{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:22:11Z","timestamp":1792081331303,"version":"4.4.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250842","type":"print"},{"value":"9783031250859","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25085-9_16","type":"book-chapter","created":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T09:12:42Z","timestamp":1676106762000},"page":"271-287","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Sign Spotting via\u00a0Multi-modal Fusion and\u00a0Testing Time Transferring"],"prefix":"10.1007","author":[{"given":"Hongyu","family":"Fu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingqun","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beibei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lincheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,12]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Baradel, F., Wolf, C., Mille, J.: Human action recognition: pose-based attention draws focus to hands. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 604\u2013613 (2017)","DOI":"10.1109\/ICCVW.2017.77"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Z., Wang, L., Peng, X., Qiao, Y.: Multi-view super vector for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 596\u2013603 (2014)","DOI":"10.1109\/CVPR.2014.83"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"16_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/978-3-030-58586-0_32","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Cheng","year":"2020","unstructured":"Cheng, K., Zhang, Y., Cao, C., Shi, L., Cheng, J., Lu, H.: Decoupling GCN with DropGraph module for skeleton-based action recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 536\u2013553. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_32"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Choutas, V., Weinzaepfel, P., Revaud, J., Schmid, C.: Potion: pose motion representation for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7024\u20137033 (2018)","DOI":"10.1109\/CVPR.2018.00734"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Cihan Camgoz, N., Hadfield, S., Koller, O., Bowden, R.: SubUNets: end-to-end hand shape and continuous sign language recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3056\u20133065 (2017)","DOI":"10.1109\/ICCV.2017.332"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116 (2019)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"16_CR8","unstructured":"Conneau, A., Lample, G.: Cross-lingual language model pretraining. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"16_CR9","first-page":"2205","volume":"13","author":"H Cooper","year":"2012","unstructured":"Cooper, H., Ong, E.J., Pugeault, N., Bowden, R.: Sign language recognition using sub-units. J. Mach. Learn. Res. 13, 2205\u20132231 (2012)","journal-title":"J. Mach. Learn. Res."},{"issue":"11","key":"16_CR10","doi-asserted-by":"publisher","first-page":"3592","DOI":"10.1109\/TIM.2011.2161140","volume":"60","author":"NH Dardas","year":"2011","unstructured":"Dardas, N.H., Georganas, N.D.: Real-time hand gesture detection and recognition using bag-of-features and support vector machine techniques. IEEE Trans. Instrum. Meas. 60(11), 3592\u20133607 (2011)","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"1","key":"16_CR11","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1109\/72.182690","volume":"4","author":"SS Fels","year":"1993","unstructured":"Fels, S.S., Hinton, G.E.: Glove-talk: a neural network interface between a data-glove and a speech synthesizer. IEEE Trans. Neural Netw. 4(1), 2\u20138 (1993)","journal-title":"IEEE Trans. Neural Netw."},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Grobel, K., Assan, M.: Isolated sign language recognition using hidden Markov models. In: 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, vol. 1, pp. 162\u2013167. IEEE (1997)","DOI":"10.1109\/ICSMC.1997.625742"},{"key":"16_CR13","unstructured":"Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Hoffman, J., Gupta, S., Darrell, T.: Learning with side information through modality hallucination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 826\u2013834 (2016)","DOI":"10.1109\/CVPR.2016.96"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Hu, J.F., Zheng, W.S., Pan, J., Lai, J., Zhang, J.: Deep bilinear learning for RGB-D action recognition. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 335\u2013351 (2018)","DOI":"10.1007\/978-3-030-01234-2_21"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Huang, J., Zhou, W., Zhang, Q., Li, H., Li, W.: Video-based sign language recognition without temporal segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11903"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, S., Sun, B., Wang, L., Bai, Y., Li, K., Fu, Y.: Skeleton aware multi-modal sign language recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 3413\u20133423 (2021)","DOI":"10.1109\/CVPRW53098.2021.00380"},{"key":"16_CR18","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":"16_CR19","unstructured":"Li, D., et al.: TSPNet: hierarchical feature learning via temporal semantic pyramid for sign language translation. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12034\u201312045 (2020)"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Li, D., Yu, X., Xu, C., Petersson, L., Li, H.: Transferring cross-domain knowledge for video sign language recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6205\u20136214 (2020)","DOI":"10.1109\/CVPR42600.2020.00624"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Li, D., Yu, X., Xu, C., Petersson, L., Li, H.: Transferring cross-domain knowledge for video sign language recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00624"},{"issue":"14","key":"16_CR22","doi-asserted-by":"publisher","first-page":"19917","DOI":"10.1007\/s11042-019-7263-7","volume":"78","author":"KM Lim","year":"2019","unstructured":"Lim, K.M., Tan, A.W.C., Lee, C.P., Tan, S.C.: Isolated sign language recognition using convolutional neural network hand modelling and hand energy image. Multimed. Tools Appl. 78(14), 19917\u201319944 (2019). https:\/\/doi.org\/10.1007\/s11042-019-7263-7","journal-title":"Multimed. Tools Appl."},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Lin, B., Zhang, S., Yu, X.: Gait recognition via effective global-local feature representation and local temporal aggregation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14648\u201314656 (2021)","DOI":"10.1109\/ICCV48922.2021.01438"},{"key":"16_CR24","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1162\/tacl_a_00343","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu, Y., et al.: Multilingual denoising pre-training for neural machine translation. Trans. Assoc. Comput. Linguist. 8, 726\u2013742 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Mehdi, S.A., Khan, Y.N.: Sign language recognition using sensor gloves. In: Proceedings of the 9th International Conference on Neural Information Processing, ICONIP 2002, vol. 5, pp. 2204\u20132206. IEEE (2002)","DOI":"10.1109\/ICONIP.2002.1201884"},{"key":"16_CR26","unstructured":"Momeni, L., Varol, G., Albanie, S., Afouras, T., Zisserman, A.: Watch, read and lookup: learning to spot signs from multiple supervisors. CoRR abs\/2010.04002 (2020). https:\/\/arxiv.org\/abs\/2010.04002"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Momeni, L., Varol, G., Albanie, S., Afouras, T., Zisserman, A.: Watch, read and lookup: learning to spot signs from multiple supervisors. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69544-6_18"},{"key":"16_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/978-3-030-66096-3_18","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"M Parelli","year":"2020","unstructured":"Parelli, M., Papadimitriou, K., Potamianos, G., Pavlakos, G., Maragos, P.: Exploiting 3D hand pose estimation in deep learning-based sign language recognition from RGB videos. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12536, pp. 249\u2013263. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-66096-3_18"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Rong, Y., Shiratori, T., Joo, H.: FrankMocap: a monocular 3D whole-body pose estimation system via regression and integration. In: IEEE International Conference on Computer Vision Workshops (2021)","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"16_CR30","doi-asserted-by":"publisher","first-page":"9532","DOI":"10.1109\/TIP.2020.3028207","volume":"29","author":"L Shi","year":"2020","unstructured":"Shi, L., Zhang, Y., Cheng, J., Lu, H.: Skeleton-based action recognition with multi-stream adaptive graph convolutional networks. IEEE Trans. Image Process. 29, 9532\u20139545 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Wang, D., Ouyang, W., Li, W., Xu, D.: Dividing and aggregating network for multi-view action recognition. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 451\u2013467 (2018)","DOI":"10.1007\/978-3-030-01240-3_28"},{"issue":"1","key":"16_CR33","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vis. 103(1), 60\u201379 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, L.: Modeling temporal dynamics and spatial configurations of actions using two-stream recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 499\u2013508 (2017)","DOI":"10.1109\/CVPR.2017.387"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Wang, L., Ding, Z., Tao, Z., Liu, Y., Fu, Y.: Generative multi-view human action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6212\u20136221 (2019)","DOI":"10.1109\/ICCV.2019.00631"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Q.: Chinese sign language recognition based on video sequence appearance modeling. In: 2010 5th IEEE Conference on Industrial Electronics and Applications, pp. 1537\u20131542. IEEE (2010)","DOI":"10.1109\/ICIEA.2010.5514688"},{"issue":"6","key":"16_CR38","doi-asserted-by":"publisher","first-page":"2542","DOI":"10.1109\/TIP.2016.2548242","volume":"25","author":"J Zheng","year":"2016","unstructured":"Zheng, J., Jiang, Z., Chellappa, R.: Cross-view action recognition via transferable dictionary learning. IEEE Trans. Image Process. 25(6), 2542\u20132556 (2016)","journal-title":"IEEE Trans. Image Process."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25085-9_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:07:34Z","timestamp":1728864454000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25085-9_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250842","9783031250859"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25085-9_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"12 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}