{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T21:58:44Z","timestamp":1743112724433,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030057091"},{"type":"electronic","value":"9783030057107"}],"license":[{"start":{"date-parts":[[2018,12,8]],"date-time":"2018-12-08T00:00:00Z","timestamp":1544227200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-05710-7_33","type":"book-chapter","created":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T07:48:55Z","timestamp":1544168935000},"page":"399-410","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Audiovisual Annotation Procedure for Multi-view Field Recordings"],"prefix":"10.1007","author":[{"given":"Patrice","family":"Guyot","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thierry","family":"Malon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geoffrey","family":"Roman-Jimenez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sylvie","family":"Chambon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Charvillat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alain","family":"Crouzil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andr\u00e9","family":"P\u00e9ninou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julien","family":"Pinquier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florence","family":"S\u00e8des","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christine","family":"S\u00e9nac","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,8]]},"reference":[{"issue":"1","key":"33_CR1","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1609\/aimag.v36i1.2564","volume":"36","author":"L Aroyo","year":"2015","unstructured":"Aroyo, L., Welty, C.: Truth is a lie: crowd truth and the seven myths of human annotation. AI Mag. 36(1), 15\u201324 (2015)","journal-title":"AI Mag."},{"unstructured":"Auer, E., et al.: Automatic annotation of media field recordings. In: ECAI 2010 Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities (LaTeCH 2010), pp. 31\u201334. University de Lisbon (2010)","key":"33_CR2"},{"issue":"1\u20132","key":"33_CR3","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/S0167-6393(00)00068-6","volume":"33","author":"S Bird","year":"2001","unstructured":"Bird, S., Liberman, M.: A formal framework for linguistic annotation. Speech Commun. 33(1\u20132), 23\u201360 (2001)","journal-title":"Speech Commun."},{"key":"33_CR4","volume-title":"Audio-Vision: Sound on Screen","author":"M Chion","year":"1994","unstructured":"Chion, M.: Audio-Vision: Sound on Screen. Columbia University Press, New York (1994)"},{"unstructured":"Ellis, D.P., Whitman, B., Berenzweig, A., Lawrence, S.: The quest for ground truth in musical artist similarity. In: ISMIR, Paris, France (2002)","key":"33_CR5"},{"doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE (2017)","key":"33_CR6","DOI":"10.1109\/ICASSP.2017.7952261"},{"doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. CoRR abs\/1705.08421 (2017)","key":"33_CR7","DOI":"10.1109\/CVPR.2018.00633"},{"issue":"1","key":"33_CR8","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1177\/1470357203002001751","volume":"2","author":"R Iedema","year":"2003","unstructured":"Iedema, R.: Multimodality, resemiotization: extending the analysis of discourse as multi-semiotic practice. Vis. Commun. 2(1), 29\u201357 (2003)","journal-title":"Vis. Commun."},{"issue":"7553","key":"33_CR9","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 (2015)","journal-title":"Nature"},{"key":"33_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-642-23538-2_4","volume-title":"Text, Speech and Dialogue","author":"I Lefter","year":"2011","unstructured":"Lefter, I., Rothkrantz, L.J.M., Burghouts, G., Yang, Z., Wiggers, P.: Addressing multimodality in overt aggression detection. In: Habernal, I., Matou\u0161ek, V. (eds.) TSD 2011. LNCS (LNAI), vol. 6836, pp. 25\u201332. Springer, Heidelberg (2011). \n                      https:\/\/doi.org\/10.1007\/978-3-642-23538-2_4"},{"doi-asserted-by":"crossref","unstructured":"Li, D., Dimitrova, N., Li, M., Sethi, I.K.: Multimedia content processing through cross-modal association. In: Proceedings of the Eleventh ACM International Conference on Multimedia, pp. 604\u2013611. ACM (2003)","key":"33_CR11","DOI":"10.1145\/957142.957143"},{"issue":"7","key":"33_CR12","doi-asserted-by":"publisher","first-page":"1781","DOI":"10.1109\/TCYB.2016.2582918","volume":"47","author":"AA Liu","year":"2017","unstructured":"Liu, A.A., Xu, N., Nie, W.Z., Su, Y.T., Wong, Y., Kankanhalli, M.: Benchmarking a multimodal and multiview and interactive dataset for human action recognition. IEEE Trans. Cybern. 47(7), 1781\u20131794 (2017)","journal-title":"IEEE Trans. Cybern."},{"doi-asserted-by":"crossref","unstructured":"Malon, T., et al.: Toulouse campus surveillance dataset: scenarios, soundtracks, synchronized videos with overlapping and disjoint views (regular paper). In: ACM Multimedia Systems Conference (MMSys), Amsterdam, 12 June 2018\u201315 June 2018. ACM Multimedia Systems, June 2018","key":"33_CR13","DOI":"10.1145\/3204949.3208133"},{"issue":"5588","key":"33_CR14","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1038\/264746a0","volume":"264","author":"H McGurk","year":"1976","unstructured":"McGurk, H., MacDonald, J.: Hearing lips and seeing voices. Nature 264(5588), 746 (1976)","journal-title":"Nature"},{"unstructured":"Mesaros, A., et al.: DCASE 2017 challenge setup: tasks, datasets and baseline system. In: DCASE 2017-Workshop on Detection and Classification of Acoustic Scenes and Events (2017)","key":"33_CR15"},{"doi-asserted-by":"crossref","unstructured":"Ofli, F., Chaudhry, R., Kurillo, G., Vidal, R., Bajcsy, R.: Berkeley MHAD: a comprehensive multimodal human action database. In: 2013 IEEE Workshop on Applications of Computer Vision (WACV), pp. 53\u201360. IEEE (2013)","key":"33_CR16","DOI":"10.1109\/WACV.2013.6474999"},{"issue":"3","key":"33_CR17","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1109\/TPAMI.2013.142","volume":"36","author":"JC Pereira","year":"2014","unstructured":"Pereira, J.C., et al.: On the role of correlation and abstraction in cross-modal multimedia retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 521\u2013535 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"unstructured":"Pinquier, J., et al.: Strategies for multiple feature fusion with hierarchical hmm: application to activity recognition from wearable audiovisual sensors. In: 2012 21st International Conference on Pattern Recognition (ICPR), pp. 3192\u20133195. IEEE (2012)","key":"33_CR18"},{"unstructured":"Rohlfing, K., et al.: Comparison of multimodal annotation tools-workshop report. Gespr\u00e4chforschung-Online-Zeitschrift zur Verbalen Interaktion 7, 99\u2013123 (2006)","key":"33_CR19"},{"issue":"3","key":"33_CR20","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet Large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"issue":"2","key":"33_CR21","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1109\/TASL.2007.913750","volume":"16","author":"D Turnbull","year":"2008","unstructured":"Turnbull, D., Barrington, L., Torres, D., Lanckriet, G.: Semantic annotation and retrieval of music and sound effects. IEEE Trans. Audio Speech Lang. Process. 16(2), 467\u2013476 (2008)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"1","key":"33_CR22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.patrec.2012.07.005","volume":"34","author":"X Wang","year":"2013","unstructured":"Wang, X.: Intelligent multi-camera video surveillance: a review. Pattern Recogn. Lett. 34(1), 3\u201319 (2013)","journal-title":"Pattern Recogn. Lett."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-05710-7_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T05:37:52Z","timestamp":1558330672000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-05710-7_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,8]]},"ISBN":["9783030057091","9783030057107"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-05710-7_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018,12,8]]},"assertion":[{"value":"8 December 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thessaloniki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/mmm2019.iti.gr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double blind for full papers and workshop papers, single blind for other paper types","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"204","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"96","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"47% - 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"}},{"value":"2.67","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"6 demonstration papers, 5 industry papers, 6 workshop papers, and 6 Video Browser Showdown papers were also accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}