{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T22:01:56Z","timestamp":1781215316575,"version":"3.54.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031937088","type":"print"},{"value":"9783031937095","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T00:00:00Z","timestamp":1754092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T00:00:00Z","timestamp":1754092800000},"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":[[2026]]},"DOI":"10.1007\/978-3-031-93709-5_27","type":"book-chapter","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T09:49:50Z","timestamp":1754041790000},"page":"376-390","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hand Detection in\u00a0the\u00a0Wild Leveraging RetinaNet"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1296-7748","authenticated-orcid":false,"given":"Kankana","family":"Roy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5185-3156","authenticated-orcid":false,"given":"Aparna","family":"Mohanty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0820-0616","authenticated-orcid":false,"given":"Rajiv","family":"Ranjan Sahay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,2]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Bambach, S., Crandall, D.J., Yu, C.: Understanding embodied visual attention in child-parent interaction. In: IEEE Joint International Conference on Development and Learning and Epigenetic Robotics, pp.\u00a01\u20136. IEEE (2013)","DOI":"10.1109\/DevLrn.2013.6652555"},{"key":"27_CR2","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: Proceedings of IEEE International Conference on Computer Vision, pp. 1949\u20131957 (2015)","DOI":"10.1109\/ICCV.2015.226"},{"key":"27_CR3","unstructured":"Bhattacharjee, Y.: A little black box to jog failing memory. The New York Times 1 (2010)"},{"key":"27_CR4","unstructured":"Bouakaz, H., Azzopardi, G., Mart\u00ednez, E.T.: Egocentric camera-based fall detection system using rotation, motion, HOG and LBP. Ph.D. thesis (2020)"},{"issue":"3","key":"27_CR5","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1177\/0278364914555720","volume":"34","author":"IM Bullock","year":"2015","unstructured":"Bullock, I.M., Feix, T., Dollar, A.M.: The Yale human grasping dataset: grasp, object, and task data in household and machine shop environments. Intl. J. Robot. Res. 34(3), 251\u2013255 (2015)","journal-title":"Intl. J. Robot. Res."},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Chen, T., Wu, M., Hsieh, Y., Fu, L.: Deep learning for integrated hand detection and pose estimation. In: International Conference on Pattern Recognition, pp. 615\u2013620. IEEE (2016)","DOI":"10.1109\/ICPR.2016.7899702"},{"key":"27_CR7","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: IEEE International Conference on Intelligent Transportation Systems, pp. 2953\u20132958. IEEE (2015)","DOI":"10.1109\/ITSC.2015.473"},{"issue":"4","key":"27_CR8","doi-asserted-by":"publisher","first-page":"1888","DOI":"10.1109\/TIP.2017.2779600","volume":"27","author":"X Deng","year":"2017","unstructured":"Deng, X., et al.: Joint hand detection and rotation estimation using CNN. IEEE Trans. Image Process. 27(4), 1888\u20131900 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Do, N.H., Yanai, K.: Hand detection and tracking in videos for fine-grained action recognition. In: Asian Conference on Computer Vision, pp. 19\u201334. Springer, Cham (2014)","DOI":"10.1007\/978-3-319-16628-5_2"},{"key":"27_CR10","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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"27_CR11","first-page":"2999","volume":"39","author":"P Goyal","year":"2018","unstructured":"Goyal, P., Kaiming, H.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 39, 2999\u20133007 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR12","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":"27_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR14","doi-asserted-by":"crossref","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 the IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 46\u201353 (2016)","DOI":"10.1109\/CVPRW.2016.13"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Kulon, D., Guler, R.A., Kokkinos, I., Bronstein, M.M., Zafeiriou, S.: Weakly-supervised mesh-convolutional hand reconstruction in the wild. In: CVPR, pp. 4990\u20135000 (2020)","DOI":"10.1109\/CVPR42600.2020.00504"},{"key":"27_CR16","unstructured":"Lab, S.H.: SCUT HCII Lab (2008). http:\/\/cvrr.ucsd.edu\/vivachallenge\/index.php\/hands\/hand-detection\/cite2\/. Accessed 19 July 2008"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Le, T.H.N., Quach, K.G., Zhu, C., Duong, C.N., Luu, K., Savvides, M.: Robust hand detection and classification in vehicles and in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 1203\u20131210. IEEE (2017)","DOI":"10.1109\/CVPRW.2017.159"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Le, T.H.N., Zhu, C., Zheng, Y., Luu, K., Savvides, M.: Robust hand detection in vehicles. In: International Conference on Pattern Recognition, pp. 573\u2013578. IEEE (2016)","DOI":"10.1109\/ICPR.2016.7899695"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Li, C., Kitani, K.M.: Pixel-level hand detection in ego-centric videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3570\u20133577 (2013)","DOI":"10.1109\/CVPR.2013.458"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"27_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107202","volume":"105","author":"D Liu","year":"2020","unstructured":"Liu, D., Zhang, L., Luo, T., Tao, L., Wu, Y.: Towards interpretable and robust hand detection via pixel-wise prediction. Pattern Recogn. 105, 107202 (2020)","journal-title":"Pattern Recogn."},{"key":"27_CR22","unstructured":"Mittal, A., Zisserman, A., Torr, P.H.: Hand detection using multiple proposals. In: British Machine Vision Conference, vol.\u00a02, p.\u00a05 (2011)"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Narasimhaswamy, S., Wei, Z., Wang, Y., Zhang, J., Hoai, M.: Contextual attention for hand detection in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9567\u20139576 (2019)","DOI":"10.1109\/ICCV.2019.00966"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Ohn-Bar, E., Trivedi, M.M.: Beyond just keeping hands on the wheel: towards visual interpretation of driver hand motion patterns. In: IEEE International Conference on Intelligent Transportation Systems, pp. 1245\u20131250. IEEE (2014)","DOI":"10.1109\/ITSC.2014.6957858"},{"key":"27_CR25","unstructured":"Pinheiro, P.O., Collobert, R., Doll\u00e1r, P.: Learning to segment object candidates. In: Advances in Neural Information Processing Systems, pp. 1990\u20131998 (2015)"},{"issue":"6","key":"27_CR26","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","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 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR27","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 the IEEE International Conference on Computer Vision Workshop, pp. 640\u2013649 (2017)","DOI":"10.1109\/ICCVW.2017.81"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Roy, K., Sahay, R.R.: A robust multi-scale deep learning approach for unconstrained hand detection aided by skin segmentation. Vis. Comput. 1\u201325 (2021)","DOI":"10.1007\/s00371-021-02157-8"},{"key":"27_CR29","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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9869\u20139878. IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"27_CR30","unstructured":"Wingfield, N.: Gopro sees opportunity in its amateur daredevils. The New York Times 1 (2014)"},{"key":"27_CR31","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 the IEEE International Conference on Computer Vision, 1331\u20131338. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"27_CR32","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.cviu.2015.07.008","volume":"141","author":"X Zhu","year":"2015","unstructured":"Zhu, X., Jia, X., Wong, K.K.: Structured forests for pixel-level hand detection and hand part labelling. Comput. Vis. Image Under. 141, 95\u2013107 (2015)","journal-title":"Comput. Vis. Image Under."}],"container-title":["Communications in Computer and Information Science","Computer Vision and Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-93709-5_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T21:32:13Z","timestamp":1781213533000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-93709-5_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,2]]},"ISBN":["9783031937088","9783031937095"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-93709-5_27","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,2]]},"assertion":[{"value":"2 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision and Image Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chennai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cvip2024.iiitdm.ac.in\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}