{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T09:51:40Z","timestamp":1781257900256,"version":"3.54.1"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,5,18]],"date-time":"2021-05-18T00:00:00Z","timestamp":1621296000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,18]],"date-time":"2021-05-18T00:00:00Z","timestamp":1621296000000},"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":["Vis Comput"],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s00371-021-02157-8","type":"journal-article","created":{"date-parts":[[2021,5,18]],"date-time":"2021-05-18T21:02:54Z","timestamp":1621371774000},"page":"2801-2825","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["A robust multi-scale deep learning approach for unconstrained hand detection aided by skin segmentation"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1296-7748","authenticated-orcid":false,"given":"Kankana","family":"Roy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajiv Ranjan","family":"Sahay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,5,18]]},"reference":[{"key":"2157_CR1","doi-asserted-by":"crossref","unstructured":"Yang, Y., Fermuller C.and\u00a0Li, Y., Aloimonos, Y.: Grasp type revisited: a modern perspective on a classical feature for vision. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 400\u2013408 (2015)","DOI":"10.1109\/CVPR.2015.7298637"},{"key":"2157_CR2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942030","author":"X Shu","year":"2019","unstructured":"Shu, X., Tang, J., Qi, G., Liu, W., Yang, J.: Hierarchical long short-term concurrent memory for human interaction recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2019). https:\/\/doi.org\/10.1109\/TPAMI.2019.2942030","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2157_CR3","unstructured":"Shu, X., Zhang, L., Sun, Y., Tang, J.: Host-parasite: Graph lstm-in-lstm for group activity recognition. IEEE Trans. Neural Netw. Learn. Syst. 1\u201312 (2020)"},{"key":"2157_CR4","doi-asserted-by":"crossref","unstructured":"Koller, O., Ney, H., Bowden, R.: Deep hand: How to train a cnn on 1 million hand images when your data is continuous and weakly labelled. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3793\u20133802 (2016)","DOI":"10.1109\/CVPR.2016.412"},{"issue":"10","key":"2157_CR5","doi-asserted-by":"publisher","first-page":"2433","DOI":"10.1007\/s00371-020-01955-w","volume":"36","author":"W Zhang","year":"2020","unstructured":"Zhang, W., Lin, Z., Cheng, J., Ma, C., Deng, X., Wang, H.: STA-GCN: two-stream graph convolutional network with spatial-temporal attention for hand gesture recognition. Vis. Comput. 36(10), 2433\u20132444 (2020)","journal-title":"Vis. Comput."},{"issue":"4","key":"2157_CR6","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1016\/j.jnca.2006.09.007","volume":"30","author":"H Gunes","year":"2007","unstructured":"Gunes, H., Piccardi, M.: Bi-modal emotion recognition from expressive face and body gestures. J. Netw. Comput. Appl. 30(4), 1334\u20131345 (2007)","journal-title":"J. Netw. Comput. Appl."},{"key":"2157_CR7","doi-asserted-by":"crossref","unstructured":"Do, N.H., Yanai, K.: Hand detection and tracking in videos for fine-grained action recognition. In: Proceedings of Asian Conference on Computer Vision, pp. 19\u201334. Springer (2014)","DOI":"10.1007\/978-3-319-16628-5_2"},{"issue":"10","key":"2157_CR8","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.1007\/s00371-013-0894-1","volume":"30","author":"Z Ma","year":"2014","unstructured":"Ma, Z., Wu, E.: Real-time and robust hand tracking with a single depth camera. Vis. Comput. 30(10), 1133\u20131144 (2014)","journal-title":"Vis. Comput."},{"key":"2157_CR9","unstructured":"Shu, X., Zhang, L., Qi, G., Liu, W., Tang, J.: Spatiotemporal co-attention recurrent neural networks for human-skeleton motion prediction. arXiv preprint arXiv:1909.13245 (2019)"},{"key":"2157_CR10","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1016\/j.image.2016.05.019","volume":"47","author":"A Mohanty","year":"2016","unstructured":"Mohanty, A., Vaishnavi, P., Jana, P., Majumdar, A., Ahmed, A., Goswami, T., Sahay, R.R.: Nrityabodha: Towards understanding Indian classical dance using a deep learning approach. Signal Process. Image Commun. 47, 529\u2013548 (2016)","journal-title":"Signal Process. Image Commun."},{"key":"2157_CR11","doi-asserted-by":"crossref","unstructured":"Mittal A.and\u00a0Zisserman, A., Torr, P.H.: Hand detection using multiple proposals. In: Proceedings of British Machine Vision Conference, pp. 1\u201311. BMVA (2011)","DOI":"10.5244\/C.25.75"},{"issue":"3","key":"2157_CR12","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/s11263-012-0560-5","volume":"101","author":"PK Pisharady","year":"2013","unstructured":"Pisharady, P.K., Vadakkepat, P., Loh, A.P.: Attention based detection and recognition of hand postures against complex backgrounds. Int. J. Comput. Vis. 101(3), 403\u2013419 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"2157_CR13","doi-asserted-by":"crossref","unstructured":"Narasimhaswamy, S., Wei, Z., Wang, Y., Zhang, J., Hoai, M.: Contextual attention for hand detection in the wild. arXiv preprint arXiv:1904.04882 (2019)","DOI":"10.1109\/ICCV.2019.00966"},{"key":"2157_CR14","unstructured":"Hoang Ngan\u00a0Le, T., Zheng, Y., Zhu, C., Luu, K., Savvides, M.: Multiple scale Faster-RCNN approach to driver\u2019s cell-phone usage and hands on steering wheel detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 46\u201353 (2016)"},{"key":"2157_CR15","doi-asserted-by":"crossref","unstructured":"Roy, K., Mohanty, A., Sahay, R.R.: Deep learning based hand detection in cluttered environment using skin segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 640\u2013649. IEEE (2017)","DOI":"10.1109\/ICCVW.2017.81"},{"key":"2157_CR16","doi-asserted-by":"publisher","first-page":"1888","DOI":"10.1109\/TIP.2017.2779600","volume":"27","author":"X Deng","year":"2017","unstructured":"Deng, X., Zhang, Y., Yang, S., Tan, P., Chang, L., Yuan, Y., Wang, H.: Joint hand detection and rotation estimation using CNN. IEEE Trans. Image Process. 27, 1888\u20131900 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"2157_CR17","doi-asserted-by":"crossref","unstructured":"Le, T.H.N., Zhu, C., Zheng, Y., Luu, K., Savvides, M.: Robust hand detection in vehicles. In: Proceedings of International Conference on Pattern Recognit., pp. 573\u2013578. IEEE (2016)","DOI":"10.1109\/ICPR.2016.7899695"},{"issue":"6","key":"2157_CR18","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2157_CR19","doi-asserted-by":"crossref","unstructured":"Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Proceedings of European Conference on Computer Vision, pp. 354\u2013370. Springer (2016)","DOI":"10.1007\/978-3-319-46493-0_22"},{"issue":"2","key":"2157_CR20","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola, P., Jones, M.J.: Robust real-time face detection. Int. J. Comput. Vis. 57(2), 137\u2013154 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"2157_CR21","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo P., Loy, C., Tang, X.: Wider face: a face detection benchmark. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5525\u20135533 (2016)","DOI":"10.1109\/CVPR.2016.596"},{"issue":"10","key":"2157_CR22","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 Signal Process. Lett. 23(10), 1499\u20131503 (2016)","journal-title":"IEEE Signal Process. Lett."},{"key":"2157_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: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5325\u20135334 (2015)","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"2157_CR24","doi-asserted-by":"crossref","unstructured":"Qin, H., Yan, J., Li, X., Hu, X.: Joint training of cascaded CNN for face detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3456\u20133465 (2016)","DOI":"10.1109\/CVPR.2016.376"},{"key":"2157_CR25","unstructured":"Ouyang, W., Wang, K., Zhu, X., Wang, X.: Learning chained deep features and classifiers for cascade in object detection. arXiv preprint arXiv:1702.07054 (2017)"},{"issue":"8","key":"2157_CR26","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.: Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1532\u20131545 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2157_CR27","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Proceedings of International Conference on Medical Image Computing and Computer Assisted Intervention, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"4","key":"2157_CR28","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/TMM.2016.2638204","volume":"19","author":"Y Lei","year":"2017","unstructured":"Lei, Y., Yuan, W., Wang, H., Wenhu, Y., Bo, W.: A skin segmentation algorithm based on stacked autoencoders. IEEE Trans. Multimed. 19(4), 740\u2013749 (2017)","journal-title":"IEEE Trans. Multimed."},{"key":"2157_CR29","doi-asserted-by":"crossref","unstructured":"Chakraborty, B.K., Bhuyan, M.: Skin segmentation using possibilistic fuzzy C-means clustering in presence of skin-colored background. In: Proceedings of the IEEE Recent Advances in Intelligent Computational Systems, pp. 246\u2013250 (2015)","DOI":"10.1109\/RAICS.2015.7488422"},{"key":"2157_CR30","doi-asserted-by":"crossref","unstructured":"Hwang, I., Kim, Y., Cho, N.I.: Skin detection based on multi-seed propagation in a multi-layer graph for regional and color consistency. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 1273\u20131277. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952361"},{"key":"2157_CR31","doi-asserted-by":"crossref","unstructured":"Kim, Y., Hwang, I., Cho, N.I.: Convolutional neural networks and training strategies for skin detection. In: Proceedings of IEEE International Conference on Image Processing, pp. 3919\u20133923. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8297017"},{"issue":"4","key":"2157_CR32","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640\u2013651 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1\u20134","key":"2157_CR33","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/0167-2789(92)90242-F","volume":"60","author":"LI Rudin","year":"1992","unstructured":"Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D Nonlinear Phenom. 60(1\u20134), 259\u2013268 (1992)","journal-title":"Physica D Nonlinear Phenom."},{"key":"2157_CR34","doi-asserted-by":"crossref","unstructured":"Le, T.H.N., Quach, K.G., Zhu, C., Duong, C.N., Luu, K., Savvides, M., Center, C.B.: Robust hand detection and classification in vehicles and in the wild. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1203\u20131210. IEEE (2017)","DOI":"10.1109\/CVPRW.2017.159"},{"key":"2157_CR35","doi-asserted-by":"crossref","unstructured":"Oikonomidis, I., Kyriazis, N., Argyros, A.A.: Efficient model-based 3d tracking of hand articulations using kinect. In: Proceedings of British Machine Vision Conference, vol.\u00a01, p.\u00a03. BMVA (2011)","DOI":"10.5244\/C.25.101"},{"key":"2157_CR36","doi-asserted-by":"crossref","unstructured":"Li, C., Kitani, K.M.: Pixel-level hand detection in ego-centric videos. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3570\u20133577 (2013)","DOI":"10.1109\/CVPR.2013.458"},{"key":"2157_CR37","doi-asserted-by":"crossref","unstructured":"Chen, T., Wu, M., Hsieh, Y., Fu, L.: Deep learning for integrated hand detection and pose estimation. In: Proceedings of International Conference on Computer Vision and Pattern Recognition, pp. 615\u2013620. IEEE (2016)","DOI":"10.1109\/ICPR.2016.7899702"},{"key":"2157_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, C., Zheng, Y., Luu, K., Savvides, M.: CMS-RCNN: contextual multi-scale region-based CNN for unconstrained face detection. In: Deep Learning for Biometrics, pp. 57\u201379. Springer (2017)","DOI":"10.1007\/978-3-319-61657-5_3"},{"key":"2157_CR39","doi-asserted-by":"crossref","unstructured":"Chen, C., Liu, M., Tuzel, O., Xiao, J.: R-CNN for small object detection. In: Proceedings of Asian Conference on Computer Vision, pp. 214\u2013230. Springer (2016)","DOI":"10.1007\/978-3-319-54193-8_14"},{"key":"2157_CR40","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Lerer, A., Lin, T., Pinheiro, P.O., Gross, S., Chintala, S., Doll\u00e1r, P.: A multipath network for object detection. arXiv preprint arXiv:1604.02135 (2016)","DOI":"10.5244\/C.30.15"},{"key":"2157_CR41","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Komodakis, N.: Object detection via a multi-region and semantic segmentation-aware CNN model. In: Proceedings of IEEE International Conference on Computer Vision, pp. 1134\u20131142 (2015)","DOI":"10.1109\/ICCV.2015.135"},{"key":"2157_CR42","unstructured":"Vezhnevets, V., Sazonov, V., Andreeva, A.: A survey on pixel-based skin color detection techniques. In: Proceedings of Graphicon, vol.\u00a03, pp. 85\u201392. Moscow, Russia (2003)"},{"key":"2157_CR43","doi-asserted-by":"crossref","unstructured":"Yu, Z., et\u00a0al.: Fast Gaussian mixture clustering for skin detection. In: Proceedings of IEEE International Conference on Image Processing, pp. 2997\u20133000 (2006)","DOI":"10.1109\/ICIP.2006.312967"},{"key":"2157_CR44","doi-asserted-by":"crossref","unstructured":"Kawulok, M.: Fast propagation-based skin regions segmentation in color images. In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, pp. 1\u20137. IEEE (2013)","DOI":"10.1109\/FG.2013.6553733"},{"issue":"1","key":"2157_CR45","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1023\/A:1013200319198","volume":"46","author":"MJ Jones","year":"2002","unstructured":"Jones, M.J., Rehg, J.M.: Statistical color models with application to skin detection. Int. J. Comput. Vis. 46(1), 81\u201396 (2002)","journal-title":"Int. J. Comput. Vis."},{"key":"2157_CR46","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.asoc.2015.04.046","volume":"33","author":"HK Al-Mohair","year":"2015","unstructured":"Al-Mohair, H.K., Saleh, J.M., Suandi, S.A.: Hybrid human skin detection using neural network and k-means clustering technique. Appl. Soft Comput. 33, 337\u2013347 (2015)","journal-title":"Appl. Soft Comput."},{"issue":"3","key":"2157_CR47","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1016\/j.patcog.2006.06.010","volume":"40","author":"P Kakumanu","year":"2007","unstructured":"Kakumanu, P., Makrogiannis, S., Bourbakis, N.: A survey of skin-color modeling and detection methods. Pattern Recognit. 40(3), 1106\u20131122 (2007)","journal-title":"Pattern Recognit."},{"issue":"3","key":"2157_CR48","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1109\/LSP.2017.2654803","volume":"24","author":"H Zuo","year":"2017","unstructured":"Zuo, H., Fan, H., Blasch, E., Ling, H.: Combining convolutional and recurrent neural networks for human skin detection. IEEE Signal Process. Lett. 24(3), 289\u2013293 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"2157_CR49","unstructured":"Kim, Y., Hwang, I., Cho, N.I.: A new convolutional network-in-network structure and its applications in skin detection, semantic segmentation, and artifact reduction. arXiv preprint arXiv:1701.06190 (2017)"},{"issue":"4","key":"2157_CR50","first-page":"905","volume":"40","author":"J Tang","year":"2017","unstructured":"Tang, J., Li, Z., Lai, H., Zhang, L., Yan, S., et al.: Personalized age progression with bi-level aging dictionary learning. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 905\u2013917 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2157_CR51","doi-asserted-by":"crossref","unstructured":"Das, N., Ohn-Bar, E., Trivedi, M.M.: On performance evaluation of driver hand detection algorithms: Challenges, dataset, and metrics. In: Proceedings of International IEEE Conference on Intelligent Transportation Systems, pp. 2953\u20132958. IEEE (2015)","DOI":"10.1109\/ITSC.2015.473"},{"key":"2157_CR52","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. arXiv preprint arXiv:1612.03144 (2016)","DOI":"10.1109\/CVPR.2017.106"},{"key":"2157_CR53","doi-asserted-by":"crossref","unstructured":"Sun, X., Wu, P., Hoi, S.C.: Face detection using deep learning: an improved faster RCNN approach. arXiv preprint arXiv:1701.08289 (2017)","DOI":"10.1016\/j.neucom.2018.03.030"},{"key":"2157_CR54","volume-title":"Learning multiple layers of features from tiny images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)"},{"key":"2157_CR55","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"2157_CR56","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"2157_CR57","doi-asserted-by":"crossref","unstructured":"Ohn-Bar, E., Trivedi, M.M.: In-vehicle hand localization using integration of regions. In: Proceedings of IEEE Intelligent Vehicle Symposium, pp. 1034\u20131039 (2013)","DOI":"10.1109\/IVS.2013.6629602"},{"key":"2157_CR58","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Chen, X., Liu, X., Cho, N., Lee, S., Fidler, S., Urtasun, R., Yuille, A.: The role of context for object detection and semantic segmentation in the wild. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 891\u2013898 (2014)","DOI":"10.1109\/CVPR.2014.119"},{"issue":"10","key":"2157_CR59","doi-asserted-by":"publisher","first-page":"1978","DOI":"10.1109\/TPAMI.2011.276","volume":"34","author":"D Parikh","year":"2012","unstructured":"Parikh, D., Zitnick, C.L., Chen, T.: Exploring tiny images: The roles of appearance and contextual information for machine and human object recognition. IEEE Trans. Pattern Anal. Mach. Intell. 34(10), 1978\u20131991 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"2157_CR60","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, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"2157_CR61","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: Proceedings of International Conference on Learning Representations (2015)"},{"key":"2157_CR62","doi-asserted-by":"crossref","unstructured":"Wang, T., Sun, M., Hu, K.: Dilated deep residual network for image denoising. In: Proceedings of Int. Conf. Tools Artif. Intell., pp. 1272\u20131279. IEEE (2017)","DOI":"10.1109\/ICTAI.2017.00192"},{"key":"2157_CR63","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"2157_CR64","unstructured":"Luc, P., Couprie, C., Chintala, S., Verbeek, J.: Semantic segmentation using adversarial networks. arXiv preprint arXiv:1611.08408 (2016)"},{"issue":"3\u20134","key":"2157_CR65","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/s12021-018-9377-x","volume":"16","author":"Y Xue","year":"2018","unstructured":"Xue, Y., Xu, T., Zhang, H., Long, L.R., Huang, X.: Segan: adversarial network with multi-scale l1 loss for medical image segmentation. Neuroinformatics 16(3\u20134), 383\u2013392 (2018)","journal-title":"Neuroinformatics"},{"key":"2157_CR66","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5967\u20135976. IEEE (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"2157_CR67","doi-asserted-by":"crossref","unstructured":"Ohn-Bar, E., Trivedi, M.M.: The power is in your hands: 3D analysis of hand gestures in naturalistic video. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 912\u2013917 (2013)","DOI":"10.1109\/CVPRW.2013.134"},{"key":"2157_CR68","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.html (2007)"},{"key":"2157_CR69","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html (2012)"},{"key":"2157_CR70","doi-asserted-by":"crossref","unstructured":"Yao, B., Jiang, X., Khosla, A., Lin, A.L., Guibas, L., Fei-Fei, L.: Human action recognition by learning bases of action attributes and parts. In: Proceedings of International Conference on Computer Vision, pp. 1331\u20131338. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"2157_CR71","doi-asserted-by":"crossref","unstructured":"Shan, D., Geng, J., Shu, M., Fouhey, D.F.: Understanding human hands in contact at internet scale. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 9869\u20139878 (2020)","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"2157_CR72","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2157_CR73","unstructured":"Lab, S.H.: SCUT HCII Lab. http:\/\/cvrr.ucsd.edu\/vivachallenge\/index.php\/hands\/hand-detection\/#cite2\/ (2008). Accessed 19 July 2008"},{"key":"2157_CR74","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Wu, C., Cheng, K., Wu, Y.: An adaptive skin model and its application to objectionable image filtering. In: Proceedings of ACM Multimedia, pp. 56\u201363. ACM (2004)","DOI":"10.1145\/1027527.1027538"},{"key":"2157_CR75","unstructured":"Ruiz-del Solar, J., Verschae, R.: Skin detection using neighborhood information. In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, pp. 463\u2013468. IEEE (2004)"},{"issue":"1","key":"2157_CR76","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1109\/TII.2011.2172451","volume":"8","author":"WR Tan","year":"2012","unstructured":"Tan, W.R., Chan, C.S., Yogarajah, P., Condell, J.: A fusion approach for efficient human skin detection. IEEE Trans. Ind. Inform. 8(1), 138\u2013147 (2012)","journal-title":"IEEE Trans. Ind. Inform."},{"key":"2157_CR77","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.patrec.2013.08.028","volume":"41","author":"M Kawulok","year":"2014","unstructured":"Kawulok, M., Kawulok, J., Nalepa, J.: Spatial-based skin detection using discriminative skin-presence features. Pattern Recognit. Lett. 41, 3\u201313 (2014)","journal-title":"Pattern Recognit. Lett."},{"key":"2157_CR78","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02157-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-021-02157-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02157-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T09:09:13Z","timestamp":1658221753000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-021-02157-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,18]]},"references-count":78,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["2157"],"URL":"https:\/\/doi.org\/10.1007\/s00371-021-02157-8","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,18]]},"assertion":[{"value":"27 April 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}