{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:26:42Z","timestamp":1757611602428,"version":"3.44.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863302"},{"type":"electronic","value":"9783030863319"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86331-9_51","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:05:57Z","timestamp":1630721157000},"page":"793-807","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dialogue Act Recognition Using Visual Information"],"prefix":"10.1007","author":[{"given":"Ji\u0159\u00ed","family":"Mart\u00ednek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Kr\u00e1l","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ladislav","family":"Lenc","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"issue":"1","key":"51_CR1","first-page":"19","volume":"3","author":"H Bunt","year":"1994","unstructured":"Bunt, H.: Context and dialogue control. Think Quarterly 3(1), 19\u201331 (1994)","journal-title":"Think Quarterly"},{"issue":"3","key":"51_CR2","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1162\/089120100561737","volume":"26","author":"A Stolcke","year":"2000","unstructured":"Stolcke, A., et al.: Dialogue act modeling for automatic tagging and recognition of conversational speech. Comput. Linguist. 26(3), 339\u2013373 (2000)","journal-title":"Comput. Linguist."},{"key":"51_CR3","doi-asserted-by":"crossref","unstructured":"Frankel, J., King, S.: ASR-articulatory speech recognition. In: Seventh European Conference on Speech Communication and Technology (2001)","DOI":"10.21437\/Eurospeech.2001-159"},{"key":"51_CR4","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1016\/j.csl.2017.07.009","volume":"47","author":"C Cerisara","year":"2018","unstructured":"Cerisara, C., Kr\u00e1l, P., Lenc, L.: On the effects of using word2vec representations in neural networks for dialogue act recognition. Comput. Speech Lang. 47, 175\u2013193 (2018)","journal-title":"Comput. Speech Lang."},{"key":"51_CR5","unstructured":"Jekat, S., Klein, A., Maier, E., Maleck, I., Mast, M., Quantz, J.J.: Dialogue acts in verbmobil (1995)"},{"key":"51_CR6","doi-asserted-by":"crossref","unstructured":"Godfrey, J.J., Holliman, E.C., McDaniel, J.: Switchboard: telephone speech corpus for research and development. In: Proceedings of the 1992 IEEE International Conference on Acoustics, Speech and Signal Processing - Volume 1, ser. ICASSP 1992, pp. 517\u2013520. IEEE Computer Society, USA (1992)","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"51_CR7","doi-asserted-by":"crossref","unstructured":"Shriberg, E., Dhillon, R., Bhagat, S., Ang, J., Carvey, H.: The ICSI meeting recorder dialog act (MRDA) corpus. Technical report, International Computer Science Institute, Berkely (2004)","DOI":"10.21236\/ADA460980"},{"key":"51_CR8","unstructured":"Bened\u0131, J.-M., et al.: Design and acquisition of a telephone spontaneous speech dialogue corpus in Spanish: Dihana. In: Fifth International Conference on Language Resources and Evaluation (LREC), pp. 1636\u20131639 (2006)"},{"key":"51_CR9","doi-asserted-by":"crossref","unstructured":"Colombo, P., Chapuis, E., Manica, M., Vignon, E., Varni, G., Clavel, C.: Guiding attention in sequence-to-sequence models for dialogue act prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 05, pp. 7594\u20137601 (2020)","DOI":"10.1609\/aaai.v34i05.6259"},{"key":"51_CR10","doi-asserted-by":"crossref","unstructured":"Shang, G., Tixier, A.J.-P., Vazirgiannis, M., Lorr\u00e9, J.-P.: Speaker-change aware CRF for dialogue act classification, arXiv preprint arXiv:2004.02913 (2020)","DOI":"10.18653\/v1\/2020.coling-main.40"},{"key":"51_CR11","unstructured":"Alexandersson, J., et al.: Dialogue acts in Verbmobil 2. DFKI Saarbr\u00fccken (1998)"},{"key":"51_CR12","doi-asserted-by":"crossref","unstructured":"Reithinger, N., Klesen, M.: Dialogue act classification using language models. In: Fifth European Conference on Speech Communication and Technology (1997)","DOI":"10.21437\/Eurospeech.1997-589"},{"key":"51_CR13","doi-asserted-by":"crossref","unstructured":"Samuel, K., Carberry, S., Vijay-Shanker, K.: Dialogue act tagging with transformation-based learning, arXiv preprint cmp-lg\/9806006 (1998)","DOI":"10.3115\/980432.980757"},{"key":"51_CR14","doi-asserted-by":"crossref","unstructured":"Mart\u00ednek, J., Kr\u00e1l, P., Lenc, L., Cerisara, C.: Multi-lingual dialogue act recognition with deep learning methods, arXiv preprint arXiv:1904.05606 (2019)","DOI":"10.21437\/Interspeech.2019-1691"},{"key":"51_CR15","unstructured":"Cerisara, C., Jafaritazehjani, S., Oluokun, A., Le, H.: Multi-task dialog act and sentiment recognition on mastodon, arXiv preprint arXiv:1807.05013 (2018)"},{"key":"51_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Fei, H., Ji, D.: Modeling local contexts for joint dialogue act recognition and sentiment classification with bi-channel dynamic convolutions. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 616\u2013626 (2020)","DOI":"10.18653\/v1\/2020.coling-main.53"},{"key":"51_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Fu, J., Liu, X., Huang, X.: Adaptive co-attention network for named entity recognition in tweets. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"51_CR18","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/978-3-030-43823-4_35","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"N Audebert","year":"2020","unstructured":"Audebert, N., Herold, C., Slimani, K., Vidal, C.: Multimodal deep networks for text and image-based document classification. In: Cellier, P., Driessens, K. (eds.) ECML PKDD 2019. CCIS, vol. 1167, pp. 427\u2013443. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-43823-4_35"},{"key":"51_CR19","unstructured":"Joulin, A., Grave, E., Bojanowski, P., Douze, M., J\u00e9gou, H., Mikolov, T.: Fasttext.zip: compressing text classification models, arXiv preprint arXiv:1612.03651 (2016)"},{"key":"51_CR20","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"51_CR21","doi-asserted-by":"crossref","unstructured":"Jain, R., Wigington, C.: Multimodal document image classification. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 71\u201377. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00021"},{"issue":"11","key":"51_CR22","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"51_CR23","doi-asserted-by":"crossref","unstructured":"Mart\u00ednek, J., Lenc, L., Kr\u00e1l, P., Nicolaou, A., Christlein, V.: Hybrid training data for historical text OCR. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 565\u2013570. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00096"},{"key":"51_CR24","doi-asserted-by":"crossref","unstructured":"Han, L., Kamdar, M.R.: MRI to MGMT: predicting methylation status in glioblastoma patients using convolutional recurrent neural networks (2017)","DOI":"10.1142\/9789813235533_0031"},{"key":"51_CR25","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376. ACM (2006)","DOI":"10.1145\/1143844.1143891"},{"issue":"8","key":"51_CR26","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"51_CR27","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space, arXiv preprint arXiv:1301.3781 (2013)"},{"issue":"2","key":"51_CR28","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/S0031-3203(99)00055-2","volume":"33","author":"J Sauvola","year":"2000","unstructured":"Sauvola, J., Pietik\u00e4inen, M.: Adaptive document image binarization. Pattern Recogn. 33(2), 225\u2013236 (2000)","journal-title":"Pattern Recogn."}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86331-9_51","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T22:03:34Z","timestamp":1756937014000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86331-9_51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863302","9783030863319"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86331-9_51","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":"2 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"340","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":"182","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":"54% - 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":"2.9","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":"4.9","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)"}},{"value":"Additionally, 13 competition reports are included.","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)"}}]}}