{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T13:44:01Z","timestamp":1760708641733},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,11,5]],"date-time":"2013-11-05T00:00:00Z","timestamp":1383609600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2014,11]]},"DOI":"10.1007\/s11042-013-1748-6","type":"journal-article","created":{"date-parts":[[2013,11,4]],"date-time":"2013-11-04T06:48:01Z","timestamp":1383547681000},"page":"267-271","source":"Crossref","is-referenced-by-count":9,"title":["Multimodal joint information processing in human machine interaction: recent advances"],"prefix":"10.1007","volume":"73","author":[{"given":"Lei","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhigang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Cox","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,11,5]]},"reference":[{"key":"1748_CR1","doi-asserted-by":"crossref","unstructured":"Alcoverro M, Suau X, Morros JR, L\u00f3pez-M\u00e9ndez A, Gil A, Ruiz-Hidalgo J, Casas JR (2013) Gesture control interface for immersive panoramic displays. Multimed Tool Appl. doi: 10.1007\/s11042-013-1605-7","DOI":"10.1007\/s11042-013-1605-7"},{"issue":"1","key":"1748_CR2","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s11042-011-0744-y","volume":"59","author":"E Alepis","year":"2012","unstructured":"Alepis E, Virvou M (2012) Multimodal object oriented user interfaces in mobile affective interaction. Multimed Tool Appl 59(1):41\u201363","journal-title":"Multimed Tool Appl"},{"issue":"1","key":"1748_CR3","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1109\/79.911195","volume":"18","author":"T Chen","year":"2001","unstructured":"Chen T (2001) Audiovisual speech processing: lip reading and lip synchronization. IEEE Signal Proc Mag 18(1): 9\u201321","journal-title":"IEEE Signal Proc Mag"},{"issue":"1","key":"1748_CR4","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s11042-010-0529-8","volume":"54","author":"M Debevc","year":"2011","unstructured":"Debevc M, Kosec P, Holzinger A (2011) Improving multimodal web accessibility for deaf people: sign language interpreter module. Multimed Tool Appl 54(1):181\u2013199","journal-title":"Multimed Tool Appl"},{"issue":"2","key":"1748_CR5","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1007\/s11042-011-0923-x","volume":"63","author":"HK Ekenel","year":"2013","unstructured":"Ekenel HK, Semela T (2013) Multimodal genre classification of TV programs and youtube videos. Multimed Tool Appl 63(2):547\u2013567","journal-title":"Multimed Tool Appl"},{"key":"1748_CR6","doi-asserted-by":"crossref","unstructured":"Fu H, Ma H, Xiao H (2013) Scene-adaptive accurate and fast vertical crowd counting via joint using depth and color information. Multimed Tool Appl. doi: 10.1007\/s11042-013-1608-4","DOI":"10.1007\/s11042-013-1608-4"},{"key":"1748_CR7","doi-asserted-by":"crossref","unstructured":"Gamboa H, Silva H, Fred A (2013) Himotion: a new research resource for the study of behavior, cognition, and emotion. Multimed Tool Appl. doi: 10.1007\/s11042-013-1602-x","DOI":"10.1007\/s11042-013-1602-x"},{"key":"1748_CR8","doi-asserted-by":"crossref","unstructured":"Hsu F-S, Lin W-Y, Tsai T-W Facial expression recognition using bag of distances. Multimed Tool Appl. doi: 10.1007\/s11042-013-1616-4","DOI":"10.1007\/s11042-013-1616-4"},{"issue":"7","key":"1748_CR9","doi-asserted-by":"crossref","first-page":"1925","DOI":"10.1109\/TASL.2010.2103059","volume":"19","author":"Q Huang","year":"2010","unstructured":"Huang Q, Cox S (2010) Inferring the structure of a tennis game using audio information. IEEE Trans Audio Speech Lang Process 19(7):1925\u20131937","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1748_CR10","doi-asserted-by":"crossref","unstructured":"Jia J, Wu Z, Zhang S, Meng HM, Cai L (2013) Head and facial gestures synthesis using PAD model for an expressive talking avatar. Multimed Tool Appl. doi: 10.1007\/s11042-013-1604-8","DOI":"10.1007\/s11042-013-1604-8"},{"key":"1748_CR11","doi-asserted-by":"crossref","unstructured":"Jiang D, Zhao Y, Sahli H, Zhang Y (2013) Speech driven photo realistic facial animation based on an articulatory DBN model and AAM features. Multimed Tool Appl. doi: 10.1007\/s11042-013-1610-x","DOI":"10.1007\/s11042-013-1610-x"},{"key":"1748_CR12","doi-asserted-by":"crossref","unstructured":"Khan NU, Arya KV, Pattanaik M (2013) Edge preservation of impulse noise filtered images by improved anisotropic diffusion. Multimed Tool Appl. doi: 10.1007\/s11042-013-1620-8","DOI":"10.1007\/s11042-013-1620-8"},{"key":"1748_CR13","doi-asserted-by":"crossref","unstructured":"Khoury EE, S\u00e9nac C, Joly P (2013) Audiovisual diarization of people in video content. Multimed Tool Appl. doi: 10.1007\/s11042-012-1080-6","DOI":"10.1007\/s11042-012-1080-6"},{"issue":"3","key":"1748_CR14","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/s11042-006-0031-5","volume":"30","author":"E Kijak","year":"2006","unstructured":"Kijak E, Gravier G, Oisel L, Gros P (2006) Audiovisual integration for tennis broadcast structuring. Multimed Tool Appl 30(3):289\u2013311","journal-title":"Multimed Tool Appl"},{"issue":"11","key":"1748_CR15","doi-asserted-by":"crossref","first-page":"1902","DOI":"10.1109\/TVCG.2012.74","volume":"18","author":"BH Le","year":"2012","unstructured":"Le BH, Ma X, Deng Z (2012) Live speech driven head-and-eye motion generators. IEEE Trans Vis Comput Graph 18(11):1902\u20131914","journal-title":"IEEE Trans Vis Comput Graph"},{"issue":"2","key":"1748_CR16","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1007\/s11042-009-0344-2","volume":"49","author":"M Mansoorizadeh","year":"2010","unstructured":"Mansoorizadeh M, Charkari NM (2010) Multimodal information fusion application to human emotion recognition from face and speech. Multimed Tool Appl 49(2):277\u2013297","journal-title":"Multimed Tool Appl"},{"key":"1748_CR17","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1038\/264746a0","volume":"264","author":"H McGurk","year":"1976","unstructured":"McGurk H, MacDonald J (1976) Hearing lips and seeing voices. Nature 264:746\u2013748","journal-title":"Nature"},{"issue":"2","key":"1748_CR18","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1007\/s11042-011-0842-x","volume":"61","author":"D Mekhaldi","year":"2012","unstructured":"Mekhaldi D, Lalanne D, Ingold R (2012) A multimodal alignment framework for spoken documents. Multimed Tool Appl 61(2):353\u2013388","journal-title":"Multimed Tool Appl"},{"issue":"3","key":"1748_CR19","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1109\/TASL.2009.2013699","volume":"17","author":"H Meng","year":"2009","unstructured":"Meng H, Oviatt S, Patamianos G (2009) Introduction to the special issue on multimodal processing in speech-based interactions. IEEE Trans Audio Speech Lang Process 17(3):409\u2013410","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1748_CR20","doi-asserted-by":"crossref","unstructured":"Meng F, Wu Z, Jia J, Meng H, Cai L (2013) Synthesizing english emphatic speech for multimodal corrective feedback in computer-aided pronunciation training. Multimed Tool Appl. doi: 10.1007\/s11042-013-1601-y","DOI":"10.1007\/s11042-013-1601-y"},{"issue":"1","key":"1748_CR21","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/s11042-008-0222-3","volume":"41","author":"M Montagnuolo","year":"2009","unstructured":"Montagnuolo M, Messina A (2009) Parallel neural networks for multimodal video genre classification. Multimed Tool Appl 41(1):125\u2013159","journal-title":"Multimed Tool Appl"},{"issue":"1","key":"1748_CR22","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/B:MTAP.0000046380.27575.a5","volume":"25","author":"CG Snoek","year":"2005","unstructured":"Snoek CG, Worring M (2005) Multimodal video indexing: a review of the state-of-the-art. Multimed Tool Appl 25(1):5\u201335","journal-title":"Multimed Tool Appl"},{"key":"1748_CR23","doi-asserted-by":"crossref","unstructured":"Shih P-Y, Paul A, Wang J-F, Chen Y-H (2013) Speech-driven talking face using embedded confusable system for real time mobile multimedia. Multimed Tool Appl. doi: 10.1007\/s11042-013-1609-3","DOI":"10.1007\/s11042-013-1609-3"},{"key":"1748_CR24","doi-asserted-by":"crossref","unstructured":"Sun L, Song M, Tao D, Bu J, Chen C (2013) Motionlet LLC coding for discriminative human pose estimation. Multimed Tool Appl. doi: 10.1007\/s11042-013-1617-3","DOI":"10.1007\/s11042-013-1617-3"},{"key":"1748_CR25","doi-asserted-by":"crossref","unstructured":"Tsai H-C, Chen B-W, Wang J-F, Paul A (2013) Enhanced long-range personal identification based on multimodal information of human features. Multimed Tool Appl. doi: 10.1007\/s11042-013-1606-6","DOI":"10.1007\/s11042-013-1606-6"},{"key":"1748_CR26","doi-asserted-by":"crossref","unstructured":"Wang Z, Yu J, He Y, Guan T (2013) Affection arousal based highlight extraction for soccer video. Multimed Tool Appl. doi: 10.1007\/s11042-013-1619-1","DOI":"10.1007\/s11042-013-1619-1"},{"issue":"23","key":"1748_CR27","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1109\/TMM.2006.888009","volume":"9","author":"L Xie","year":"2007","unstructured":"Xie L, Liu Z-Q (2007) Realistic mouth-synching for speech-driven talking face using articulatory modelling. IEEE Trans Multimed 9(23):500\u2013510","journal-title":"IEEE Trans Multimed"},{"key":"1748_CR28","doi-asserted-by":"crossref","unstructured":"Xie L, Sun N, Fan B (2013) A statistical parametric approach to video-realistic text-driven talking avatar. Multimed Tool Appl. doi: 10.1007\/s11042-013-1633-3","DOI":"10.1007\/s11042-013-1633-3"},{"key":"1748_CR29","doi-asserted-by":"crossref","unstructured":"Zhang W, Liu C, Wang Z, Li G, Huang Q, Gao W (2013) Web video thumbnail recommendation with content-aware analysis and query-sensitive matching. Multimed Tool Appl. doi: 10.1007\/s11042-013-1607-5","DOI":"10.1007\/s11042-013-1607-5"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-013-1748-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-013-1748-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-013-1748-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T03:31:56Z","timestamp":1559359916000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-013-1748-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11,5]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,11]]}},"alternative-id":["1748"],"URL":"https:\/\/doi.org\/10.1007\/s11042-013-1748-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,11,5]]}}}