{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T21:28:08Z","timestamp":1782941288606,"version":"3.54.5"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2022,2,19]],"date-time":"2022-02-19T00:00:00Z","timestamp":1645228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,19]],"date-time":"2022-02-19T00:00:00Z","timestamp":1645228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s00521-021-05978-9","type":"journal-article","created":{"date-parts":[[2022,2,19]],"date-time":"2022-02-19T12:04:21Z","timestamp":1645272261000},"page":"8275-8290","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":128,"title":["Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3"],"prefix":"10.1007","volume":"34","author":[{"given":"Petr","family":"Hurtik","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vojtech","family":"Molek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Hula","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marek","family":"Vajgl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0759-0341","authenticated-orcid":false,"given":"Pavel","family":"Vlasanek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomas","family":"Nejezchleba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,2,19]]},"reference":[{"key":"5978_CR1","doi-asserted-by":"crossref","unstructured":"Hurtik P, Molek V, Vlasanek P (2020) YOLO-ASC: you only look once and see contours, accepted. In: Proceedings of IEEE-WCCI conference","DOI":"10.1109\/IJCNN48605.2020.9207223"},{"key":"5978_CR2","doi-asserted-by":"crossref","unstructured":"Kirillov A, He K, Girshick R, Rother C, Doll\u00e1r P (2019) Panoptic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9404\u20139413","DOI":"10.1109\/CVPR.2019.00963"},{"key":"5978_CR3","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91\u201399"},{"key":"5978_CR4","doi-asserted-by":"crossref","unstructured":"Lin TY, 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"},{"issue":"2","key":"5978_CR5","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2020","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2020) Mask R-CNN. IEEE Trans Pattern Anal Mach Intell 42(2):386\u2013397","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5978_CR6","unstructured":"Fu CY, Shvets M, Berg AC (2019) RetinaMask: learning to predict masks improves state-of-the-art single-shot detection for free. arXiv preprint, arXiv:1901.03353"},{"key":"5978_CR7","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint, arXiv:1804.02767"},{"key":"5978_CR8","doi-asserted-by":"crossref","unstructured":"Huang R, Pedoeem J, Chen C (2018) YOLO-LITE: a real-time object detection algorithm optimized for non-GPU computers. In: 2018 IEEE international conference on big data (big data). IEEE, pp 2503\u20132510","DOI":"10.1109\/BigData.2018.8621865"},{"key":"5978_CR9","doi-asserted-by":"crossref","unstructured":"Oltean G, Florea C, Orghidan R, Oltean V (2019) Towards real time vehicle counting using yolo-tiny and fast motion estimation. In: 2019 IEEE 25th international symposium for design and technology in electronic packaging (SIITME). IEEE, pp 240\u2013243","DOI":"10.1109\/SIITME47687.2019.8990708"},{"key":"5978_CR10","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2019) Efficientdet: scalable and efficient object detection. arXiv preprint, arXiv:1911.09070","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"5978_CR11","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":"5978_CR12","doi-asserted-by":"crossref","unstructured":"Xie S, Girshick R, Doll\u00e1r P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1492\u20131500","DOI":"10.1109\/CVPR.2017.634"},{"issue":"2","key":"5978_CR13","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1109\/TPAMI.2019.2922181","volume":"42","author":"Zhiqiang Shen","year":"2019","unstructured":"Shen Zhiqiang, Liu Zhuang, Li Jianguo, Jiang Yu-Gang, Chen Yurong, Xue Xiangyang (2019) Object detection from scratch with deep supervision. IEEE Trans Pattern Anal Mach Intell 42(2):398\u2013412","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5978_CR14","doi-asserted-by":"crossref","unstructured":"Zhu R, Zhang S, Wang X, Wen L, Shi H, Bo L, Mei T (2019) ScratchDet: training single-shot object detectors from scratch. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2268\u20132277","DOI":"10.1109\/CVPR.2019.00237"},{"key":"5978_CR15","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"},{"issue":"8","key":"5978_CR16","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/TPAMI.2014.2300479","volume":"36","author":"Piotr Doll\u00e1r","year":"2014","unstructured":"Doll\u00e1r Piotr, Appel Ron, Belongie Serge, Perona Pietro (2014) Fast feature pyramids for object detection. IEEE Trans Pattern Anal Mach Intell 36(8):1532\u20131545","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5978_CR17","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, 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":"5978_CR18","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":"5978_CR19","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 international conference on computer vision, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"5978_CR20","doi-asserted-by":"crossref","unstructured":"Chen X, Girshick R, He K, Doll\u00e1r P (2019) TensorMask: a foundation for dense object segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 2061\u20132069","DOI":"10.1109\/ICCV.2019.00215"},{"key":"5978_CR21","doi-asserted-by":"crossref","unstructured":"Bolya D, Zhou C, Xiao F, Lee YJ (2019) YOLACT++: better real-time instance segmentation. arXiv preprint, arXiv:1912.06218","DOI":"10.1109\/ICCV.2019.00925"},{"key":"5978_CR22","unstructured":"Newell A, Huang Z, Deng J (2017) Associative embedding: end-to-end learning for joint detection and grouping. In: Advances in neural information processing systems, pp 2277\u20132287"},{"key":"5978_CR23","doi-asserted-by":"crossref","unstructured":"Liu S, Jia J, Fidler S, Urtasun R (2017) SGN: sequential grouping networks for instance segmentation. In: Proceedings of the IEEE International conference on computer vision, pp 3496\u20133504","DOI":"10.1109\/ICCV.2017.378"},{"key":"5978_CR24","unstructured":"Wang X, Zhang R, Kong T, Li L, Shen C (2020) SOLOv2: dynamic, faster and stronger. arXiv preprint, arXiv:2003.10152"},{"key":"5978_CR25","doi-asserted-by":"crossref","unstructured":"Xie E, Sun P, Song X, Wang W, Liu X, Liang D, Shen C, Luo P (2019) PolarMask: single shot instance segmentation with polar representation. arXiv preprint, arXiv:1909.13226","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"5978_CR26","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":"5978_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"5978_CR28","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"5978_CR29","unstructured":"MacQueen J et al (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, vol 1. Oakland, CA, USA, pp 281\u2013297"},{"key":"5978_CR30","doi-asserted-by":"crossref","unstructured":"Lin TY, 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"},{"key":"5978_CR31","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"4","key":"5978_CR32","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1109\/TPAMI.2016.2578328","volume":"39","author":"Bharath Hariharan","year":"2016","unstructured":"Hariharan Bharath, Arbelaez Pablo, Girshick Ross, Malik Jitendra (2016) Object instance segmentation and fine-grained localization using hypercolumns. IEEE Trans Pattern Anal Mach Intell 39(4):627\u2013639","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5978_CR33","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"5978_CR34","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"},{"key":"5978_CR35","unstructured":"Bochkovskiy A, Wang CY, Liao HY (2020) YOLOv4: optimal speed and accuracy of object detection. arXiv preprint, arXiv:2004.10934"},{"issue":"10","key":"5978_CR36","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/2001269.2001295","volume":"54","author":"Honglak Lee","year":"2011","unstructured":"Lee Honglak, Grosse Roger, Ranganath Rajesh, Ng Andrew Y (2011) Unsupervised learning of hierarchical representations with convolutional deep belief networks. Commun ACM 54(10):95\u2013103","journal-title":"Commun ACM"},{"key":"5978_CR37","unstructured":"Ruder S (2017) An overview of multi-task learning in deep neural networks. arXiv preprint, arXiv:1706.05098"},{"key":"5978_CR38","doi-asserted-by":"crossref","unstructured":"Varma G, Subramanian A, Namboodiri A, Chandraker M, Jawahar CV (2019) IDD: a dataset for exploring problems of autonomous navigation in unconstrained environments. In: 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 1743\u20131751","DOI":"10.1109\/WACV.2019.00190"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05978-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-05978-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05978-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,18]],"date-time":"2022-04-18T12:27:29Z","timestamp":1650284849000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-05978-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,19]]},"references-count":38,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["5978"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-05978-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,19]]},"assertion":[{"value":"12 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and animals participants"}}]}}