{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:21:01Z","timestamp":1742941261587,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030496944"},{"type":"electronic","value":"9783030496951"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-49695-1_11","type":"book-chapter","created":{"date-parts":[[2020,7,10]],"date-time":"2020-07-10T00:25:10Z","timestamp":1594340710000},"page":"152-170","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Arms and Hands Segmentation for Egocentric Perspective Based on PSPNet and Deeplab"],"prefix":"10.1007","author":[{"given":"Heverton","family":"Sarah","sequence":"first","affiliation":[]},{"given":"Esteban","family":"Clua","sequence":"additional","affiliation":[]},{"given":"Cristina Nader","family":"Vasconcelos","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,7,10]]},"reference":[{"key":"11_CR1","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. CoRR abs\/1603.04467 (2016). http:\/\/arxiv.org\/abs\/1603.04467"},{"key":"11_CR2","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. arXiv:1511.00561 [cs], November 2015"},{"issue":"5","key":"11_CR3","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1109\/TCSVT.2015.2409731","volume":"25","author":"A Betancourt","year":"2015","unstructured":"Betancourt, A., Morerio, P., Regazzoni, C.S., Rauterberg, M.: The evolution of first person vision methods: a survey. IEEE Trans. Circuits Syst. Video Technol. 25(5), 744\u2013760 (2015). https:\/\/doi.org\/10.1109\/TCSVT.2015.2409731","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"11_CR4","doi-asserted-by":"publisher","unstructured":"Boughorbel, S., Jarray, F., El-Anbari, M.: Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric. PLoS ONE 12(6), e0177678 (2017). https:\/\/doi.org\/10.1371\/journal.pone.0177678. https:\/\/journals.plos.org\/plosone\/article?id=10.1371\/journal.pone.0177678","DOI":"10.1371\/journal.pone.0177678"},{"key":"11_CR5","unstructured":"Casati, J.P.B., Moraes, D.R., Rodrigues, E.L.L.: SFA: a human skin image database based on FERET and AR facial images. In: Anais do VIII Workshop de Vis\u00e3o Computacional. Rio de Janeiro (2013). http:\/\/www.sel.eesc.usp.br\/sfa\/"},{"key":"11_CR6","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv:1412.7062 [cs], December 2014"},{"key":"11_CR7","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. arXiv:1606.00915 [cs], June 2016"},{"key":"11_CR8","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587 [cs], June 2017"},{"key":"11_CR9","unstructured":"Chen, L., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. CoRR abs\/1802.02611 (2018). http:\/\/arxiv.org\/abs\/1802.02611"},{"key":"11_CR10","doi-asserted-by":"publisher","unstructured":"Chinchor, N.: MUC-4 evaluation metrics. In: Proceedings of the 4th Conference on Message Understanding, MUC4 1992, pp. 22\u201329. Association for Computational Linguistics, Stroudsburg (1992). https:\/\/doi.org\/10.3115\/1072064.1072067","DOI":"10.3115\/1072064.1072067"},{"key":"11_CR11","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. CoRR abs\/1610.02357 (2016). http:\/\/arxiv.org\/abs\/1610.02357"},{"key":"11_CR12","unstructured":"Dai, J., et al.: Deformable convolutional networks. CoRR abs\/1703.06211 (2017). http:\/\/arxiv.org\/abs\/1703.06211"},{"issue":"4","key":"11_CR13","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","volume":"34","author":"P Dollar","year":"2012","unstructured":"Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 743\u2013761 (2012). https:\/\/doi.org\/10.1109\/TPAMI.2011.155","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR14","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2012 (VOC2012) results (2012)"},{"key":"11_CR15","doi-asserted-by":"publisher","unstructured":"Fathi, A., Ren, X., Rehg, J.M.: Learning to recognize objects in egocentric activities. In: CVPR 2011, pp. 3281\u20133288 (2011). https:\/\/doi.org\/10.1109\/CVPR.2011.5995444","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V., Garcia-Rodriguez, J.: A review on deep learning techniques applied to semantic segmentation. arXiv:1704.06857 [cs], April 2017","DOI":"10.1016\/j.asoc.2018.05.018"},{"key":"11_CR17","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1007\/978-3-642-04962-0_53","volume-title":"Computational Intelligence and Intelligent Systems","author":"Q Gu","year":"2009","unstructured":"Gu, Q., Zhu, L., Cai, Z.: Evaluation measures of the classification performance of imbalanced data sets. In: Cai, Z., Li, Z., Kang, Z., Liu, Y. (eds.) ISICA 2009. CCIS, vol. 51, pp. 461\u2013471. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-04962-0_53"},{"issue":"2","key":"11_CR18","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s11263-014-0777-6","volume":"112","author":"S Gupta","year":"2015","unstructured":"Gupta, S., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Indoor scene understanding with RGB-D images: bottom-up segmentation, object detection and semantic segmentation. Int. J. Comput. Vis. 112(2), 133\u2013149 (2015). https:\/\/doi.org\/10.1007\/s11263-014-0777-6","journal-title":"Int. J. Comput. Vis."},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv:1512.03385 [cs], December 2015","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR20","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 [cs], April 2017"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Jia, Y.,et al.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"11_CR22","unstructured":"Koyejo, O.O., Natarajan, N., Ravikumar, P.K., Dhillon, I.S.: Consistent binary classification with generalized performance metrics. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 27, pp. 2744\u20132752. Curran Associates, Inc. (2014). http:\/\/papers.nips.cc\/paper\/5454-consistent-binary-classification-with-generalized-performance-metrics.pdf"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Li, C., Kitani, K.M.: Pixel-level hand detection in ego-centric videos, pp. 3570\u20133577 (2013)","DOI":"10.1109\/CVPR.2013.458"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. arXiv:1411.4038 [cs], November 2014","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"11_CR25","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. CoRR abs\/1411.4038 (2014). http:\/\/arxiv.org\/abs\/1411.4038"},{"key":"11_CR26","doi-asserted-by":"publisher","unstructured":"Matthews, B.W.: Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochimica et Biophysica Acta (BBA) - Protein Structure 405(2), 442\u2013451 (1975). https:\/\/doi.org\/10.1016\/0005-2795(75)90109-9. http:\/\/www.sciencedirect.com\/science\/article\/pii\/0005279575901099","DOI":"10.1016\/0005-2795(75)90109-9"},{"key":"11_CR27","doi-asserted-by":"publisher","unstructured":"Maurya, J., Hebbalaguppe, R., Gupta, P.: Real time hand segmentation on frugal headmounted device for gestural interface. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 4023\u20134027 (2018). https:\/\/doi.org\/10.1109\/ICIP.2018.8451213","DOI":"10.1109\/ICIP.2018.8451213"},{"key":"11_CR28","unstructured":"Menon, A., Narasimhan, H., Agarwal, S., Chawla, S.: On the statistical consistency of algorithms for binary classification under class imbalance. In: International Conference on Machine Learning, pp. 603\u2013611, February 2013. http:\/\/proceedings.mlr.press\/v28\/menon13a.html"},{"key":"11_CR29","first-page":"320","volume":"173","author":"S Obdr\u017e\u00e1lek","year":"2012","unstructured":"Obdr\u017e\u00e1lek, S., Kurillo, G., Han, J., Abresch, T., Bajcsy, R.: Real-time human pose detection and tracking for tele-rehabilitation in virtual reality. Stud. Health Technol. Inform. 173, 320\u2013324 (2012)","journal-title":"Stud. Health Technol. Inform."},{"key":"11_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/978-3-030-34644-7_6","volume-title":"Entertainment Computing and Serious Games","author":"E de Oliveira","year":"2019","unstructured":"de Oliveira, E., Clua, E.W.G., Vasconcelos, C.N., Marques, B.A.D., Trevisan, D.G., de Castro Salgado, L.C.: FPVRGame: deep learning for hand pose recognition in real-time using low-end HMD. In: van der Spek, E., G\u00f6bel, S., Do, E.Y.-L., Clua, E., Baalsrud Hauge, J. (eds.) ICEC-JCSG 2019. LNCS, vol. 11863, pp. 70\u201384. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-34644-7_6"},{"issue":"1","key":"11_CR31","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/TPAMI.2005.17","volume":"27","author":"SL Phung","year":"2005","unstructured":"Phung, S.L., Bouzerdoum, A., Chai, D.: Skin segmentation using color pixel classification: analysis and comparison. IEEE Trans. Pattern Anal. Mach. Intell. 27(1), 148\u2013154 (2005). https:\/\/doi.org\/10.1109\/TPAMI.2005.17","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR32","doi-asserted-by":"publisher","unstructured":"Qi, X., Liao, R., Jia, J., Fidler, S., Urtasun, R.: 3D graph neural networks for RGBD semantic segmentation. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5209\u20135218, October 2017. https:\/\/doi.org\/10.1109\/ICCV.2017.556, iSSN 2380-7504","DOI":"10.1109\/ICCV.2017.556"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. arXiv:1506.02640 [cs], June 2015","DOI":"10.1109\/CVPR.2016.91"},{"key":"11_CR34","doi-asserted-by":"publisher","unstructured":"Rother, C., Kolmogorov, V., Blake, A.: \u201cGrabCut\u201d: interactive foreground extraction using iterated graph cuts. In: ACM SIGGRAPH 2004 Papers, SIGGRAPH 2004, pp. 309\u2013314. ACM, New York (2004). https:\/\/doi.org\/10.1145\/1186562.1015720","DOI":"10.1145\/1186562.1015720"},{"key":"11_CR35","unstructured":"Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.: Inverted residuals and linear bottlenecks: mobile networks for classification, detection and segmentation. CoRR abs\/1801.04381 (2018). http:\/\/arxiv.org\/abs\/1801.04381"},{"key":"11_CR36","unstructured":"Siddharth, Rangesh, A., Ohn-Bar, E., Trivedi, M.M.: Driver hand localization and grasp analysis: a vision-based real-time approach, February 2018. https:\/\/arxiv.org\/abs\/1802.07854v1"},{"key":"11_CR37","unstructured":"Sifre, L.: Rigid-motion scattering for image classification. Ph.D. thesis, Ecole Polytechnique, CMAP, October 2014"},{"key":"11_CR38","doi-asserted-by":"publisher","unstructured":"Slater, M., Wilbur, S.: A framework for immersive virtual environments (five): Speculations on the role of presence in virtual environments. Presence: Teleoperators and Virtual Environments 6(6), 603\u2013616 (1997). https:\/\/doi.org\/10.1162\/pres.1997.6.6.603, https:\/\/doi.org\/10.1162\/pres.1997.6.6.603","DOI":"10.1162\/pres.1997.6.6.603 10.1162\/pres.1997.6.6.603"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Song, X., Herranz, L., Jiang, S.: Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs. CoRR abs\/1801.06797 (2018). http:\/\/arxiv.org\/abs\/1801.06797","DOI":"10.1609\/aaai.v31i1.11226"},{"issue":"10","key":"11_CR40","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1109\/TPAMI.2009.186","volume":"32","author":"Z Tu","year":"2010","unstructured":"Tu, Z., Bai, X.: Auto-context and its application to high-level vision tasks and 3D brain image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 32(10), 1744\u20131757 (2010). https:\/\/doi.org\/10.1109\/TPAMI.2009.186","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"11_CR41","unstructured":"Vasconcelos, C.N., Clua, E.W.G.: Deep learning - Teoria e Pr\u00e1tica. In: Jornadas de Atualiza\u00e7\u00e3o em Inform\u00e1tica 2017. Sociedade Brasileira de Computa\u00e7\u00e3o - SBC, Porto Alegre\/RS, July 2017"},{"key":"11_CR42","doi-asserted-by":"publisher","unstructured":"Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, vol. 1, pp. I-511\u2013I-518, vol. 1 (2001). https:\/\/doi.org\/10.1109\/CVPR.2001.990517","DOI":"10.1109\/CVPR.2001.990517"},{"issue":"2","key":"11_CR43","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). https:\/\/doi.org\/10.1023\/B:VISI.0000013087.49260.fb","journal-title":"Int. J. Comput. Vis."},{"key":"11_CR44","unstructured":"Vodopivec, T., Lepetit, V., Peer, P.: Fine hand segmentation using convolutional neural networks. arXiv:1608.07454 [cs], August 2016"},{"key":"11_CR45","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122 [cs], November 2015"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. arXiv:1612.01105 [cs], December 2016","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["Lecture Notes in Computer Science","Virtual, Augmented and Mixed Reality. Design and Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-49695-1_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T01:08:49Z","timestamp":1720573729000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-49695-1_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030496944","9783030496951"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-49695-1_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"10 July 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Copenhagen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denmark","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 July 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2020.hci.international\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}