@article{bb247700,
        AUTHOR = "Gong, Y.H.",
        TITLE = "Summarizing Audiovisual Contents of a Video Program",
        JOURNAL = JASP,
        VOLUME = "2003",
        YEAR = "2003",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "160",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242548"}

@inproceedings{bb247701,
        AUTHOR = "Gong, Y.H. and Liu, X.",
        TITLE = "Method and system for segmentation, classification, and summarization
of video images",
        BOOKTITLE = US_Patent,
        YEAR = "2006",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242549"}

@inproceedings{bb247702,
        AUTHOR = "Liu, X. and Gong, Y.H.",
        TITLE = "Method and system for segmentation, classification, and summarization
of video images",
        BOOKTITLE = US_Patent,
        YEAR = "2006",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242549"}

@inproceedings{bb247703,
        AUTHOR = "Gong, Y.H. and Liu, X.",
        TITLE = "Creating audio-centric, image-centric, 
and integrated audio-visual summaries",
        BOOKTITLE = US_Patent,
        YEAR = "2005",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242550"}

@inproceedings{bb247704,
        AUTHOR = "Gong, Y.H. and Liu, X.",
        TITLE = "Video Summarization using Singular Value Decomposition",
        BOOKTITLE = CVPR00,
        YEAR = "2000",
        PAGES = "II: 174-180",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242551"}

@inproceedings{bb247705,
        AUTHOR = "Gong, Y.H. and Liu, X.",
        TITLE = "Video Shot Segmentation and Classification",
        BOOKTITLE = ICPR00,
        YEAR = "2000",
        PAGES = "Vol I: 860-863",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242552"}

@article{bb247706,
        AUTHOR = "Wang, H.L. and Divakaran, A. and Vetro, A. and Chang, S.F. and Sun, H.F.",
        TITLE = "Survey of compressed-domain features used in audio-visual indexing and
analysis",
        JOURNAL = JVCIR,
        VOLUME = "14",
        YEAR = "2003",
        NUMBER = "2",
        MONTH = "June",
        PAGES = "150-183",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242553"}

@article{bb247707,
        AUTHOR = "Naphade, M.R.",
        TITLE = "On supervision and statistical learning for semantic multimedia
analysis",
        JOURNAL = JVCIR,
        VOLUME = "15",
        YEAR = "2004",
        NUMBER = "3",
        MONTH = "September",
        PAGES = "348-369",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242554"}

@article{bb247708,
        AUTHOR = "Naphade, M.R. and Kozintsev, I.V. and Huang, T.S.",
        TITLE = "A factor graph framework for semantic video indexing",
        JOURNAL = CirSysVideo,
        VOLUME = "12",
        YEAR = "2002",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "40-52",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242555"}

@inproceedings{bb247709,
        AUTHOR = "Naphade, M.R. and Kozintsev, I.V. and Huang, T.S. and Ramchandran, K.",
        TITLE = "A factor graph framework for semantic indexing and retrieval in video",
        BOOKTITLE = CBAIVL00,
        YEAR = "2000",
        PAGES = "35-39",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242556"}

@inproceedings{bb247710,
        AUTHOR = "Naphade, M.R. and Huang, T.S.",
        TITLE = "Detecting Semantic Concepts Using Context and Audio/Visual Features",
        BOOKTITLE = EventVideo01,
        YEAR = "2001",
        PAGES = "92-98",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242557"}

@inproceedings{bb247711,
        AUTHOR = "Naphade, M.R. and Huang, T.S.",
        TITLE = "Recognizing High-level Audio-visual Concepts Using Context",
        BOOKTITLE = ICIP01,
        YEAR = "2001",
        PAGES = "III: 46-49",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242558"}

@inproceedings{bb247712,
        AUTHOR = "Naphade, M.R. and Huang, T.S.",
        TITLE = "Semantic Video Indexing Using a Probabilistic Framework",
        BOOKTITLE = ICPR00,
        YEAR = "2000",
        PAGES = "Vol III: 79-84",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242559"}

@inproceedings{bb247713,
        AUTHOR = "Naphade, M.R. and Huang, T.S.",
        TITLE = "A Probabilistic Framework for Semantic Indexing and Retrieval in Video",
        BOOKTITLE = ICME00,
        YEAR = "2000",
        PAGES = "MP9",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242560"}

@inproceedings{bb247714,
        AUTHOR = "Naphade, M.R. and Huang, T.S.",
        TITLE = "Inferring Semantic Concepts for Video Indexing and Retrieval",
        BOOKTITLE = ICIP00,
        YEAR = "2000",
        PAGES = "Vol III: 766-769",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242561"}

@inproceedings{bb247715,
        AUTHOR = "Naphade, M.R. and Kristjansson, T. and Frey, B.J. and Huang, T.S.",
        TITLE = "Probabilistic multimedia objects (multijects): a novel approach to
video indexing and retrieval in multimedia systems",
        BOOKTITLE = ICIP98,
        YEAR = "1998",
        PAGES = "III: 536-540",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242562"}

@article{bb247716,
        AUTHOR = "Xie, X. and Lu, L. and Jia, M. and Li, H. and Seide, F. and Ma, W.Y.",
        TITLE = "Mobile Search With Multimodal Queries",
        JOURNAL = PIEEE,
        VOLUME = "96",
        YEAR = "2008",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "589-601",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242563"}

@article{bb247717,
        AUTHOR = "Kiranyaz, S. and Gabbouj, M.",
        TITLE = "Generic content-based audio indexing and retrieval framework",
        JOURNAL = VISP,
        VOLUME = "153",
        YEAR = "2006",
        NUMBER = "3",
        MONTH = "June",
        PAGES = "285-297",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242564"}

@article{bb247718,
        AUTHOR = "Monaci, G. and Jost, P. and Vandergheynst, P. and Mailhe, B. and Lesage, S. and Gribonval, R.",
        TITLE = "Learning Multimodal Dictionaries",
        JOURNAL = IP,
        VOLUME = "16",
        YEAR = "2007",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2272-2283",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242565"}

@inproceedings{bb247719,
        AUTHOR = "Zhang, T.",
        TITLE = "Using background audio change detection for segmenting video",
        BOOKTITLE = US_Patent,
        YEAR = "2007",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242566"}

@article{bb247720,
        AUTHOR = "Kotti, M. and Ververidis, D. and Evangelopoulos, G. and Panagakis, I. and Kotropoulos, C. and Maragos, P. and Pitas, I.",
        TITLE = "Audio-Assisted Movie Dialogue Detection",
        JOURNAL = CirSysVideo,
        VOLUME = "18",
        YEAR = "2008",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "1618-1627",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242567"}

@article{bb247721,
        AUTHOR = "Cristani, M. and Bicego, M. and Murino, V.",
        TITLE = "Audio-Visual Event Recognition in Surveillance Video Sequences",
        JOURNAL = MultMed,
        VOLUME = "9",
        YEAR = "2007",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "257-267",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242568"}

@inproceedings{bb247722,
        AUTHOR = "Cristani, M. and Bicego, M. and Murino, V.",
        TITLE = "Audio-Visual Foreground Extraction for Event Characterization",
        BOOKTITLE = SLAM06,
        YEAR = "2006",
        PAGES = "116",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242569"}

@inproceedings{bb247723,
        AUTHOR = "Cristani, M. and Bicego, M. and Murino, V.",
        TITLE = "Audio-Video Integration for Background Modelling",
        BOOKTITLE = ECCV04,
        YEAR = "2004",
        PAGES = "Vol II: 202-213",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242570"}

@article{bb247724,
        AUTHOR = "Zeng, Z.H. and Tu, J.L. and Liu, M. and Huang, T.S. and Pianfetti, B. and Roth, D. and Levinson, S.",
        TITLE = "Audio-Visual Affect Recognition",
        JOURNAL = MultMed,
        VOLUME = "9",
        YEAR = "2007",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "424-428",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242571"}

@article{bb247725,
        AUTHOR = "Zeng, Z.H. and Tu, J.L. and Pianfetti, B.M. and Huang, T.S.",
        TITLE = "Audio-Visual Affective Expression Recognition Through Multistream Fused
HMM",
        JOURNAL = MultMed,
        VOLUME = "10",
        YEAR = "2008",
        NUMBER = "4",
        MONTH = "June",
        PAGES = "570-577",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242572"}

@inproceedings{bb247726,
        AUTHOR = "Zeng, Z.H. and Tu, J.L. and Pianfetti, B. and Liu, M. and Zhang, T. and Zhang, Z.Q. and Huang, T.S. and Levinson, S.",
        TITLE = "Audio-Visual Affect Recognition through Multi-Stream Fused HMM for HCI",
        BOOKTITLE = CVPR05,
        YEAR = "2005",
        PAGES = "II: 967-972",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242573"}

@article{bb247727,
        AUTHOR = "Zhang, S.L. and Huang, Q.M. and Jiang, S. and Gao, W. and Tian, Q.",
        TITLE = "Affective Visualization and Retrieval for Music Video",
        JOURNAL = MultMed,
        VOLUME = "12",
        YEAR = "2010",
        NUMBER = "6",
        PAGES = "510-522",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242574"}

@article{bb247728,
        AUTHOR = "Zhang, S.L. and Tian, Q. and Hua, G. and Huang, Q.M. and Gao, W.",
        TITLE = "Generating Descriptive Visual Words and Visual Phrases for Large-Scale
Image Applications",
        JOURNAL = IP,
        VOLUME = "20",
        YEAR = "2011",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2664-2677",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242575"}

@article{bb247729,
        AUTHOR = "Zhang, S.L. and Tian, Q. and Huang, Q.M. and Gao, W. and Rui, Y.",
        TITLE = "USB: Ultrashort Binary Descriptor for Fast Visual Matching and
Retrieval",
        JOURNAL = IP,
        VOLUME = "23",
        YEAR = "2014",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "3671-3683",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242576"}

@article{bb247730,
        AUTHOR = "Zhang, S.L. and Tian, Q. and Huang, Q.M. and Gao, W. and Rui, Y.",
        TITLE = "Cascade Category-Aware Visual Search",
        JOURNAL = IP,
        VOLUME = "23",
        YEAR = "2014",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "2514-2527",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242577"}

@article{bb247731,
        AUTHOR = "Irie, G. and Satou, T. and Kojima, A. and Yamasaki, T. and Aizawa, K.",
        TITLE = "Affective Audio-Visual Words and Latent Topic Driving Model for
Realizing Movie Affective Scene Classification",
        JOURNAL = MultMed,
        VOLUME = "12",
        YEAR = "2010",
        NUMBER = "6",
        PAGES = "523-535",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242578"}

@article{bb247732,
        AUTHOR = "Ibrahim, Z.A. and Ferrane, I. and Joly, P.",
        TITLE = "A Similarity-Based Approach for Audiovisual Document Classification
Using Temporal Relation Analysis",
        JOURNAL = JIVP,
        VOLUME = "2011",
        YEAR = "2011",
        NUMBER = "2011",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242579"}

@inproceedings{bb247733,
        AUTHOR = "Philippeau, J. and Pinquier, J. and Joly, P. and Carrive, J.",
        TITLE = "Dynamic organization of audiovisual database using a user-defined
similarity measure based on low-level features",
        BOOKTITLE = ICIP08,
        YEAR = "2008",
        PAGES = "33-36",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242580"}

@inproceedings{bb247734,
        AUTHOR = "Haidar, S. and Joly, P. and Chebaro, B.",
        TITLE = "Style Similarity Measure for Video Documents Comparison",
        BOOKTITLE = CIVR05,
        YEAR = "2005",
        PAGES = "307-317",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242581"}

@article{bb247735,
        AUTHOR = "Huurnink, B. and Snoek, C.G.M. and de Rijke, M. and Smeulders, A.W.M.",
        TITLE = "Content-Based Analysis Improves Audiovisual Archive Retrieval",
        JOURNAL = MultMed,
        VOLUME = "14",
        YEAR = "2012",
        NUMBER = "4",
        PAGES = "1166-1178",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242582"}

@inproceedings{bb247736,
        AUTHOR = "Huurnink, B. and Snoek, C.G.M. and de Rijke, M. and Smeulders, A.W.M.",
        TITLE = "Today's and tomorrow's retrieval practice in the audiovisual archive",
        BOOKTITLE = CIVR10,
        YEAR = "2010",
        PAGES = "18-25",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242583"}

@inproceedings{bb247737,
        AUTHOR = "Huurnink, B. and de Rijke, M.",
        TITLE = "The value of stories for speech-based video search",
        BOOKTITLE = CIVR07,
        YEAR = "2007",
        PAGES = "266-271",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242584"}

@article{bb247738,
        AUTHOR = "Jhuo, I.H. and Ye, G.N. and Gao, S.H. and Liu, D. and Jiang, Y.G. and Lee, D.T. and Chang, S.F.",
        TITLE = "Discovering joint audio-visual codewords for video event detection",
        JOURNAL = MVA,
        VOLUME = "25",
        YEAR = "2014",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "33-47",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242585"}

@inproceedings{bb247739,
        AUTHOR = "Ye, G.N. and Jhuo, I.H. and Liu, D. and Jiang, Y.G. and Lee, D.T. and Chang, S.F.",
        TITLE = "Joint audio-visual bi-modal codewords for video event detection",
        BOOKTITLE = ICMR12,
        YEAR = "2012",
        PAGES = "39",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242586"}

@article{bb247740,
        AUTHOR = "Feki, I. and Ben Ammar, A. and Alimi, A.M.",
        TITLE = "Automatic environmental sound concepts discovery for video retrieval",
        JOURNAL = MultInfoRetr,
        VOLUME = "5",
        YEAR = "2016",
        NUMBER = "2",
        MONTH = "June",
        PAGES = "105-115",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242587"}

@article{bb247741,
        AUTHOR = "Khan, M.U.G. and Gotoh, Y.",
        TITLE = "Generating natural language tags for video information management",
        JOURNAL = MVA,
        VOLUME = "28",
        YEAR = "2017",
        NUMBER = "3-4",
        MONTH = "May",
        PAGES = "243-265",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242588"}

@inproceedings{bb247742,
        AUTHOR = "Khan, M.U.G. and Zhang, L. and Gotoh, Y.",
        TITLE = "Generating coherent natural language annotations for video streams",
        BOOKTITLE = ICIP12,
        YEAR = "2012",
        PAGES = "2893-2896",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242589"}

@inproceedings{bb247743,
        AUTHOR = "Khan, M.U.G. and Zhang, L. and Gotoh, Y.",
        TITLE = "Towards coherent natural language description of video streams",
        BOOKTITLE = SIG11,
        YEAR = "2011",
        PAGES = "664-671",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242590"}

@inproceedings{bb247744,
        AUTHOR = "Zhang, L. and Khan, M.U.G. and Gotoh, Y.",
        TITLE = "Video scene classification based on natural language description",
        BOOKTITLE = ARTEMIS11,
        YEAR = "2011",
        PAGES = "942-949",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242591"}

@inproceedings{bb247745,
        AUTHOR = "Guo, X.N. and Zhong, W. and Ye, L. and Fang, L. and Heng, Y. and Zhang, Q.",
        TITLE = "Global Affective Video Content Regression Based on Complementary
Audio-visual Features",
        BOOKTITLE = MMMod20,
        YEAR = "2020",
        PAGES = "II:540-550",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242592"}

@inproceedings{bb247746,
        AUTHOR = "Peri, D. and Sah, S. and Ptucha, R.",
        TITLE = "Show, Translate and Tell",
        BOOKTITLE = ICIP19,
        YEAR = "2019",
        PAGES = "295-299",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242593"}

@inproceedings{bb247747,
        AUTHOR = "Chen, K. and Zhang, C.X. and Fang, C. and Wang, Z.W. and Bui, T. and Nevatia, R.",
        TITLE = "Visually Indicated Sound Generation by Perceptually Optimized
Classification",
        BOOKTITLE = MultLearnApp18,
        YEAR = "2018",
        PAGES = "VI:560-574",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242594"}

@inproceedings{bb247748,
        AUTHOR = "Haurilet, M.L. and Tapaswi, M. and Al Halah, Z. and Stiefelhagen, R.",
        TITLE = "Naming TV characters by watching and analyzing dialogs",
        BOOKTITLE = WACV16,
        YEAR = "2016",
        PAGES = "1-9",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242595"}

@inproceedings{bb247749,
        AUTHOR = "Numano, S. and Enami, N. and Ariki, Y.",
        TITLE = "Task-Driven Saliency Detection on Music Video",
        BOOKTITLE = CV4AC14,
        YEAR = "2014",
        PAGES = "658-671",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242596"}

@inproceedings{bb247750,
        AUTHOR = "Scott, D. and Zhang, Z.X. and Albatal, R. and McGuinness, K. and Acar, E. and Hopfgartner, F. and Gurrin, C. and O'Connor, N.E. and Smeaton, A.F.",
        TITLE = "Audio-Visual Classification Video Browser",
        BOOKTITLE = MMMod14,
        YEAR = "2014",
        PAGES = "II: 398-401",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242597"}

@inproceedings{bb247751,
        AUTHOR = "Lin, Y.T. and Tsai, T.H. and Hu, M.C. and Cheng, W.H. and Wu, J.L.",
        TITLE = "Semantic Based Background Music Recommendation for Home Videos",
        BOOKTITLE = MMMod14,
        YEAR = "2014",
        PAGES = "II: 283-290",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242598"}

@inproceedings{bb247752,
        AUTHOR = "Shamma, D.A. and Kennedy, L. and Churchill, E.F.",
        TITLE = "Watching and talking: media content as social nexus",
        BOOKTITLE = ICMR12,
        YEAR = "2012",
        PAGES = "12",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242599"}

@inproceedings{bb247753,
        AUTHOR = "Nowak, S. and Paduschek, R. and Kuhhirt, U.",
        TITLE = "Photo summary: automated selection of representative photos from a
digital collection",
        BOOKTITLE = ICMR11,
        YEAR = "2011",
        PAGES = "75",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242600"}

@inproceedings{bb247754,
        AUTHOR = "Paduschek, R. and Nowak, S. and Kuhhirt, U.",
        TITLE = "Automated detection of errors and quality issues in audio-visual
content",
        BOOKTITLE = ICMR11,
        YEAR = "2011",
        PAGES = "74",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242601"}

@inproceedings{bb247755,
        AUTHOR = "Vretos, N. and Nikolaidis, N. and Pitas, I.",
        TITLE = "The use of Audio-Visual Description Profile in 3D video content
description",
        BOOKTITLE = "3DTV12",
        YEAR = "2012",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242602"}

@inproceedings{bb247756,
        AUTHOR = "Ta, A.P. and Ben, M. and Gravier, G.",
        TITLE = "Improving Cluster Selection and Event Modeling in Unsupervised Mining
for Automatic Audiovisual Video Structuring",
        BOOKTITLE = MMMod12,
        YEAR = "2012",
        PAGES = "529-540",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242603"}

@inproceedings{bb247757,
        AUTHOR = "Muhling, M. and Ewerth, R. and Freisleben, B.",
        TITLE = "Improving Cross-Domain Concept Detection via Object-Based Features",
        BOOKTITLE = CAIP15,
        YEAR = "2015",
        PAGES = "II:359-370",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242604"}

@inproceedings{bb247758,
        AUTHOR = "Muhling, M. and Ewerth, R. and Freisleben, B.",
        TITLE = "On the Spatial Extents of SIFT Descriptors for Visual Concept Detection",
        BOOKTITLE = CVS11,
        YEAR = "2011",
        PAGES = "71-80",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242605"}

@inproceedings{bb247759,
        AUTHOR = "Muhling, M. and Ewerth, R. and Zhou, J. and Freisleben, B.",
        TITLE = "Multimodal Video Concept Detection via Bag of Auditory Words and
Multiple Kernel Learning",
        BOOKTITLE = MMMod12,
        YEAR = "2012",
        PAGES = "40-50",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242606"}

@inproceedings{bb247760,
        AUTHOR = "Gianni, F. and Pinquier, J. and Irisa, E.K.",
        TITLE = "ACADI showcase: Automatic character indexing in audiovisual document",
        BOOKTITLE = CIVR07,
        YEAR = "2007",
        PAGES = "109-112",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242607"}

@inproceedings{bb247761,
        AUTHOR = "Putthividhy, D. and Attias, H.T. and Nagarajan, S.S.",
        TITLE = "Topic regression multi-modal Latent Dirichlet Allocation for image
annotation",
        BOOKTITLE = CVPR10,
        YEAR = "2010",
        PAGES = "3408-3415",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242608"}

@inproceedings{bb247762,
        AUTHOR = "Jung, K.H. and Choi, S.H. and Kim, H.S. and Hur, N.H. and Kim, J.K.",
        TITLE = "Caption insertion method for 3D broadcasting service",
        BOOKTITLE = "3DTV10",
        YEAR = "2010",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242609"}

@inproceedings{bb247763,
        AUTHOR = "Pramod, S.K. and Jawahar, C.V. and Zisserman, A.",
        TITLE = "Subtitle-free Movie to Script Alignment",
        BOOKTITLE = BMVC09,
        YEAR = "2009",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242610"}

@inproceedings{bb247764,
        AUTHOR = "Zeng, Z. and Liang, W. and Li, H.P. and Zhang, S.W.",
        TITLE = "A Novel Video Classification Method Based on Hybrid
Generative/Discriminative Models",
        BOOKTITLE = SSPR08,
        YEAR = "2008",
        PAGES = "705-713",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242611"}

@inproceedings{bb247765,
        AUTHOR = "Zhu, Y.Y. and Ming, Z. and Huang, Q.A.",
        TITLE = "SVM-Based Audio Classification for Content- Based Multimedia Retrieval",
        BOOKTITLE = MCAM07,
        YEAR = "2007",
        PAGES = "474-482",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242612"}

@inproceedings{bb247766,
        AUTHOR = "Goldmann, L. and Samour, A. and Karaman, M. and Sikora, T.",
        TITLE = "Extracting High Level Semantics by Means of Speech, Audio, and Image
Primitives in Surveillance Applications",
        BOOKTITLE = ICIP06,
        YEAR = "2006",
        PAGES = "2397-2400",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242613"}

@inproceedings{bb247767,
        AUTHOR = "Luo, J. and Caputo, B. and Zweig, A. and Bach, J.H. and Anemuller, J.",
        TITLE = "Object Category Detection Using Audio-Visual Cues",
        BOOKTITLE = CVS08,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242614"}

@inproceedings{bb247768,
        AUTHOR = "Caputo, B. and Wallraven, C. and Nilsback, M.E.",
        TITLE = "Object categorization via local kernels",
        BOOKTITLE = ICPR04,
        YEAR = "2004",
        PAGES = "II: 132-135",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242615"}

@inproceedings{bb247769,
        AUTHOR = "Schauer, C. and Gross, H.M.",
        TITLE = "A Computational Model of Early Auditory-Visual Integration",
        BOOKTITLE = DAGM03,
        YEAR = "2003",
        PAGES = "362-369",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242616"}

@inproceedings{bb247770,
        AUTHOR = "Fu, T.Y. and Liu, X.X. and Liang, L.H. and Pi, X.B. and Nefian, A.V.",
        TITLE = "A audio-visual speaker identification using coupled hidden Markov
models",
        BOOKTITLE = ICIP03,
        YEAR = "2003",
        PAGES = "III: 29-32",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242617"}

@inproceedings{bb247771,
        AUTHOR = "Yemez, Y. and Kanak, A. and Erzin, E. and Tekalp, A.M.",
        TITLE = "Multimodal speaker identification with audio-video processing",
        BOOKTITLE = ICIP03,
        YEAR = "2003",
        PAGES = "III: 5-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242618"}

@inproceedings{bb247772,
        AUTHOR = "Sugano, M. and Isaksson, R. and Nakajima, Y. and Yanagihara, H.",
        TITLE = "Shot genre classification using compressed audio-visual features",
        BOOKTITLE = ICIP03,
        YEAR = "2003",
        PAGES = "II: 17-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242619"}

@inproceedings{bb247773,
        AUTHOR = "Moncrieff, S. and Venkatesh, S. and Dorai, C.",
        TITLE = "Horror film genre typing and scene labeling via audio analysis",
        BOOKTITLE = "ICME03",
        YEAR = "2003",
        PAGES = "I: 193-196",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242620"}

@inproceedings{bb247774,
        AUTHOR = "Moncrieff, S. and Dorai, C. and Venkatesh, S.",
        TITLE = "Affect computing in film through sound energy dynamics",
        BOOKTITLE = "ACMMM01",
        YEAR = "2001",
        PAGES = "525-527",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242621"}

@inproceedings{bb247775,
        AUTHOR = "Wachsmuth, S. and Sagerer, G.",
        TITLE = "Integrated analysis of speech and images as a probabilistic decoding
process",
        BOOKTITLE = ICPR02,
        YEAR = "2002",
        PAGES = "II: 588-592",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242622"}

@inproceedings{bb247776,
        AUTHOR = "Kulesh, V. and Petrushin, V.A. and Sethi, I.K.",
        TITLE = "Video clip recognition using joint audio-visual processing model",
        BOOKTITLE = ICPR02,
        YEAR = "2002",
        PAGES = "I: 500-503",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242623"}

@inproceedings{bb247777,
        AUTHOR = "Miyamori, H.",
        TITLE = "Improving accuracy in behaviour identification for content-based
retrieval by using audio and video information",
        BOOKTITLE = ICPR02,
        YEAR = "2002",
        PAGES = "II: 826-830",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242624"}

@inproceedings{bb247778,
        AUTHOR = "de Santo, M. and Percannella, G. and Sansone, C. and Vento, M.",
        TITLE = "Classifying audio of movies by a multi-expert system",
        BOOKTITLE = CIAP01,
        YEAR = "2001",
        PAGES = "386-391",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242625"}

@inproceedings{bb247779,
        AUTHOR = "Albiol, A. and Torres, L. and Delp, E.J.",
        TITLE = "Video preprocessing for audiovisual indexing",
        BOOKTITLE = Southwest02,
        YEAR = "2002",
        PAGES = "57-61",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242626"}

@inproceedings{bb247780,
        AUTHOR = "Bakker, E.M. and Lew, M.S.",
        TITLE = "Semantic Video Retrieval Using Audio Analysis",
        BOOKTITLE = CIVR02,
        YEAR = "2002",
        PAGES = "271-277",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242627"}

@inproceedings{bb247781,
        AUTHOR = "Kim, K. and Choi, J. and Kim, N. and Kim, P.K.",
        TITLE = "Extracting Semantic Information from Basketball Video Based on
Audio-Visual Features",
        BOOKTITLE = CIVR02,
        YEAR = "2002",
        PAGES = "278-288",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242628"}

@inproceedings{bb247782,
        AUTHOR = "Fisher, J.W. and Darrell, T.J.",
        TITLE = "Probabalistic Models and Informative Subspaces for Audiovisual
Correspondence",
        BOOKTITLE = ECCV02,
        YEAR = "2002",
        PAGES = "III: 592 ff.",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242629"}

@inproceedings{bb247783,
        AUTHOR = "Chu, S.M. and Huang, T.S.",
        TITLE = "Audio-Visual Speech Fusion Using Coupled Hidden Markov Models",
        BOOKTITLE = MSCSAS07,
        YEAR = "2007",
        PAGES = "1-2",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242630"}

@inproceedings{bb247784,
        AUTHOR = "Naphade, M.R. and Garg, A. and Huang, T.S.",
        TITLE = "Audio-Visual Event Detection using Duration Dependent Input Output
Markov Models",
        BOOKTITLE = CBAIVL01,
        YEAR = "2001",
        PAGES = "30",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242631"}

@inproceedings{bb247785,
        AUTHOR = "Alatan, A.A.",
        TITLE = "Automatic Multi-modal Dialogue Scene Indexing",
        BOOKTITLE = ICIP01,
        YEAR = "2001",
        PAGES = "III: 374-377",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242632"}

@inproceedings{bb247786,
        AUTHOR = "Sundaram, H. and Chang, S.F.",
        TITLE = "Video Scene Segmentation Using Video and Audio Features",
        BOOKTITLE = ICME00,
        YEAR = "2000",
        PAGES = "TP10",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242633"}

@inproceedings{bb247787,
        AUTHOR = "Smith, J.R. and Li, C.S.",
        TITLE = "Adaptive Synthesis in Progressive Retrieval of Audio-Visual Data",
        BOOKTITLE = ICME00,
        YEAR = "2000",
        PAGES = "MP5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242634"}

@inproceedings{bb247788,
        AUTHOR = "Toklu, C. and Liou, S.P.",
        TITLE = "Image and Audio Sequence Visualization and Interaction Mechanisms for
Structured Video Browsing and Editing",
        BOOKTITLE = ICIP00,
        YEAR = "2000",
        PAGES = "Vol II: 263-266",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242635"}

@inproceedings{bb247789,
        AUTHOR = "Jiang, H. and Lin, T. and Zhang, H.J.",
        TITLE = "Video Segmentation with the Assistance of Audio Content Analysis",
        BOOKTITLE = ICME00,
        YEAR = "2000",
        PAGES = "WP5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242636"}

@inproceedings{bb247790,
        AUTHOR = "Pandit, M. and Kittler, J.V. and Li, Y. and Chilton, E.",
        TITLE = "A Comparative Study of Different Segmentation Approaches for Audio
Track Indexing",
        BOOKTITLE = ICPR00,
        YEAR = "2000",
        PAGES = "Vol II: 467-470",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242637"}

@inproceedings{bb247791,
        AUTHOR = "Huang, J.C. and Liu, Z. and Yao, W.",
        TITLE = "Integration of audio and visual information for content-based video
segmentation",
        BOOKTITLE = ICIP98,
        YEAR = "1998",
        PAGES = "III: 526-529",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242638"}

@inproceedings{bb247792,
        AUTHOR = "Saraceno, C. and Leonardi, R.",
        TITLE = "Identification of story units in audio-visual sequences by joint audio
and video processing",
        BOOKTITLE = ICIP98,
        YEAR = "1998",
        PAGES = "I: 363-367",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT242639"}

@article{bb247793,
        AUTHOR = "Ahanger, G. and Little, T.D.C.",
        TITLE = "A Survey of Technologies for Parsing and Indexing Digital Video",
        JOURNAL = JVCIR,
        VOLUME = "7",
        YEAR = "1996",
        NUMBER = "1",
        MONTH = "March",
        PAGES = "28-43",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823.html#TT242640"}

@article{bb247794,
        AUTHOR = "Boreczky, J.S. and Rowe, L.A.",
        TITLE = "Comparison of Video Shot Boundary Detection Techniques",
        JOURNAL = JEI,
        VOLUME = "5",
        YEAR = "1996",
        NUMBER = "2",
        MONTH = "April",
        PAGES = "122-128",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823.html#TT242641"}

@article{bb247795,
        AUTHOR = "Rowe, L.A. and Boreczky, J.S.",
        TITLE = "Comparison of Video Shot Boundary Detection Techniques",
        JOURNAL = SPIE,
        VOLUME = "2670",
        YEAR = "1996",
        PAGES = "170-179",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823.html#TT242641"}

@inproceedings{bb247796,
        AUTHOR = "Wilcox, L.D. and Boreczky, J.S.",
        TITLE = "Automatic video segmentation using hidden markov model",
        BOOKTITLE = US_Patent,
        YEAR = "2000",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823.html#TT242642"}

@article{bb247797,
        AUTHOR = "Gargi, U. and Kasturi, R. and Strayer, S.H.",
        TITLE = "Performance Characterization of Video-Shot-Change Detection Methods",
        JOURNAL = CirSysVideo,
        VOLUME = "10",
        YEAR = "2000",
        NUMBER = "1",
        MONTH = "February",
        PAGES = "1",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823.html#TT242643"}

@article{bb247798,
        AUTHOR = "Jeannin, S.",
        TITLE = "Motion descriptors for content-based video representation",
        JOURNAL = SP:IC,
        VOLUME = "16",
        YEAR = "2000",
        NUMBER = "1-2",
        MONTH = "September",
        PAGES = "59-85",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823.html#TT242644"}

@article{bb247799,
        AUTHOR = "Brunelli, R. and Mich, O. and Modena, C.M.",
        TITLE = "A Survey on the Automatic Indexing of Video Data",
        JOURNAL = JVCIR,
        VOLUME = "10",
        YEAR = "1999",
        NUMBER = "2",
        MONTH = "June",
        PAGES = "78-112",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823.html#TT242645"}

Last update:Mar 28, 2026 at 17:09:41