{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T05:21:25Z","timestamp":1779340885992,"version":"3.51.4"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T00:00:00Z","timestamp":1719446400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T00:00:00Z","timestamp":1719446400000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s00138-024-01565-9","type":"journal-article","created":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T14:14:08Z","timestamp":1719497648000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A multi-modal framework for continuous and isolated hand gesture recognition utilizing movement epenthesis detection"],"prefix":"10.1007","volume":"35","author":[{"given":"Navneet","family":"Nayan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Debashis","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pyari Mohan","family":"Pradhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,27]]},"reference":[{"key":"1565_CR1","doi-asserted-by":"crossref","unstructured":"Abavisani, M., Joze, H.R.V., Patel, V.M.: Improving the performance of unimodal dynamic hand-gesture recognition with multimodal training. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1165\u20131174 (2019)","DOI":"10.1109\/CVPR.2019.00126"},{"key":"1565_CR2","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.imavis.2017.02.003","volume":"61","author":"S Belgacem","year":"2017","unstructured":"Belgacem, S., Chatelain, C., Paquet, T.: Gesture sequence recognition with one shot learned crf\/hmm hybrid model. Image Vis. Comput. 61, 12\u201321 (2017)","journal-title":"Image Vis. Comput."},{"key":"1565_CR3","doi-asserted-by":"crossref","unstructured":"Benitez-Garcia, G., Olivares-Mercado, J., Sanchez-Perez, G., et\u00a0al.: IPN Hand: a video dataset and benchmark for real-time continuous hand gesture recognition. In: 2020 25th International Conference on Pattern Recognition, pp. 4340\u20134347 (2021)","DOI":"10.1109\/ICPR48806.2021.9412317"},{"key":"1565_CR4","doi-asserted-by":"crossref","unstructured":"Camgoz, N.C., Hadfield, S., Koller, O., et\u00a0al.: Using convolutional 3D neural networks for user-independent continuous gesture recognition. In: 2016 23rd International Conference on Pattern Recognition, pp. 49\u201354 (2016)","DOI":"10.1109\/ICPR.2016.7899606"},{"key":"1565_CR5","doi-asserted-by":"crossref","unstructured":"Camgoz, N.C., Hadfield, S., Bowden, R.: Particle filter based probabilistic forced alignment for continuous gesture recognition. In: 2017 IEEE International Conference on Computer Vision Workshops, pp. 3079\u20133085 (2017)","DOI":"10.1109\/ICCVW.2017.364"},{"key":"1565_CR6","doi-asserted-by":"crossref","unstructured":"Chai, X., Liu, Z., Yin, F., et\u00a0al.: Two streams recurrent neural networks for large-scale continuous gesture recognition. In: 2016 23rd International Conference on Pattern Recognition, pp. 31\u201336 (2016)","DOI":"10.1109\/ICPR.2016.7899603"},{"issue":"3","key":"1565_CR7","first-page":"471","volume":"26","author":"A Choudhury","year":"2017","unstructured":"Choudhury, A., Talukdar, A.K., Bhuyan, M.K., et al.: Movement epenthesis detection for continuous sign language recognition. J. Intell. Syst. 26(3), 471\u2013481 (2017)","journal-title":"J. Intell. Syst."},{"issue":"1","key":"1565_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3131343","volume":"14","author":"J Duan","year":"2018","unstructured":"Duan, J., Wan, J., Zhou, S., et al.: A unified framework for multi-modal isolated gesture recognition. ACM Trans. Multimed. Comput. Commun. Appl. 14(1), 1\u201316 (2018)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"1565_CR9","doi-asserted-by":"publisher","first-page":"7689","DOI":"10.1109\/TIP.2021.3108349","volume":"30","author":"H Gammulle","year":"2021","unstructured":"Gammulle, H., Denman, S., Sridharan, S., et al.: TMMF: Temporal multi-modal fusion for single-stage continuous gesture recognition. IEEE Trans. Image Process. 30, 7689\u20137701 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"1565_CR10","doi-asserted-by":"crossref","unstructured":"Gao, W., Fang, G., Zhao, D., et\u00a0al.: Transition movement models for large vocabulary continuous sign language recognition. In: Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 553\u2013558 (2004)","DOI":"10.1109\/AFGR.2004.1301591"},{"key":"1565_CR11","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1007\/s00138-014-0596-3","volume":"25","author":"I Guyon","year":"2014","unstructured":"Guyon, I., Athitsos, V., Jangyodsuk, P., et al.: The ChaLearn gesture dataset (CGD 2011). Mach. Vis. Appl. 25, 1929\u20131951 (2014)","journal-title":"Mach. Vis. Appl."},{"key":"1565_CR12","doi-asserted-by":"crossref","unstructured":"Hu, T.K., Lin, Y.Y., Hsiu, P.C.: Learning adaptive hidden layers for mobile gesture recognition. Proceedings of the AAAI Conference on Artificial Intelligence pp. 32(1) (2018)","DOI":"10.1609\/aaai.v32i1.12279"},{"key":"1565_CR13","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., et\u00a0al.: Caffe: Convolutional architecture for fast feature embedding. Proceedings of the 2014 ACM Conference on Multimedia pp. 675\u2013678 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"1565_CR14","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.imavis.2016.06.001","volume":"58","author":"A Joshi","year":"2017","unstructured":"Joshi, A., Monnier, C., Betke, M., et al.: Comparing random forest approaches to segmenting and classifying gestures. Image Vis. Comput. 58, 86\u201395 (2017)","journal-title":"Image Vis. Comput."},{"key":"1565_CR15","doi-asserted-by":"crossref","unstructured":"Kelly, D., Mc Donald, J., Markham, C.: Continuous recognition of motion based gestures in sign language. In: 2009 IEEE 12th International Conference on Computer Vision Workshops, pp. 1073\u20131080 (2009)","DOI":"10.1109\/ICCVW.2009.5457585"},{"key":"1565_CR16","doi-asserted-by":"crossref","unstructured":"Kelly, D., McDonald, J., Markham, C.: Recognizing spatiotemporal gestures and movement epenthesis in sign language. In: 2009 13th International Machine Vision and Image Processing Conference, pp. 145\u2013150 (2009)","DOI":"10.1109\/IMVIP.2009.33"},{"key":"1565_CR17","doi-asserted-by":"crossref","unstructured":"K\u00f6p\u00fckl\u00fc, O., Gunduz, A., Kose, N., et\u00a0al.: Real-time hand gesture detection and classification using convolutional neural networks. In: 2019 14th IEEE International Conference on Automatic Face and Gesture Recognition, pp. 1\u20138 (2019)","DOI":"10.1109\/FG.2019.8756576"},{"issue":"10","key":"1565_CR18","doi-asserted-by":"publisher","first-page":"2956","DOI":"10.1109\/TCSVT.2017.2749509","volume":"28","author":"Y Li","year":"2018","unstructured":"Li, Y., Miao, Q., Tian, K., et al.: Large-scale gesture recognition with a fusion of RGB-D data based on saliency theory and C3D model. IEEE Trans. Circuits Syst. Video Technol. 28(10), 2956\u20132964 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"5","key":"1565_CR19","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1007\/s00138-018-0996-x","volume":"30","author":"Y Li","year":"2019","unstructured":"Li, Y., Miao, Q., Qi, X., et al.: A spatiotemporal attention-based ResC3D model for large-scale gesture recognition. Mach. Vis. Appl. 30(5), 875\u2013888 (2019)","journal-title":"Mach. Vis. Appl."},{"key":"1565_CR20","doi-asserted-by":"crossref","unstructured":"Lin, C., Wan, J., Liang, Y., et\u00a0al.: Large-scale isolated gesture recognition using a refined fused model based on masked Res-C3D network and skeleton LSTM. In: 2018 13th IEEE International Conference on Automatic Face and Gesture Recognition, pp. 52\u201358 (2018)","DOI":"10.1109\/FG.2018.00018"},{"key":"1565_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Chai, X., Liu, Z., et\u00a0al.: Continuous gesture recognition with hand-oriented spatiotemporal feature. In: 2017 IEEE International Conference on Computer Vision Workshops, pp. 3056\u20133064 (2017)","DOI":"10.1109\/ICCVW.2017.361"},{"key":"1565_CR22","doi-asserted-by":"publisher","first-page":"19626","DOI":"10.1109\/ACCESS.2018.2813079","volume":"6","author":"M Mohandes","year":"2018","unstructured":"Mohandes, M., Deriche, M., Aliyu, S.O.: Classifiers combination techniques: a comprehensive review. IEEE Access 6, 19626\u201319639 (2018)","journal-title":"IEEE Access"},{"key":"1565_CR23","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Yang, X., Gupta, S., et\u00a0al.: Online detection and classification of dynamic hand gestures with recurrent 3D convolutional neural networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 4207\u20134215 (2016)","DOI":"10.1109\/CVPR.2016.456"},{"key":"1565_CR24","doi-asserted-by":"crossref","unstructured":"Narayana, P., Beveridge, J.R., Draper, B.A.: Gesture recognition: focus on the hands. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5235\u20135244 (2018)","DOI":"10.1109\/CVPR.2018.00549"},{"key":"1565_CR25","doi-asserted-by":"crossref","unstructured":"Nayan, N., Ghosh, D., Pradhan, P.M.: An optical flow based approach to detect movement epenthesis in continuous fingerspelling of sign language. In: 2021 National Conference on Communications, pp. 1\u20135 (2021)","DOI":"10.1109\/NCC52529.2021.9530076"},{"key":"1565_CR26","doi-asserted-by":"crossref","unstructured":"Nayan, N., Ghosh, D., Pradhan, P.M.: A cnn bi-lstm based multimodal continuous hand gesture recognition. In: 2022 IEEE India Council International Subsections Conference (INDISCON), pp. 1\u20134 (2022)","DOI":"10.1109\/INDISCON54605.2022.9862878"},{"key":"1565_CR27","first-page":"862","volume-title":"2022 17th International Conference on Control","author":"N Nayan","year":"2022","unstructured":"Nayan, N., Ghosh, D., Pradhan, P.M.: An unsupervised learning approach to handle movement epenthesis in continuous sign language recognition. In: 2022 17th International Conference on Control, pp. 862\u2013867. Automation, Robotics and Vision (ICARCV) (2022)"},{"key":"1565_CR28","doi-asserted-by":"crossref","unstructured":"Ni, B., Wang, G., Moulin, P.: RGBD-HuDaAct: a color-depth video database for human daily activity recognition. In: 2011 IEEE International Conference on Computer Vision Workshops, pp. 1147\u20131153 (2011)","DOI":"10.1109\/ICCVW.2011.6130379"},{"key":"1565_CR29","doi-asserted-by":"crossref","unstructured":"Pigou, L., Van Herreweghe, M., Dambre, J.: Gesture and sign language recognition with temporal residual networks. In: 2017 IEEE International Conference on Computer Vision Workshops, pp. 3086\u20133093 (2017)","DOI":"10.1109\/ICCVW.2017.365"},{"issue":"3","key":"1565_CR30","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/j.imavis.2011.11.003","volume":"30","author":"X Shen","year":"2012","unstructured":"Shen, X., Hua, G., Williams, L., et al.: Dynamic hand gesture recognition: an exemplar-based approach from motion divergence fields. Image Vis. Comput. 30(3), 227\u2013235 (2012)","journal-title":"Image Vis. Comput."},{"issue":"8","key":"1565_CR31","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1016\/j.imavis.2014.04.015","volume":"32","author":"X Suau","year":"2014","unstructured":"Suau, X., Alcoverro, M., L\u00f3pez-M\u00e9ndez, A., et al.: Real-time fingertip localization conditioned on hand gesture classification. Image Vis. Comput. 32(8), 522\u2013532 (2014)","journal-title":"Image Vis. Comput."},{"key":"1565_CR32","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., et\u00a0al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1565_CR33","doi-asserted-by":"crossref","unstructured":"Talukdar, A.K., Bhuyan, M.K.: Movement epenthesis detection in continuous fingerspelling from a coarsely sampled motion vector field in h.264\/avc video. In: 2018 IEEE Recent Advances in Intelligent Computational Systems, pp. 26\u201330 (2018)","DOI":"10.1109\/RAICS.2018.8634902"},{"issue":"8","key":"1565_CR34","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1016\/j.imavis.2014.04.012","volume":"32","author":"S Theodorakis","year":"2014","unstructured":"Theodorakis, S., Pitsikalis, V., Maragos, P.: Dynamic-static unsupervised sequentiality, statistical subunits and lexicon for sign language recognition. Image Vis. Comput. 32(8), 533\u2013549 (2014)","journal-title":"Image Vis. Comput."},{"key":"1565_CR35","doi-asserted-by":"crossref","unstructured":"Vogler, C., Metaxas, D.: ASL recognition based on a coupling between HMMs and 3D motion analysis. In: Sixth International Conference on Computer Vision, pp. 363\u2013369 (1998)","DOI":"10.1109\/ICCV.1998.710744"},{"issue":"3","key":"1565_CR36","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1006\/cviu.2000.0895","volume":"81","author":"C Vogler","year":"2001","unstructured":"Vogler, C., Metaxas, D.: A framework for recognizing the simultaneous aspects of American sign language. Comput. Vis. Image Underst. 81(3), 358\u2013384 (2001)","journal-title":"Comput. Vis. Image Underst."},{"issue":"8","key":"1565_CR37","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.1109\/TPAMI.2015.2513479","volume":"38","author":"J Wan","year":"2016","unstructured":"Wan, J., Guo, G., Li, S.Z.: Explore efficient local features from RGB-D data for one-shot learning gesture recognition. IEEE Trans. Pattern Anal. Mach. Intell. 38(8), 1626\u20131639 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1565_CR38","doi-asserted-by":"crossref","unstructured":"Wan, J., Li, S.Z., Zhao, Y., et\u00a0al.: Chalearn looking at people RGB-D isolated and continuous datasets for gesture recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 761\u2013769 (2016)","DOI":"10.1109\/CVPRW.2016.100"},{"issue":"5","key":"1565_CR39","doi-asserted-by":"publisher","first-page":"3422","DOI":"10.1109\/TCYB.2020.3012092","volume":"52","author":"J Wan","year":"2022","unstructured":"Wan, J., Lin, C., Wen, L., et al.: Chalearn looking at people: IsoGD and ConGD large-scale RGB-D gesture recognition. IEEE Trans. Cybern. 52(5), 3422\u20133433 (2022)","journal-title":"IEEE Trans. Cybern."},{"key":"1565_CR40","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, P., Song, Z., et\u00a0al.: Large-scale multimodal gesture recognition using heterogeneous networks. In: 2017 IEEE International Conference on Computer Vision Workshops, pp. 3129\u20133137 (2017)","DOI":"10.1109\/ICCVW.2017.370"},{"key":"1565_CR41","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, P., Song, Z., et\u00a0al.: Large-scale multimodal gesture segmentation and recognition based on convolutional neural networks. In: 2017 IEEE International Conference on Computer Vision Workshops, pp. 3138\u20133146 (2017)","DOI":"10.1109\/ICCVW.2017.371"},{"key":"1565_CR42","doi-asserted-by":"crossref","unstructured":"Wang, P., Li, W., Liu, S., et\u00a0al.: Large-scale isolated gesture recognition using convolutional neural networks. In: 2016 23rd International Conference on Pattern Recognition, pp. 7\u201312 (2016)","DOI":"10.1109\/ICPR.2016.7899599"},{"key":"1565_CR43","doi-asserted-by":"crossref","unstructured":"Wang, P., Li, W., Liu, S., et\u00a0al.: Large-scale continuous gesture recognition using convolutional neural networks. In: 2016 23rd International Conference on Pattern Recognition, pp. 13\u201318 (2016)","DOI":"10.1109\/ICPR.2016.7899600"},{"issue":"5","key":"1565_CR44","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1109\/TMM.2018.2818329","volume":"20","author":"P Wang","year":"2018","unstructured":"Wang, P., Li, W., Gao, Z., et al.: Depth pooling based large-scale 3-D action recognition with convolutional neural networks. IEEE Trans. Multimed. 20(5), 1051\u20131061 (2018)","journal-title":"IEEE Trans. Multimed."},{"key":"1565_CR45","doi-asserted-by":"crossref","unstructured":"Wang, P., Li, W., Wan, J., et\u00a0al.: Cooperative training of deep aggregation networks for RGB-D action recognition. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, pp. 1\u20138 (2018)","DOI":"10.1609\/aaai.v32i1.12228"},{"key":"1565_CR46","doi-asserted-by":"crossref","unstructured":"Yang, R., Sarkar, S., Loeding, B.: Enhanced level building algorithm for the movement epenthesis problem in sign language recognition. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383347"},{"issue":"3","key":"1565_CR47","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1109\/TPAMI.2009.26","volume":"32","author":"R Yang","year":"2010","unstructured":"Yang, R., Sarkar, S., Loeding, B.: Handling movement epenthesis and hand segmentation ambiguities in continuous sign language recognition using nested dynamic programming. IEEE Trans. Pattern Anal. Mach. Intell. 32(3), 462\u2013477 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1565_CR48","unstructured":"Yuan, Q., Geo, W., Yao, H., et\u00a0al.: Recognition of strong and weak connection models in continuous sign language. In: 2002 International Conference on Pattern Recognition, pp. 75\u201378 (2002)"},{"key":"1565_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhu, G., Shen, P., et\u00a0al.: Learning spatiotemporal features using 3DCNN and convolutional LSTM for gesture recognition. In: 2017 IEEE International Conference on Computer Vision Workshops, pp. 3120\u20133128 (2017)","DOI":"10.1109\/ICCVW.2017.369"},{"key":"1565_CR50","doi-asserted-by":"crossref","unstructured":"Zhu, G., Zhang, L., Mei, L., et\u00a0al.: Large-scale isolated gesture recognition using pyramidal 3D convolutional networks. In: 2016 23rd International Conference on Pattern Recognition, pp. 19\u201324 (2016)","DOI":"10.1109\/ICPR.2016.7899601"},{"key":"1565_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, G., Zhang, L., Shen, P., et al.: Continuous gesture segmentation and recognition using 3DCNN and convolutional LSTM. IEEE Trans. Multimed. 21(4), 1011\u20131021 (2019)","DOI":"10.1109\/TMM.2018.2869278"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01565-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-024-01565-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01565-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T22:17:16Z","timestamp":1732313836000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-024-01565-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,27]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["1565"],"URL":"https:\/\/doi.org\/10.1007\/s00138-024-01565-9","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,27]]},"assertion":[{"value":"7 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 June 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"86"}}