{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T20:51:58Z","timestamp":1765486318168,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208899"},{"type":"electronic","value":"9783030208905"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-20890-5_15","type":"book-chapter","created":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T15:18:34Z","timestamp":1559402314000},"page":"228-240","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Detector-in-Detector: Multi-level Analysis for Human-Parts"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6449-2727","authenticated-orcid":false,"given":"Xiaojie","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3857-3982","authenticated-orcid":false,"given":"Lu","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4616-2200","authenticated-orcid":false,"given":"Qing","family":"Song","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9341-9342","authenticated-orcid":false,"given":"Fuqiang","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,2]]},"reference":[{"key":"15_CR1","unstructured":"Ribeiro, D., Mateus, A., Nascimento, J.C., Miraldo, P.: A real-time pedestrian detector using deep learning for human-aware navigation (2016)"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation (2017)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Papandreou, G., et al.: Towards accurate multi-person pose estimation in the wild, pp. 3711\u20133719 (2017)","DOI":"10.1109\/CVPR.2017.395"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Xiao, S., et al.: Recurrent 3D\u20132D dual learning for large-pose facial landmark detection. In: IEEE International Conference on Computer Vision, pp. 1642\u20131651 (2017)","DOI":"10.1109\/ICCV.2017.181"},{"key":"15_CR5","first-page":"6","volume":"72","author":"A Dhawan","year":"2013","unstructured":"Dhawan, A., Honrao, V.: Implementation of hand detection based techniques for human computer interaction. Comput. Sci. 72, 6\u201313 (2013)","journal-title":"Comput. Sci."},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Ghorban, F., Mar\u00edn, J., Yu, S., Colombo, A., Kummert, A.: Aggregated channels network for real-time pedestrian detection (2018)","DOI":"10.1117\/12.2309864"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Samangouei, P., Najibi, M., Davis, L., Chellappa, R.: Face-MagNet: magnifying feature maps to detect small faces (2018)","DOI":"10.1109\/WACV.2018.00020"},{"key":"15_CR8","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/978-3-319-61657-5_3","volume-title":"Deep Learning for Biometrics","author":"Chenchen Zhu","year":"2017","unstructured":"Zhu, C., Zheng, Y., Luu, K., Savvides, M.: CMS-RCNN: contextual multi-scale region-based CNN for unconstrained face detection (2017)"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Deng, X., et al.: Joint hand detection and rotation estimation by using CNN. IEEE Trans. Image Process. 27 (2016)","DOI":"10.1109\/TIP.2017.2779600"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Le, T.H.N., Quach, K.G., Zhu, C., Chi, N.D., Luu, K., Savvides, M.: Robust hand detection and classification in vehicles and in the wild. In: Computer Vision and Pattern Recognition Workshops, pp. 1203\u20131210 (2017)","DOI":"10.1109\/CVPRW.2017.159"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Mittal, A., Zisserman, A., Torr, P.: Hand detection using multiple proposals. In: British Machine Vision Conference, pp. 75.1\u201375.11 (2011)","DOI":"10.5244\/C.25.75"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Zhao, K., Zhang, W., Jiang, Y.: Semantic interactions in multi-level objects segmentation. In: International Conference on Computational and Information Sciences, pp. 665\u2013668 (2010)","DOI":"10.1109\/ICCIS.2010.342"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. Comput. Sci. (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"15_CR15","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Wei Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector, pp. 21\u201337 (2015)"},{"key":"15_CR16","unstructured":"Li, Z., Zhou, F.: FSSD: feature fusion single shot multibox detector (2017)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection, pp. 779\u2013788 (2015)","DOI":"10.1109\/CVPR.2016.91"},{"key":"15_CR18","unstructured":"Jiang, H., Learnedmiller, E.: Face detection with the faster R-CNN, pp. 650\u2013657 (2016)"},{"key":"15_CR19","unstructured":"He, K., Fu, Y., Xue, X.: A jointly learned deep architecture for facial attribute analysis and face detection in the wild (2017)"},{"key":"15_CR20","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: International Conference on Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Hu, P., Ramanan, D.: Finding tiny faces (2016)","DOI":"10.1109\/CVPR.2017.166"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Najibi, M., Samangouei, P., Chellappa, R., Davis, L.S.: SSH: single stage headless face detector, pp. 4885\u20134894 (2017)","DOI":"10.1109\/ICCV.2017.522"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Li, H., Lin, Z., Shen, X., Brandt, J., Hua, G.: A convolutional neural network cascade for face detection. In: Computer Vision and Pattern Recognition, pp. 5325\u20135334 (2015)","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"15_CR24","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Sign. Process. Lett. 23, 1499\u20131503 (2016)","journal-title":"IEEE Sign. Process. Lett."},{"key":"15_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Li, F.F.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15_CR28","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks (2016)"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Girshick, R., Iandola, F., Darrell, T., Malik, J.: Deformable part models are convolutional neural networks, pp. 437\u2013446 (2014)","DOI":"10.1109\/CVPR.2015.7298641"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: Proceedings Conference on Computer Vision Pattern Recognition, pp. 304\u2013311 (2009)","DOI":"10.1109\/CVPRW.2009.5206631"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, S., Benenson, R., Schiele, B.: CityPersons: a diverse dataset for pedestrian detection (2017)","DOI":"10.1109\/CVPR.2017.474"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Bambach, S., Lee, S., Crandall, D.J., Yu, C.: Lending a hand: detecting hands and recognizing activities in complex egocentric interactions. In: IEEE International Conference on Computer Vision (2016)","DOI":"10.1109\/ICCV.2015.226"},{"key":"15_CR33","unstructured":"Jain, V., Learned-Miller, E.: FDDB: a benchmark for face detection in unconstrained settings (2010)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, P., Chen, C.L., Tang, X.: WIDER FACE: a face detection benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5525\u20135533 (2016)","DOI":"10.1109\/CVPR.2016.596"},{"key":"15_CR35","unstructured":"Wu, J., et al.: AI challenger: a large-scale dataset for going deeper in image understanding (2017)"},{"key":"15_CR36","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Qin, H., Yan, J., Li, X., Hu, X.: Joint training of cascaded CNN for face detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3456\u20133465 (2016)","DOI":"10.1109\/CVPR.2016.376"},{"key":"15_CR38","first-page":"1","volume":"PP","author":"S Yang","year":"2017","unstructured":"Yang, S., Luo, P., Loy, C.C., Tang, X.: Faceness-Net: face detection through deep facial part responses. IEEE Trans. Pattern Anal. Mach. Intell. PP, 1 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining, pp. 761\u2013769 (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection, pp. 936\u2013944 (2016)","DOI":"10.1109\/CVPR.2017.106"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20890-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T15:23:35Z","timestamp":1559402615000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20890-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208899","9783030208905"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20890-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"2 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"979","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"274","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2.7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}