@inproceedings{bb245600,
AUTHOR = "Park, S. and Golshani, P.",
TITLE = "Video Composition and Retrieval",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP11",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat822.html#TT240450"}
@inproceedings{bb245601,
AUTHOR = "Loui, A.C. and Savakis, A.E.",
TITLE = "Automatic image event segmentation and quality screening for albuming
applications",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP10",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat822.html#TT240451"}
@inproceedings{bb245602,
AUTHOR = "Kurokawa, M.",
TITLE = "Representation and Retrieval of Video Scene by Using Object Actions and
Their Spatio-temporal Relationships",
BOOKTITLE = ICIP99,
YEAR = "1999",
PAGES = "II:86-90",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat822.html#TT240452"}
@inproceedings{bb245603,
AUTHOR = "Vinod, V.V.",
TITLE = "Activity Based Video Shot Retrieval and Ranking",
BOOKTITLE = ICPR98,
YEAR = "1998",
PAGES = "Vol I: 682-684",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat822.html#TT240453"}
@article{bb245604,
AUTHOR = "Swanberg, D. and Shu, C.F. and Jain, R.C.",
TITLE = "Knowledge-Guided Parsing in Video Databases",
JOURNAL = SPIE,
VOLUME = "1908",
YEAR = "1993",
MONTH = "February",
PAGES = "13-24",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat822.html#TT240454"}
@article{bb245605,
AUTHOR = "Saraceno, C. and Leonardi, R.",
TITLE = "Indexing audiovisual databases through joint audio and video processing",
JOURNAL = IJIST,
VOLUME = "9",
YEAR = "1999",
NUMBER = "5",
PAGES = "320-331",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240455"}
@inproceedings{bb245606,
AUTHOR = "Saraceno, C. and Leonardi, R.",
TITLE = "Identification of Successive Correlated Camera Shots Using Audio
and Video Information",
BOOKTITLE = ICIP97,
YEAR = "1997",
PAGES = "III: 166-169",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240456"}
@inproceedings{bb245607,
AUTHOR = "Saraceno, C. and Leonardi, R.",
TITLE = "Audio-visual processing for scene change detection",
BOOKTITLE = CIAP97,
YEAR = "1997",
PAGES = "II: 124-131",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240457"}
@article{bb245608,
AUTHOR = "Li, D.G. and Sethi, I.K. and Dimitrova, N. and McGee, T.",
TITLE = "Classification of general audio data for content-based retrieval",
JOURNAL = PRL,
VOLUME = "22",
YEAR = "2001",
NUMBER = "5",
MONTH = "April",
PAGES = "533-544",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240458"}
@article{bb245609,
AUTHOR = "Tsekeridou, S. and Pitas, I.",
TITLE = "Content-based video parsing and indexing based on audio-visual
interaction",
JOURNAL = CirSysVideo,
VOLUME = "11",
YEAR = "2001",
NUMBER = "4",
MONTH = "April",
PAGES = "522-535",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240459"}
@inproceedings{bb245610,
AUTHOR = "Tsekeridou, S. and Pitas, I.",
TITLE = "Speaker dependent video indexing based on audio-visual interaction",
BOOKTITLE = ICIP98,
YEAR = "1998",
PAGES = "I: 358-362",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240460"}
@inproceedings{bb245611,
AUTHOR = "Tsekeridou, S. and Krinidis, S. and Pitas, I.",
TITLE = "Scene Change Detection Based on Audio-Visual Analysis and Interaction",
BOOKTITLE = "WTRCV01",
YEAR = "2001",
PAGES = "214",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240461"}
@article{bb245612,
AUTHOR = "Kyperountas, M. and Kotropoulos, C. and Pitas, I.",
TITLE = "Enhanced Eigen-Audioframes for Audiovisual Scene Change Detection",
JOURNAL = MultMed,
VOLUME = "9",
YEAR = "2007",
NUMBER = "4",
PAGES = "785-797",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240462"}
@article{bb245613,
AUTHOR = "Gauvain, J.L. and Lamel, L. and Adda, G.",
TITLE = "Audio Partitioning and Transcription for Broadcast Data Indexation",
JOURNAL = MultToolApp,
VOLUME = "14",
YEAR = "2001",
NUMBER = "2",
MONTH = "June",
PAGES = "187-200",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240463"}
@article{bb245614,
AUTHOR = "Amir, A. and Srinivasan, S. and Efrat, A.",
TITLE = "Search the Audio, Browse the Video:
A Generic Paradigm for Video Collections",
JOURNAL = JASP,
VOLUME = "2003",
YEAR = "2003",
NUMBER = "2",
MONTH = "February",
PAGES = "209",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240464"}
@article{bb245615,
AUTHOR = "Beal, M.J. and Jojic, N. and Attias, H.T.",
TITLE = "A graphical model for audiovisual object tracking",
JOURNAL = PAMI,
VOLUME = "25",
YEAR = "2003",
NUMBER = "7",
MONTH = "July",
PAGES = "828-836",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240465"}
@inproceedings{bb245616,
AUTHOR = "Beal, M.J. and Attias, H.T. and Jojic, N.",
TITLE = "Audio-Video Sensor Fusion with Probabilistic Graphical Models",
BOOKTITLE = ECCV02,
YEAR = "2002",
PAGES = "I: 736 ff.",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240466"}
@inproceedings{bb245617,
AUTHOR = "Wu, P. and Li, Y. and Tretter, D.",
TITLE = "Scalable video summarization",
BOOKTITLE = US_Patent,
YEAR = "2006",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat823av1.html#TT240467"}
@article{bb245618,
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#TT240468"}
@inproceedings{bb245619,
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#TT240469"}
@inproceedings{bb245620,
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#TT240469"}
@inproceedings{bb245621,
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#TT240470"}
@inproceedings{bb245622,
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#TT240471"}
@inproceedings{bb245623,
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#TT240472"}
@article{bb245624,
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#TT240473"}
@article{bb245625,
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#TT240474"}
@article{bb245626,
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#TT240475"}
@inproceedings{bb245627,
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#TT240476"}
@inproceedings{bb245628,
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#TT240477"}
@inproceedings{bb245629,
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#TT240478"}
@inproceedings{bb245630,
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#TT240479"}
@inproceedings{bb245631,
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#TT240480"}
@inproceedings{bb245632,
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#TT240481"}
@inproceedings{bb245633,
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#TT240482"}
@article{bb245634,
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#TT240483"}
@article{bb245635,
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#TT240484"}
@article{bb245636,
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#TT240485"}
@inproceedings{bb245637,
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#TT240486"}
@article{bb245638,
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#TT240487"}
@article{bb245639,
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#TT240488"}
@inproceedings{bb245640,
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#TT240489"}
@inproceedings{bb245641,
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#TT240490"}
@article{bb245642,
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#TT240491"}
@article{bb245643,
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#TT240492"}
@inproceedings{bb245644,
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#TT240493"}
@article{bb245645,
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#TT240494"}
@article{bb245646,
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#TT240495"}
@article{bb245647,
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#TT240496"}
@article{bb245648,
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#TT240497"}
@article{bb245649,
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#TT240498"}
@article{bb245650,
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#TT240499"}
@inproceedings{bb245651,
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#TT240500"}
@inproceedings{bb245652,
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#TT240501"}
@article{bb245653,
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#TT240502"}
@inproceedings{bb245654,
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#TT240503"}
@inproceedings{bb245655,
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#TT240504"}
@article{bb245656,
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#TT240505"}
@inproceedings{bb245657,
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#TT240506"}
@article{bb245658,
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#TT240507"}
@article{bb245659,
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#TT240508"}
@inproceedings{bb245660,
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#TT240509"}
@inproceedings{bb245661,
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#TT240510"}
@inproceedings{bb245662,
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#TT240511"}
@inproceedings{bb245663,
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#TT240512"}
@inproceedings{bb245664,
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#TT240513"}
@inproceedings{bb245665,
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#TT240514"}
@inproceedings{bb245666,
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#TT240515"}
@inproceedings{bb245667,
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#TT240516"}
@inproceedings{bb245668,
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#TT240517"}
@inproceedings{bb245669,
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#TT240518"}
@inproceedings{bb245670,
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#TT240519"}
@inproceedings{bb245671,
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#TT240520"}
@inproceedings{bb245672,
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#TT240521"}
@inproceedings{bb245673,
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#TT240522"}
@inproceedings{bb245674,
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#TT240523"}
@inproceedings{bb245675,
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#TT240524"}
@inproceedings{bb245676,
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#TT240525"}
@inproceedings{bb245677,
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#TT240526"}
@inproceedings{bb245678,
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#TT240527"}
@inproceedings{bb245679,
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#TT240528"}
@inproceedings{bb245680,
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#TT240529"}
@inproceedings{bb245681,
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#TT240530"}
@inproceedings{bb245682,
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#TT240531"}
@inproceedings{bb245683,
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#TT240532"}
@inproceedings{bb245684,
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#TT240533"}
@inproceedings{bb245685,
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#TT240534"}
@inproceedings{bb245686,
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#TT240535"}
@inproceedings{bb245687,
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#TT240536"}
@inproceedings{bb245688,
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#TT240537"}
@inproceedings{bb245689,
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#TT240538"}
@inproceedings{bb245690,
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#TT240539"}
@inproceedings{bb245691,
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#TT240540"}
@inproceedings{bb245692,
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#TT240541"}
@inproceedings{bb245693,
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#TT240542"}
@inproceedings{bb245694,
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#TT240543"}
@inproceedings{bb245695,
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#TT240544"}
@inproceedings{bb245696,
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#TT240545"}
@inproceedings{bb245697,
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#TT240546"}
@inproceedings{bb245698,
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#TT240547"}
@inproceedings{bb245699,
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#TT240548"}
Last update:Jan 8, 2026 at 12:52:16