{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T17:06:27Z","timestamp":1708362387534},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s11042-022-12439-5","type":"journal-article","created":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T06:24:54Z","timestamp":1646115894000},"page":"15707-15723","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Double parallel branches FCOS for human detection in a crowd"],"prefix":"10.1007","volume":"81","author":[{"given":"Qing","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueshi","family":"Xin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengjie","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,1]]},"reference":[{"key":"12439_CR1","unstructured":"Bochkovskiy A, Wang CY, Liao H (2020) Yolov4: Optimal speed and accuracy of object detection"},{"key":"12439_CR2","doi-asserted-by":"crossref","unstructured":"Bodla N, Singh B, Chellappa R, Davis LS (2017) Improving object detection with one line of code","DOI":"10.1109\/ICCV.2017.593"},{"key":"12439_CR3","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade r-cnn: Delving into high quality object detection. In: The IEEE conference on computer vision and pattern recognition (CVPR), pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"12439_CR4","doi-asserted-by":"crossref","unstructured":"Chen Y, Wang L, Li C, Hou Y, Li W (2020) Convnets-based action recognition from skeleton motion maps. Multimedia Tools and Applications, 79(3)","DOI":"10.1007\/s11042-019-08261-1"},{"key":"12439_CR5","unstructured":"Dai L, Jifeng H, Yi S, Kaiming, Jian (2016) R-fcn: Object detection via region-based fully convolutional networks. In: Advances in neural information processing systems 29, pp 379\u2013387"},{"key":"12439_CR6","doi-asserted-by":"crossref","unstructured":"Du X, El-Khamy M, Lee J, Davis LS (2017) Fused dnn: a deep neural network fusion approach to fast and robust pedestrian detection. In: 2017 IEEE Winter conference on applications of computer vision (WACV)","DOI":"10.1109\/WACV.2017.111"},{"key":"12439_CR7","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) Centernet: Keypoint triplets for object detection. In: The IEEE international conference on computer vision (ICCV), pp 6569\u20136578","DOI":"10.1109\/ICCV.2019.00667"},{"key":"12439_CR8","unstructured":"Fu CY, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd : Deconvolutional single shot detector coRR"},{"key":"12439_CR9","doi-asserted-by":"crossref","unstructured":"Ge Z, Jie Z, Huang X, Xu R, Yoshie O (2020) Ps-rcnn: Detecting secondary human instances in a crowd via primary object suppression. In: IEEE","DOI":"10.1109\/ICME46284.2020.9102793"},{"key":"12439_CR10","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: The IEEE international conference on computer vision (ICCV), pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"12439_CR11","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2013) Rich feature hierarchies for accurate object detection and semantic segmentation. IEEE Computer Society","DOI":"10.1109\/CVPR.2014.81"},{"key":"12439_CR12","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Dollar P, Girshick R (2017) Mask r-cnn. In: The IEEE international conference on computer vision (ICCV), pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"12439_CR13","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: The IEEE conference on computer vision and pattern recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"12439_CR14","doi-asserted-by":"crossref","unstructured":"Huang Z, Yue K, Deng J, Zhou F (2020) Visible feature guidance for crowd pedestrian detection","DOI":"10.1007\/978-3-030-68238-5_20"},{"key":"12439_CR15","unstructured":"Jianan, Li, Xiaodan, Liang, Shengmei, Shen, Tingfa, Xu, Jiashi, Feng (2017) Scale-aware fast r-cnn for pedestrian detection. IEEE Transactions on Multimedia"},{"key":"12439_CR16","unstructured":"Jianan, Li, Xiaodan, Liang, Shengmei, Shen, Tingfa, Xu, Jiashi, Feng (2017) Scale-aware fast r-cnn for pedestrian detection. IEEE Transactions on Multimedia"},{"key":"12439_CR17","unstructured":"Karen S, Andrew Z (2014) Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556"},{"key":"12439_CR18","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: Detecting objects as paired keypoints. In: The european conference on computer vision (ECCV), pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"12439_CR19","doi-asserted-by":"crossref","unstructured":"Leibe B, Matas J, Sebe N, Welling M (2016) [Lecture notes in computer science] computer vision \u2013 eccv 2016 volume 9908 \u2014\u2014 a unified multi-scale deep convolutional neural network for fast object detection, vol. 10.1007\/978-3-319-46493-0, no Chapter 22, 354\u2013370","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"12439_CR20","doi-asserted-by":"crossref","unstructured":"Lin TY, Dollar P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: The IEEE conference on computer vision and pattern recognition (CVPR), pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"12439_CR21","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R, He K, Dollar P (2017) Focal loss for dense object detection. In: The IEEE international conference on computer vision (ICCV), pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"12439_CR22","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S (2015) Ssd: Single shot multibox detector. In: The European Conference on Computer Vision (ECCV), pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"12439_CR23","doi-asserted-by":"crossref","unstructured":"Liu S, Huang D, Wang Y (2019) Adaptive nms: Refining pedestrian detection in a crowd. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00662"},{"key":"12439_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_38","volume-title":"Learning efficient single-stage pedestrian detectors by asymptotic localization fitting","author":"W Liu","year":"2018","unstructured":"Liu W et al (2018) Learning efficient single-stage pedestrian detectors by asymptotic localization fitting. Springer, Cham"},{"key":"12439_CR25","doi-asserted-by":"crossref","unstructured":"Neubeck A, Van Gool L (2006) Efficient non-maximum suppression. In: 18Th international conference on pattern recognition (ICPR\u201906), vol 3, pp 850\u2013855","DOI":"10.1109\/ICPR.2006.479"},{"key":"12439_CR26","first-page":"1","volume":"6","author":"C Pang","year":"2020","unstructured":"Pang C, Wang W, Lan R, Shi Z, Luo X (2020) Bilinear pyramid network for flower species categorization. Multimed Tools Appl 6:1\u201311","journal-title":"Multimed Tools Appl"},{"key":"12439_CR27","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Computer vision & pattern recognition","DOI":"10.1109\/CVPR.2016.91"},{"key":"12439_CR28","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: The IEEE conference on computer vision and pattern recognition (CVPR), pp 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"12439_CR29","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv e-prints"},{"key":"12439_CR30","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":"12439_CR31","doi-asserted-by":"crossref","unstructured":"Rezatofighi H, Tsoi N, Gwak J, Sadeghian A, Savarese S (2019) Generalized intersection over union: A metric and a loss for bounding box regression. In: 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00075"},{"issue":"3","key":"12439_CR32","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"issue":"47-48","key":"12439_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-020-10093-3","volume":"79","author":"KC Santosh","year":"2020","unstructured":"Santosh KC, Antani SK (2020) Recent trends in image processing and pattern recognition. Multimed Tools Appl 79(47-48):1\u20133","journal-title":"Multimed Tools Appl"},{"key":"12439_CR34","unstructured":"Shao S, Zhao Z, Li B, Xiao T, Yu G, Zhang X, Sun J (2018) Crowdhuman: A benchmark for detecting human in a crowd"},{"key":"12439_CR35","first-page":"1","volume":"99","author":"Q Song","year":"2020","unstructured":"Song Q, Yang F, Yang L, Liu C, Xia L (2020) Learning point-guided localization for detection in remote sensing images. J Sel Top Appl Earth Obs Remote Sens, vol PP 99:1\u20131","journal-title":"J Sel Top Appl Earth Obs Remote Sens, vol PP"},{"key":"12439_CR36","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) Fcos: Fully convolutional one-stage object detection. In: The IEEE international conference on computer vision (ICCV), pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"12439_CR37","unstructured":"Liu W, Liao S, Hu W et al (2017) Denet: Scalable real-time object detection with directed sparse sampling. In: 2017 IEEE International conference on computer vision (ICCV)"},{"key":"12439_CR38","unstructured":"Wang X, Chen K, Huang Z, Yao C, Liu W (2017) Point linking network for object detection"},{"key":"12439_CR39","doi-asserted-by":"crossref","unstructured":"Wang S, Cheng J, Liu H, Tang M (2018) Pcn: Part and context information for pedestrian detection with cnns. arXiv","DOI":"10.5244\/C.31.34"},{"key":"12439_CR40","doi-asserted-by":"crossref","unstructured":"Wang X, Xiao T, Jiang Y, Shao S, Sun J, Shen C (2017) Repulsion loss: Detecting pedestrians in a crowd","DOI":"10.1109\/CVPR.2018.00811"},{"key":"12439_CR41","unstructured":"Xiao Y, Tian Z, Yu J, Zhang Y, Lan X (2020) A review of object detection based on deep learning. Multimedia Tools and Applications, (11)"},{"key":"12439_CR42","doi-asserted-by":"crossref","unstructured":"Yang L, Song Q, Wang Z, Hu M, Liu C, Xin X, Jia W, Xu S (2020) Renovating parsing r-cnn for accurate multiple human parsing. In: Proceedings of European Conference on Computer Vision (ECCV)","DOI":"10.1007\/978-3-030-58610-2_25"},{"key":"12439_CR43","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang Y, Wang Z, Cao Z, Huang T (2016) Unitbox: an advanced object detection network. ACM","DOI":"10.1145\/2964284.2967274"},{"key":"12439_CR44","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: 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"12439_CR45","volume-title":"Occlusion-aware r-cnn: Detecting pedestrians in a crowd","author":"S Zhang","year":"2018","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li SZ (2018) Occlusion-aware r-cnn: Detecting pedestrians in a crowd. Springer, Cham"},{"key":"12439_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: The IEEE conference on computer vision and pattern recognition (CVPR), pp 4203\u20134212","DOI":"10.1109\/CVPR.2018.00442"},{"key":"12439_CR47","unstructured":"Zhang K, Xiong F, Sun P, Hu L, Li B, Yu G (2019) Double anchor r-cnn for human detection in a crowd"},{"key":"12439_CR48","doi-asserted-by":"crossref","unstructured":"Zheng Z, Wang P, Liu W, Li J, Ren D (2020) Distance-iou loss: Faster and better learning for bounding box regression. In: AAAI Conference on artificial intelligence","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"12439_CR49","doi-asserted-by":"crossref","unstructured":"Zhou S, Qiu J (2021) Enhanced ssd with interactive multi-scale attention features for object detection. Multimedia Tools and Applications, (1)","DOI":"10.1007\/s11042-020-10191-2"},{"key":"12439_CR50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_9","volume-title":"Bi-box regression for pedestrian detection and occlusion estimation","author":"C Zhou","year":"2018","unstructured":"Zhou C, Yuan J (2018) Bi-box regression for pedestrian detection and occlusion estimation. Springer, Cham"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12439-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-12439-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12439-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T11:28:05Z","timestamp":1651490885000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-12439-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,1]]},"references-count":50,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["12439"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-12439-5","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,1]]},"assertion":[{"value":"16 April 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service and\/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}