{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T17:16:03Z","timestamp":1794849363560,"version":"4.9.1"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032313966","type":"print"},{"value":"9783032313973","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31397-3_2","type":"book-chapter","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:01:09Z","timestamp":1785826869000},"page":"17-31","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Parameter Efficient American Sign Language Recognition via\u00a0MediaPipe Landmarks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9961-1073","authenticated-orcid":false,"given":"Abhishek Bharadwaj","family":"Varanasi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2653-5092","authenticated-orcid":false,"given":"Manjira","family":"Sinha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4714-6835","authenticated-orcid":false,"given":"Tirthankar","family":"Dasgupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2080-9794","authenticated-orcid":false,"given":"Charudatta","family":"Jadhav","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Boh\u00e1\u010dek, M., Hr\u00faz, M.: Sign pose-based transformer for word-level sign language recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 182\u2013191 (2022)","DOI":"10.1109\/WACVW54805.2022.00024"},{"key":"2_CR2","doi-asserted-by":"publisher","first-page":"1384","DOI":"10.1016\/j.procs.2023.01.117","volume":"218","author":"J Bora","year":"2023","unstructured":"Bora, J., Dehingia, S., Boruah, A., Chetia, A.A., Gogoi, D.: Real-time assamese sign language recognition using mediapipe and deep learning. Procedia Comput. Sci. 218, 1384\u20131393 (2023)","journal-title":"Procedia Comput. Sci."},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Bossen, T.E., M\u00f8gelmose, A., Greer, R.: Can vision-language models understand and interpret dynamic gestures from pedestrians? Pilot datasets and exploration towards instructive nonverbal commands for cooperative autonomous vehicles. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 4779\u20134788 (2025)","DOI":"10.1109\/CVPRW67362.2025.00464"},{"issue":"11","key":"2_CR4","doi-asserted-by":"publisher","first-page":"3247","DOI":"10.1109\/TCSVT.2018.2879913","volume":"29","author":"C Cao","year":"2018","unstructured":"Cao, C., Lan, C., Zhang, Y., Zeng, W., Lu, H., Zhang, Y.: Skeleton-based action recognition with gated convolutional neural networks. IEEE Trans. Circuits Syst. Video Technol. 29(11), 3247\u20133257 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Dasgupta, T.: A framework for the automatic generation of Indian sign language. J. Intell. Syst. (2010)","DOI":"10.1515\/JISYS.2010.19.2.125"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Dasgupta, T., Basu, A.: Prototype machine translation system from text-to-Indian sign language. In: Proceedings of the 13th International Conference on Intelligent User Interfaces, pp. 313\u2013316 (2008)","DOI":"10.1145\/1378773.1378818"},{"key":"2_CR7","doi-asserted-by":"publisher","first-page":"76893","DOI":"10.52202\/075280-3360","volume":"36","author":"A Desai","year":"2023","unstructured":"Desai, A., et al.: Asl citizen: a community-sourced dataset for advancing isolated sign language recognition. Adv. Neural. Inf. Process. Syst. 36, 76893\u201376907 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"57","key":"2_CR8","first-page":"8","volume":"2008","author":"S Diwakar","year":"2008","unstructured":"Diwakar, S., Basu, A.: A multilingual multimedia Indian sign language dictionary tool. IJCNLP 2008(57), 8\u201313 (2008)","journal-title":"IJCNLP"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1110\u20131118 (2015)","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"2_CR10","unstructured":"Golovneva, O., Wang, T., Weston, J., Sukhbaatar, S.: Multi-token attention. arXiv preprint arXiv:2504.00927 (2025)"},{"key":"2_CR11","first-page":"7421","volume":"2582","author":"A Halder","year":"2021","unstructured":"Halder, A., Tayade, A.: Real-time vernacular sign language recognition using mediapipe and machine learning. Journal homepage: www. ijrpr. com ISSN 2582, 7421 (2021)","journal-title":"Journal homepage: www. ijrpr. com ISSN"},{"key":"2_CR12","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":"2_CR13","doi-asserted-by":"crossref","unstructured":"Hosain, A.A., Santhalingam, P.S., Pathak, P., Rangwala, H., Kosecka, J.: Hand pose guided 3d pooling for word-level sign language recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3429\u20133439 (2021)","DOI":"10.1109\/WACV48630.2021.00347"},{"issue":"9","key":"2_CR14","doi-asserted-by":"publisher","first-page":"11221","DOI":"10.1109\/TPAMI.2023.3269220","volume":"45","author":"H Hu","year":"2023","unstructured":"Hu, H., Zhao, W., Zhou, W., Li, H.: Signbert+: hand-model-aware self-supervised pre-training for sign language understanding. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 11221\u201311239 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhao, W., Zhou, W., Wang, Y., Li, H.: Signbert: pre-training of hand-model-aware representation for sign language recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11087\u201311096 (2021)","DOI":"10.1109\/ICCV48922.2021.01090"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhou, W., Li, H.: Hand-model-aware sign language recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1558\u20131566 (2021)","DOI":"10.1609\/aaai.v35i2.16247"},{"key":"2_CR17","unstructured":"Jiang, S., Sun, B., Wang, L., Bai, Y., Li, K., Fu, Y.: Sign language recognition via skeleton-aware multi-model ensemble. arXiv preprint arXiv:2110.06161 (2021)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Sant, G., Moryossef, A., M\u00fcller, M., Sennrich, R., Ebling, S.: Signclip: connecting text and sign language by contrastive learning. arXiv preprint arXiv:2407.01264 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.518"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Jiao, P., Min, Y., Li, Y., Wang, X., Lei, L., Chen, X.: Cosign: exploring co-occurrence signals in skeleton-based continuous sign language recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20676\u201320686 (2023)","DOI":"10.1109\/ICCV51070.2023.01890"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Li, C., Zhong, Q., Xie, D., Pu, S.: Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation. arXiv preprint arXiv:1804.06055 (2018)","DOI":"10.24963\/ijcai.2018\/109"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Li, D., Rodriguez, C., Yu, X., Li, H.: Word-level deep sign language recognition from video: a new large-scale dataset and methods comparison. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1459\u20131469 (2020)","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"2_CR22","doi-asserted-by":"publisher","unstructured":"Lin, K., Wang, X., Zhu, L., Sun, K., Zhang, B., Yang, Y.: Gloss-free end-to-end sign language translation. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 12904\u201312916. Association for Computational Linguistics, Toronto (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.722, https:\/\/aclanthology.org\/2023.acl-long.722\/","DOI":"10.18653\/v1\/2023.acl-long.722"},{"key":"2_CR23","unstructured":"Lugaresi, C., et al.: Mediapipe: a framework for perceiving and processing reality. In: Third Workshop on Computer Vision for AR\/VR at IEEE Computer Vision and Pattern Recognition (CVPR) 2019 (2019)"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Min, Y., Hao, A., Chai, X., Chen, X.: Visual alignment constraint for continuous sign language recognition. In: proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11542\u201311551 (2021)","DOI":"10.1109\/ICCV48922.2021.01134"},{"key":"2_CR25","doi-asserted-by":"publisher","first-page":"19135","DOI":"10.1109\/ACCESS.2023.3247761","volume":"11","author":"N Naz","year":"2023","unstructured":"Naz, N., Sajid, H., Ali, S., Hasan, O., Ehsan, M.K.: Signgraph: an efficient and accurate pose-based graph convolution approach toward sign language recognition. IEEE Access 11, 19135\u201319147 (2023)","journal-title":"IEEE Access"},{"key":"2_CR26","unstructured":"Shrestha, G., Thing, N., Dhakal, P., Dahal, P., Karki, P., Guragai, M.K.: Nepali sign language letter detection and finger spelling using mediapipe and cnn. In: Proceedings of the 15th IOE Graduate Conference, vol. 15, pp. 2350\u20138906 (2024)"},{"key":"2_CR27","unstructured":"Simonyan, K.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"2_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Tunga, A., Nuthalapati, S.V., Wachs, J.: Pose-based sign language recognition using gcn and bert. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 31\u201340 (2021)","DOI":"10.1109\/WACVW52041.2021.00008"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Varanasi, A.B., Sinha, M., Dasgupta, T.: Cross-linguistic phonological similarity analysis in sign languages using hamnosys. In: Proceedings of the Workshop on Sign Language Processing (WSLP), pp. 51\u201366 (2025)","DOI":"10.18653\/v1\/2025.wslp-main.9"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Varanasi, A.B., Sinha, M., Dasgupta, T., Jadhav, C.: Linguistically informed transformers for text to American sign language translation. In: Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024), pp. 50\u201356 (2024)","DOI":"10.18653\/v1\/2024.loresmt-1.5"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Varanasi, A.B., Sinha, M., Dasgupta, T., Jadhav, C.: Real time English speech to British sign language translation for accessible banking. In: Companion Proceedings of the 30th International Conference on Intelligent User Interfaces, pp. 87\u201390 (2025)","DOI":"10.1145\/3708557.3716351"},{"key":"2_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Wong, R., Camgoz, N.C., Bowden, R.: Learnt contrastive concept embeddings for sign recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1945\u20131954 (2023)","DOI":"10.1109\/ICCVW60793.2023.00209"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, Z.: Improved adam optimizer for deep neural networks. In: 2018 IEEE\/ACM 26th International Symposium on Quality of Service (IWQoS), pp.\u00a01\u20132. IEEE (2018)","DOI":"10.1109\/IWQoS.2018.8624183"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Zhao, W., Hu, H., Zhou, W., Shi, J., Li, H.: Best: bert pre-training for sign language recognition with coupling tokenization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 3597\u20133605 (2023)","DOI":"10.1609\/aaai.v37i3.25470"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, B., et al.: Gloss-free sign language translation: Improving from visual-language pretraining. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20871\u201320881 (2023)","DOI":"10.1109\/ICCV51070.2023.01908"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, W., Zhao, W., Hu, H., Li, Z., Li, H.: Scaling up multimodal pre-training for sign language understanding. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3599313"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Zuo, R., Wei, F., Mak, B.: Natural language-assisted sign language recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14890\u201314900 (2023)","DOI":"10.1109\/CVPR52729.2023.01430"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31397-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:01:22Z","timestamp":1785826882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31397-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"ISBN":["9783032313966","9783032313973"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31397-3_2","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-032-31397-3","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"assertion":[{"value":"5 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}