructured":"Vu T, Jang H, Pham TX, Yoo CD (2019) Cascade rpn: Delving into high-quality region proposal network with adaptive convolution. arXiv preprint arXiv:1909.06720"},{"key":"8782_CR24","doi-asserted-by":"crossref","unstructured":"Zhu X, Hu H, Lin S, Dai J (2019) Deformable convnets v2: More deformable, better results. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9308\u20139316","DOI":"10.1109\/CVPR.2019.00953"},{"key":"8782_CR25","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"8782_CR26","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"8782_CR27","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"8782_CR28","doi-asserted-by":"crossref","unstructured":"Wu Y, Chen Y, Yuan L, Liu Z, Wang L, Li H, Fu Y (2020) Rethinking classification and localization for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10186\u201310195","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"8782_CR29","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: European conference on computer vision, Springer, pp 483\u2013499","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"8782_CR30","doi-asserted-by":"crossref","unstructured":"Lan S, Ren Z, Wu Y, Davis LS, Hua G (2020) Saccadenet: a fast and accurate object detector. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10397\u201310406","DOI":"10.1109\/CVPR42600.2020.01041"},{"key":"8782_CR31","doi-asserted-by":"crossref","unstructured":"Park H-J, Choi Y-J, Lee Y-W, Kim B-G (2022) ssfpn: Scale sequence (s$$^{\\hat{}}{2}$$) feature based-feature pyramid network for object detection. arXiv e-prints, 2208","DOI":"10.3390\/s23094432"},{"key":"8782_CR32","doi-asserted-by":"crossref","unstructured":"Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251\u20131258","DOI":"10.1109\/CVPR.2017.195"},{"key":"8782_CR33","doi-asserted-by":"crossref","unstructured":"He Y, Zhu C, Wang J, Savvides M, Zhang X (2019) Bounding box regression with uncertainty for accurate object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2888\u20132897","DOI":"10.1109\/CVPR.2019.00300"},{"key":"8782_CR34","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European conference on computer vision, Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"2","key":"8782_CR35","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vision 88(2):303\u2013338","journal-title":"Int J Comput Vision"},{"key":"8782_CR36","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861"},{"key":"8782_CR37","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122"},{"key":"8782_CR38","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"18","key":"8782_CR39","doi-asserted-by":"publisher","first-page":"11627","DOI":"10.1007\/s00521-021-05867-1","volume":"33","author":"W Zhang","year":"2021","unstructured":"Zhang W, Fu C, Xie H, Zhu M, Tie M, Chen J (2021) Global context aware rcnn for object detection. Neural Comput Appl 33(18):11627\u201311639","journal-title":"Neural Comput Appl"},{"key":"8782_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/3189691","volume":"2020","author":"N-D Nguyen","year":"2020","unstructured":"Nguyen N-D, Do T, Ngo TD, Le D-D (2020) An evaluation of deep learning methods for small object detection. J Electr Comput Eng 2020:1\u201318","journal-title":"J Electr Comput Eng"},{"issue":"7","key":"8782_CR41","first-page":"3614","volume":"44","author":"S Vandenhende","year":"2021","unstructured":"Vandenhende S, Georgoulis S, Van Gansbeke W, Proesmans M, Dai D, Van Gool L (2021) Multi-task learning for dense prediction tasks: A survey. IEEE Trans Pattern Anal Mach Intell 44(7):3614\u20133633","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"8782_CR42","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"issue":"19","key":"8782_CR43","doi-asserted-by":"publisher","first-page":"7663","DOI":"10.3390\/s22197663","volume":"22","author":"X Wang","year":"2022","unstructured":"Wang X, Zhu D, Yan Y (2022) Towards efficient detection for small objects via attention-guided detection network and data augmentation. Sensors 22(19):7663","journal-title":"Sensors"},{"key":"8782_CR44","unstructured":"Farhadi A, Redmon J (2018) Yolov3: an incremental improvement. In: Computer vision and pattern recognition, vol. 1804. Springer Berlin\/Heidelberg, Germany, p 1\u20136"},{"key":"8782_CR45","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934"},{"key":"8782_CR46","doi-asserted-by":"crossref","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li SZ (2018) Single-shot refinement neural network for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4203\u20134212","DOI":"10.1109\/CVPR.2018.00442"},{"key":"8782_CR47","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430"},{"key":"8782_CR48","unstructured":"Xu S, Wang X, Lv W, Chang Q, Cui C, Deng K, Wang G, Dang Q, Wei S, Du Y, et al (2022) Pp-yoloe: An evolved version of yolo. arXiv preprint arXiv:2203.16250"},{"key":"8782_CR49","unstructured":"Glenn J (2022) YOLOv5 release v6.1. https:\/\/github.com\/ ultralytics\/yolov5\/releases\/tag\/v6.1\/"},{"key":"8782_CR50","unstructured":"Wang C-Y, Yeh I-H, Liao H-YM (2021) You only learn one representation: Unified network for multiple tasks. arXiv preprint arXiv:2105.04206"},{"key":"8782_CR51","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM (2022) Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696"},{"key":"8782_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12864-019-6413-7","volume":"21","author":"D Chicco","year":"2020","unstructured":"Chicco D, Jurman G (2020) The advantages of the matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation. BMC Genom 21:1\u201313","journal-title":"BMC Genom"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08782-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08782-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08782-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T15:25:41Z","timestamp":1692026741000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08782-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,25]]},"references-count":52,"journal-issue":{"issue":"26","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["8782"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08782-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2023,6,25]]},"assertion":[{"value":"24 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}