{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T04:28:56Z","timestamp":1744172936617,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030739720"},{"type":"electronic","value":"9783030739737"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-73973-7_29","type":"book-chapter","created":{"date-parts":[[2021,4,9]],"date-time":"2021-04-09T14:03:24Z","timestamp":1617977004000},"page":"302-312","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multimodal Fusion Model Based on Hybrid Attention Mechanism for Gesture Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-5006","authenticated-orcid":false,"given":"Yajie","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqiang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianquan","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,10]]},"reference":[{"key":"29_CR1","unstructured":"Anastasopoulos, A., Kumar, S., Liao, H.: Neural language modeling with visual features. Comput. Lang. (2019)"},{"issue":"2","key":"29_CR2","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltrusaitis","year":"2019","unstructured":"Baltrusaitis, T., Ahuja, C., Morency, L.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 423\u2013443 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Bastos, I.L.O., Melo, V.H.C., Robson Schwartz, W.: Multi-loss recurrent residual networks for gesture detection and recognition. In: 2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 170\u2013177 (2019)","DOI":"10.1109\/SIBGRAPI.2019.00031"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Benyounes, H., Cadene, R., Thome, N., Cord, M.: Block: bilinear superdiagonal fusion for visual question answering and visual relationship detection. Comput. Vis. Pattern Recogn. (2019)","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"29_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-319-16178-5_32","volume-title":"Computer Vision - ECCV 2014 Workshops","author":"S Escalera","year":"2015","unstructured":"Escalera, S., et al.: ChaLearn looking at people challenge 2014: dataset and results. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8925, pp. 459\u2013473. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16178-5_32"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Hori, C., Hori, T., Lee, T.Y., Sumi, K., Hershey, J.R., Marks, T.K.: Attention-based multimodal fusion for video description (2017)","DOI":"10.1109\/ICCV.2017.450"},{"issue":"7553","key":"29_CR7","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Li, F., Neverova, N., Wolf, C., Taylor, G.W.: ModOut: learning multi-modal architectures by stochastic regularization, pp. 422\u2013429 (2017)","DOI":"10.1109\/FG.2017.59"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Lu, P., Li, H., Zhang, W., Wang, J., Wang, X.: Co-attending free-form regions and detections with multi-modal multiplicative feature embedding for visual question answering. arXiv: Computer Vision and Pattern Recognition (2017)","DOI":"10.1609\/aaai.v32i1.12240"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Yang, X., Gupta, S., Kim, K., Tyree, S., Kautz, J.: Online detection and classification of dynamic hand gestures with recurrent 3D convolutional neural networks, pp. 4207\u20134215 (2016)","DOI":"10.1109\/CVPR.2016.456"},{"issue":"8","key":"29_CR11","doi-asserted-by":"publisher","first-page":"1692","DOI":"10.1109\/TPAMI.2015.2461544","volume":"38","author":"N Neverova","year":"2016","unstructured":"Neverova, N., Wolf, C., Taylor, G., Nebout, F.: ModDrop: adaptive multi-modal gesture recognition. IEEE Trans. Pattern Anal. Mach. Intell. 38(8), 1692\u20131706 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Perezrua, J., Vielzeuf, V., Pateux, S., Baccouche, M., Jurie, F.: MFAS: multimodal fusion architecture search, pp. 6966\u20136975 (2019)","DOI":"10.1109\/CVPR.2019.00713"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Pigou, L., Van Herreweghe, M., Dambre, J.: Gesture and sign language recognition with temporal residual networks, pp. 3086\u20133093 (2017)","DOI":"10.1109\/ICCVW.2017.365"},{"issue":"5","key":"29_CR14","doi-asserted-by":"publisher","first-page":"1878","DOI":"10.1093\/bib\/bby061","volume":"20","author":"AS Rifaioglu","year":"2019","unstructured":"Rifaioglu, A.S., Atas, H., Martin, M.J., Cetin-Atalay, R., Atalay, V., Do\u011fan, T.: Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases. Briefings Bioinf. 20(5), 1878\u20131912 (2019)","journal-title":"Briefings Bioinf."},{"key":"29_CR15","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos, pp. 568\u2013576 (2014)"},{"issue":"1","key":"29_CR16","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: DropOut: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Wang, H., Meghawat, A., Morency, L., Xing, E.P.: Select-additive learning: improving generalization in multimodal sentiment analysis, pp. 949\u2013954 (2017)","DOI":"10.1109\/ICME.2017.8019301"},{"issue":"3","key":"29_CR18","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/MCI.2018.2840738","volume":"13","author":"T Young","year":"2018","unstructured":"Young, T., Hazarika, D., Poria, S., Cambria, E.: Recent trends in deep learning based natural language processing [review article]. IEEE Comput. Intell. Mag. 13(3), 55\u201375 (2018)","journal-title":"IEEE Comput. Intell. Mag."},{"issue":"3","key":"29_CR19","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1109\/JSTSP.2020.2987728","volume":"14","author":"C Zhang","year":"2020","unstructured":"Zhang, C., Yang, Z., He, X., Deng, L.: Multimodal intelligence: representation learning, information fusion, and applications. IEEE J. Sel. Topics Signal Process. 14(3), 478\u2013493 (2020)","journal-title":"IEEE J. Sel. Topics Signal Process."},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhu, G., Shen, P., Song, J.: Learning spatiotemporal features using 3D CNN and convolutional LSTM for gesture recognition, pp. 3120\u20133128 (2017)","DOI":"10.1109\/ICCVW.2017.369"},{"issue":"4","key":"29_CR21","doi-asserted-by":"publisher","first-page":"1011","DOI":"10.1109\/TMM.2018.2869278","volume":"21","author":"G Zhu","year":"2018","unstructured":"Zhu, G., Zhang, L., Shen, P., Song, J., Shah, S.A.A., Bennamoun, M.: Continuous gesture segmentation and recognition using 3D CNN and convolutional LSTM. IEEE Trans. Multimedia 21(4), 1011\u20131021 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"29_CR22","unstructured":"Zhuang, B., Wang, W., Shinozaki, T.: Investigation of attention-based multimodal fusion and maximum mutual information objective for DSTC7 track3. In: In DSTC7 at AAAI 2019 workshop (2019)"}],"container-title":["Lecture Notes in Computer Science","Structural, Syntactic, and Statistical Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-73973-7_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T22:03:25Z","timestamp":1744149805000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-73973-7_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030739720","9783030739737"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-73973-7_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"10 April 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"S+SSPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 January 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 January 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sspr2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dais.unive.it\/sspr2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"81","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":"35","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":"43% - 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","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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}