{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T03:53:16Z","timestamp":1781495596993,"version":"3.54.1"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"20","license":[{"start":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T00:00:00Z","timestamp":1690329600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T00:00:00Z","timestamp":1690329600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001289"],"award-info":[{"award-number":["62001289"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61961014"],"award-info":[{"award-number":["61961014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s10489-023-04747-6","type":"journal-article","created":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T07:01:34Z","timestamp":1690354894000},"page":"24551-24565","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["GET: group equivariant transformer for person detection of overhead fisheye images"],"prefix":"10.1007","volume":"53","author":[{"given":"Yongqing","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dandan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nanyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"You","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2506-5981","authenticated-orcid":false,"given":"Yong","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,26]]},"reference":[{"key":"4747_CR1","unstructured":"Challenging events for person detection from overhead fisheye images (2022). https:\/\/vip.bu.edu\/projects\/vsns\/cossy\/datasets\/cepdof\/"},{"key":"4747_CR2","unstructured":"Human-aligned bounding boxes from overhead fisheye cameras dataset (2022). https:\/\/vip.bu.edu\/projects\/vsns\/cossy\/datasets\/habbof\/"},{"key":"4747_CR3","unstructured":"Mirror worlds challenge (2022). http:\/\/www2.icat.vt.edu\/mirrorworlds\/challenge\/index.html"},{"key":"4747_CR4","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.neucom.2018.01.092","volume":"300","author":"A Brunetti","year":"2018","unstructured":"Brunetti A, Buongiorno D, Trotta GF, Bevilacqua V (2018) Computer vision and deep learning techniques for pedestrian detection and tracking: A survey. Neurocomputing 300:17\u201333","journal-title":"Neurocomputing"},{"key":"4747_CR5","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. European Conference on Computer Vision (ECCV) pp. 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"4747_CR6","doi-asserted-by":"crossref","unstructured":"Chang\u00a0Q Hung K\u00a0W JJ (2018) Deep learning based image super-resolution for nonlinear lens distortion. In: Neurocomputing, pp. 969\u2013982. Elsevier","DOI":"10.1016\/j.neucom.2017.09.035"},{"key":"4747_CR7","unstructured":"Chiang AT, Wang Y (2014) Human detection in fish-eye images using hog-based detectors over rotated windows. 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) pp. 1\u20136"},{"key":"4747_CR8","unstructured":"Cohen T, Welling M (2016) Group equivariant convolutional networks. International Conference on Machine Learning (ICML) pp. 2990\u20132999"},{"key":"4747_CR9","first-page":"886","volume":"1","author":"N Dalal","year":"2005","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. Proc IEEE\/CVF Int Conf Comput Vision (CVPR) 1:886\u2013893","journal-title":"Proc IEEE\/CVF Int Conf Comput Vision (CVPR)"},{"key":"4747_CR10","doi-asserted-by":"crossref","unstructured":"Deng\u00a0L Chen\u00a0Z CBea (2016) Incremental image set querying based localization. In: Neurocomputing, pp. 315\u2013324. Elsevier","DOI":"10.1016\/j.neucom.2015.11.117"},{"key":"4747_CR11","doi-asserted-by":"crossref","unstructured":"Ding J, Xue N, Long Y, Xia GS, Lu Q (2019) Learning roi transformer for oriented object detection in aerial images. Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR) pp. 2849\u20132858","DOI":"10.1109\/CVPR.2019.00296"},{"issue":"8","key":"4747_CR12","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/TPAMI.2014.2300479","volume":"36","author":"P Doll\u00e1r","year":"2014","unstructured":"Doll\u00e1r P, Appel R, Belongie S, Perona P (2014) Fast feature pyramids for object detection. IEEE Trans Pattern Anal Mach Intell (TPAMI) 36(8):1532\u20131545","journal-title":"IEEE Trans Pattern Anal Mach Intell (TPAMI)"},{"key":"4747_CR13","doi-asserted-by":"crossref","unstructured":"Duan Z, Tezcan O, Nakamura H, Ishwar P, Konrad J (2020) Rapid: rotation-aware people detection in overhead fisheye images. Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR) Workshops pp. 636\u2013637","DOI":"10.1109\/CVPRW50498.2020.00326"},{"issue":"12","key":"4747_CR14","doi-asserted-by":"publisher","first-page":"2179","DOI":"10.1109\/TPAMI.2008.260","volume":"31","author":"M Enzweiler","year":"2008","unstructured":"Enzweiler M, Gavrila DM (2008) Monocular pedestrian detection: Survey and experiments. IEEE Trans Pattern Anal Mach Intell (TPAMI) 31(12):2179\u20132195","journal-title":"IEEE Trans Pattern Anal Mach Intell (TPAMI)"},{"key":"4747_CR15","unstructured":"Fu CY, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd: Deconvolutional single shot detector. arXiv:1701.06659"},{"key":"4747_CR16","doi-asserted-by":"crossref","unstructured":"Georgakopoulos S\u00a0V Kottari\u00a0K DKea (2018) Pose recognition using convolutional neural networks on omni-directional images. In: Neurocomputing, pp. 23\u201331. Elsevier","DOI":"10.1016\/j.neucom.2017.08.071"},{"key":"4747_CR17","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision (ICCV) pp. 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"4747_CR18","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"4747_CR19","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision(ICCV), pp. 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"4747_CR20","doi-asserted-by":"crossref","unstructured":"Jiang Y, Zhu X, Wang X, Yang S, Li W, Wang H, Fu P, Luo Z (2017) R2cnn: Rotational region cnn for orientation robust scene text detection. arXiv:1706.09579","DOI":"10.1109\/ICPR.2018.8545598"},{"key":"4747_CR21","doi-asserted-by":"crossref","unstructured":"Khan S, Naseer M, Hayat M, Zamir SW, Khan FS, Shah M (2021) Transformers in vision: A survey. arXiv:2101.01169","DOI":"10.1145\/3505244"},{"key":"4747_CR22","doi-asserted-by":"crossref","unstructured":"Krams O, Kiryati N (2017) People detection in top-view fisheye imaging. In: IEEE international conference on advanced video and signal based surveillance (AVSS), pp. 1\u20136. IEEE","DOI":"10.1109\/AVSS.2017.8078535"},{"key":"4747_CR23","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: Detecting objects as paired keypoints. Proceedings of the European conference on computer vision (ECCV) pp. 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"4747_CR24","doi-asserted-by":"publisher","unstructured":"Li S, Tezcan MO, Ishwar P, Konrad J (2019) Supervised people counting using an overhead fisheye camera. 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) pp. 1\u20138. https:\/\/doi.org\/10.1109\/AVSS.2019.8909877","DOI":"10.1109\/AVSS.2019.8909877"},{"key":"4747_CR25","doi-asserted-by":"crossref","unstructured":"Li\u00a0N Si\u00a0Y DDea (2017) Ecg beats classification via online sparse dictionary and time pyramid matching. In: International Conference on Communication Technology (ICCT), pp. 1537\u20131543. IEEE","DOI":"10.1109\/ICCT.2017.8359889"},{"key":"4747_CR26","doi-asserted-by":"crossref","unstructured":"Li\u00a0N Wang\u00a0J LZea (2021) High-order-interaction for weakly supervised fine-grained visual categorization. In: Neurocomputing, pp. 27\u201336. Elsevier","DOI":"10.1016\/j.neucom.2021.08.108"},{"key":"4747_CR27","doi-asserted-by":"crossref","unstructured":"Li\u00a0N ZCC (2020) Ampa-net:optimization-inspired attention neural network for deep compressed sensing. In: International Conference on Communication Technology (ICCT), pp. 1338\u20131344. IEEE","DOI":"10.1109\/ICCT50939.2020.9295956"},{"key":"4747_CR28","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 (ECCV), pp. 740\u2013755. Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"4747_CR29","unstructured":"Liu L, Pan Z, Lei B (2017) Learning a rotation invariant detector with rotatable bounding box. arXiv:1711.09405"},{"key":"4747_CR30","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. European Conference on Computer Vision (ECCV) pp. 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"4747_CR31","doi-asserted-by":"crossref","unstructured":"Liu Z, Hu J, Weng L, Yang Y (2017) Rotated region based cnn for ship detection. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 900\u2013904. IEEE","DOI":"10.1109\/ICIP.2017.8296411"},{"issue":"11","key":"4747_CR32","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TMM.2018.2818020","volume":"20","author":"J Ma","year":"2018","unstructured":"Ma J, Shao W, Ye H, Wang L, Wang H, Zheng Y, Xue X (2018) Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans Multimed 20(11):3111\u20133122","journal-title":"IEEE Trans Multimed"},{"key":"4747_CR33","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.patcog.2015.08.027","volume":"51","author":"DT Nguyen","year":"2016","unstructured":"Nguyen DT, Li W, Ogunbona PO (2016) Human detection from images and videos: A survey. Elsevier Pattern Recog 51:148\u2013175","journal-title":"Elsevier Pattern Recog"},{"key":"4747_CR34","doi-asserted-by":"crossref","unstructured":"Noh J, Lee S, Kim B, Kim G (2018) Improving occlusion and hard negative handling for single-stage pedestrian detectors. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 966\u2013974","DOI":"10.1109\/CVPR.2018.00107"},{"key":"4747_CR35","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR) pp. 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"4747_CR36","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"4747_CR37","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv:1804.02767"},{"key":"4747_CR38","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 Inform Process Syst 28:91\u201399","journal-title":"Adv Neural Inform Process Syst"},{"key":"4747_CR39","unstructured":"Saito M, Kitaguchi K, Kimura G, Hashimoto M (2011) People detection and tracking from fish-eye image based on probabilistic appearance model. In: SICE Annual Conference 2011, pp. 435\u2013440. IEEE"},{"key":"4747_CR40","doi-asserted-by":"crossref","unstructured":"Tamura M, Horiguchi S, Murakami T (2019) Omnidirectional pedestrian detection by rotation invariant training. 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) pp. 1989\u20131998","DOI":"10.1109\/WACV.2019.00216"},{"key":"4747_CR41","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"4747_CR42","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(ICCV), pp. 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"4747_CR43","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in Neural Information Processing Systems (NIPS), pp. 5998\u20136008"},{"key":"4747_CR44","doi-asserted-by":"crossref","unstructured":"Wang H, Zhu Y, Green B, Adam H, Yuille A, Chen LC (2020) Axial-deeplab: Stand-alone axial-attention for panoptic segmentation. In: European Conference on Computer Vision(ECCV), pp. 108\u2013126. Springer","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"4747_CR45","doi-asserted-by":"crossref","unstructured":"Wang T, Chang CW, Wu YS (2107) Template-based people detection using a single downward-viewing fisheye camera. In: International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), pp. 719\u2013723. IEEE","DOI":"10.1109\/ISPACS.2017.8266570"},{"key":"4747_CR46","doi-asserted-by":"crossref","unstructured":"Zhang L, Lin L, Liang X, He K (2016) Is faster r-cnn doing well for pedestrian detection? In: European Conference on Computer Vision (ECCV), pp. 443\u2013457. Springer","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"4747_CR47","doi-asserted-by":"crossref","unstructured":"Zhang S, Benenson R, Schiele B (2017) Citypersons: A diverse dataset for pedestrian detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 3213\u20133221","DOI":"10.1109\/CVPR.2017.474"},{"key":"4747_CR48","doi-asserted-by":"crossref","unstructured":"Zhang S, Benenson R, Schiele B, et\u00a0al (2015) Filtered channel features for pedestrian detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), vol.\u00a01, p.\u00a04","DOI":"10.1109\/CVPR.2015.7298784"},{"key":"4747_CR49","doi-asserted-by":"crossref","unstructured":"Zhang S, Chi C, Yao Y, Lei Z, Li SZ (2020) Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 9759\u20139768","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"4747_CR50","doi-asserted-by":"crossref","unstructured":"Zhang S, Yang J, Schiele B (2018) Occluded pedestrian detection through guided attention in cnns. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 6995\u20137003","DOI":"10.1109\/CVPR.2018.00731"},{"key":"4747_CR51","doi-asserted-by":"crossref","unstructured":"Zhao H, Jiang L, Jia J, Torr PH, Koltun V (2021) Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 16259\u201316268","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"4747_CR52","first-page":"9259","volume":"33","author":"Q Zhao","year":"2019","unstructured":"Zhao Q, Sheng T, Wang Y, Tang Z, Chen Y, Cai L, Ling H (2019) M2det: A single-shot object detector based on multi-level feature pyramid network. Proc Conf Artif Intell (AAAI) 33:9259\u20139266","journal-title":"Proc Conf Artif Intell (AAAI)"},{"key":"4747_CR53","doi-asserted-by":"crossref","unstructured":"Zhao K, Liao K LCea (2021) Joint distortion rectification and super-resolution for self-driving scene perception. In: Neurocomputing, pp. 176\u2013185. Elsevier","DOI":"10.1016\/j.neucom.2020.12.115"},{"key":"4747_CR54","unstructured":"Zhou X, Wang D, Kr\u00e4henb\u00fchl P (2019) Objects as points. arXiv:1904.07850"},{"key":"4747_CR55","doi-asserted-by":"crossref","unstructured":"Zhou Y, Ye Q, Qiu Q, Jiao J (2017) Oriented response networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (CVPR), pp. 519\u2013528","DOI":"10.1109\/CVPR.2017.527"},{"key":"4747_CR56","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2020) Deformable detr: Deformable transformers for end-to-end object detection. arXiv:2010.04159"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-04747-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-023-04747-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-04747-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:17:25Z","timestamp":1729815445000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-023-04747-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,26]]},"references-count":56,"journal-issue":{"issue":"20","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["4747"],"URL":"https:\/\/doi.org\/10.1007\/s10489-023-04747-6","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,26]]},"assertion":[{"value":"29 May 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}