@inproceedings{bb201400,
        AUTHOR = "Zheng, Y.T. and Neo, S.Y. and Chua, T.S. and Tian, Q.",
        TITLE = "The use of temporal, semantic and visual partitioning model for
efficient near-duplicate keyframe detection in large scale news corpus",
        BOOKTITLE = CIVR07,
        YEAR = "2007",
        PAGES = "409-416",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196555"}

@inproceedings{bb201401,
        AUTHOR = "Alaoui, E.M.I. and Mendez, A. and Ibn Elhaj, E. and Garcia, B.",
        TITLE = "Keyframes detection and analysis in vocal folds recordings using
hierarchical motion techniques and texture information",
        BOOKTITLE = ICIP09,
        YEAR = "2009",
        PAGES = "653-656",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196556"}

@inproceedings{bb201402,
        AUTHOR = "Browne, P. and Smeaton, A.F.",
        TITLE = "Video Retrieval Using Dialogue, Keyframe Similarity and Video Objects",
        BOOKTITLE = ICIP05,
        YEAR = "2005",
        PAGES = "III: 1208-1211",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196557"}

@inproceedings{bb201403,
        AUTHOR = "Zhao, Z.P. and Elgammal, A.M.",
        TITLE = "Information Theoretic Key Frame Selection for Action Recognition",
        BOOKTITLE = BMVC08,
        YEAR = "2008",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196558"}

@inproceedings{bb201404,
        AUTHOR = "Onder, O. and Gudukbay, U. and Ozguc, B. and Erdem, A.T. and Erdem, C.E. and Ozkan, M.K.",
        TITLE = "Keyframe Reduction Techniques for Motion Capture Data",
        BOOKTITLE = "3DTV08",
        YEAR = "2008",
        PAGES = "293-296",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196559"}

@inproceedings{bb201405,
        AUTHOR = "Jun, J.B. and Lee, S.Y. and He, Z.M. and Lee, M.J. and Jang, E.S.",
        TITLE = "Adaptive Key Frame Selection for Efficient Video Coding",
        BOOKTITLE = PSIVT07,
        YEAR = "2007",
        PAGES = "853-866",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196560"}

@inproceedings{bb201406,
        AUTHOR = "Repko, J. and Pollefeys, M.",
        TITLE = "3D models from extended uncalibrated video sequences:
Addressing key-frame selection and projective drift",
        BOOKTITLE = "3DIM05",
        YEAR = "2005",
        PAGES = "150-157",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196561"}

@inproceedings{bb201407,
        AUTHOR = "Stich, T. and Magnor, M.",
        TITLE = "Keyframe Animation from Video",
        BOOKTITLE = ICIP06,
        YEAR = "2006",
        PAGES = "2713-2716",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196562"}

@inproceedings{bb201408,
        AUTHOR = "Ghosh, N. and Bhanu, B.",
        TITLE = "A Psychological Adaptive Model For Video Analysis",
        BOOKTITLE = ICPR06,
        YEAR = "2006",
        PAGES = "IV: 346-349",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196563"}

@inproceedings{bb201409,
        AUTHOR = "Cuntoor, N.P. and Chellappa, R.",
        TITLE = "Key Frame-Based Activity Representation Using Antieigenvalues",
        BOOKTITLE = ACCV06,
        YEAR = "2006",
        PAGES = "II:499-508",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196564"}

@inproceedings{bb201410,
        AUTHOR = "Fauvet, B. and Bouthemy, P. and Gros, P. and Spindler, F.",
        TITLE = "A Geometrical Key-Frame Selection Method Exploiting Dominant Motion
Estimation in Video",
        BOOKTITLE = CIVR04,
        YEAR = "2004",
        PAGES = "419-427",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196565"}

@inproceedings{bb201411,
        AUTHOR = "Thormahlen, T. and Broszio, H. and Weissenfeld, A.",
        TITLE = "Keyframe Selection for Camera Motion and Structure Estimation from
Multiple Views",
        BOOKTITLE = ECCV04,
        YEAR = "2004",
        PAGES = "Vol I: 523-535",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196566"}

@inproceedings{bb201412,
        AUTHOR = "Loy, G. and Sullivan, J. and Carlsson, S.",
        TITLE = "Pose-based clustering in action sequences",
        BOOKTITLE = HLK03,
        YEAR = "2003",
        PAGES = "66-72",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196567"}

@inproceedings{bb201413,
        AUTHOR = "Erol, B. and Hull, J.J. and Graham, J. and Lee, D.S.",
        TITLE = "Prescient Paper:
Multimedia Document Creation with Document Image Matching",
        BOOKTITLE = ICPR04,
        YEAR = "2004",
        PAGES = "II: 675-678",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196568"}

@inproceedings{bb201414,
        AUTHOR = "Hull, J.J. and Erol, B. and Graham, J. and Lee, D.S.",
        TITLE = "Visualizing multimedia content on paper documents: components of key
frame selection for video paper",
        BOOKTITLE = ICDAR03,
        YEAR = "2003",
        PAGES = "389-392",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196569"}

@inproceedings{bb201415,
        AUTHOR = "Taskiran, C.M. and Pollak, I. and Bouman, C.A. and Delp, E.J.",
        TITLE = "Stochastic Models of Video Structure for Program Genre Detection",
        BOOKTITLE = VLBV03,
        YEAR = "2003",
        PAGES = "84-92",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196570"}

@inproceedings{bb201416,
        AUTHOR = "Dalal, N. and Horaud, R.",
        TITLE = "Indexing key positions between multiple videos",
        BOOKTITLE = Motion02,
        YEAR = "2002",
        PAGES = "65-71",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196571"}

@inproceedings{bb201417,
        AUTHOR = "Amer, A. and Dubois, E. and Mitiche, A.",
        TITLE = "Context-independent real-time event recognition:
application to key-image extraction",
        BOOKTITLE = ICPR02,
        YEAR = "2002",
        PAGES = "II: 945-948",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196572"}

@inproceedings{bb201418,
        AUTHOR = "Lee, H.C. and Kim, S.D.",
        TITLE = "Rate-constrained key frame selection using iteration",
        BOOKTITLE = ICIP02,
        YEAR = "2002",
        PAGES = "I: 928-931",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196573"}

@inproceedings{bb201419,
        AUTHOR = "Pickering, M.J. and Ruger, S.M. and Sinclair, D.",
        TITLE = "Video Retrieval by Feature Learning in Key Frames",
        BOOKTITLE = CIVR02,
        YEAR = "2002",
        PAGES = "309-317",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196574"}

@inproceedings{bb201420,
        AUTHOR = "Sanchez, J.M. and Binefa, X.",
        TITLE = "Color Normalization for Appearance Based Recognition of Video
Key-frames",
        BOOKTITLE = ICPR00,
        YEAR = "2000",
        PAGES = "Vol I: 815-818",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196575"}

@inproceedings{bb201421,
        AUTHOR = "Ouaret, M. and DuFaux, F. and Ebrahimi, T.",
        TITLE = "Fusion-based multiview distributed video coding",
        BOOKTITLE = VSSN06,
        YEAR = "2006",
        PAGES = "139-144",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196576"}

@inproceedings{bb201422,
        AUTHOR = "DuFaux, F.",
        TITLE = "Key Frame Selection to Represent a Video",
        BOOKTITLE = ICIP00,
        YEAR = "2000",
        PAGES = "Vol II: 275-278",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196577"}

@inproceedings{bb201423,
        AUTHOR = "Campisi, P. and Neri, A.",
        TITLE = "Synthetic Summaries of Video Sequences Using a Multiresolution Based
Key Frame Selection Technique in a Perceptually Uniform Color Space",
        BOOKTITLE = ICIP00,
        YEAR = "2000",
        PAGES = "Vol II: 299-302",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196578"}

@inproceedings{bb201424,
        AUTHOR = "Kang, E.K. and Kim, S.J. and Choi, J.S.",
        TITLE = "Video Retrieval based on Key Frame Extraction in Compressed Domain",
        BOOKTITLE = ICIP99,
        YEAR = "1999",
        PAGES = "III:260-264",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196579"}

@inproceedings{bb201425,
        AUTHOR = "Eren, P.E. and Tekalp, A.M.",
        TITLE = "Keyframe-based Bi-Directional 2-D Mesh Representation for Video Object
Tracking and Manipulation",
        BOOKTITLE = ICIP99,
        YEAR = "1999",
        PAGES = "II:968-972",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196580"}

@inproceedings{bb201426,
        AUTHOR = "Zhuang, Y.T. and Rui, Y. and Huang, T.S. and Mehrotra, S.",
        TITLE = "Adaptive key frame extraction using unsupervised clustering",
        BOOKTITLE = ICIP98,
        YEAR = "1998",
        PAGES = "I: 866-870",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196581"}

@inproceedings{bb201427,
        AUTHOR = "Gresle, P.O. and Huang, T.S.",
        TITLE = "Gisting of Video Documents:
A Key Frames Selection Algorithm Using Relative Activity Measure",
        BOOKTITLE = Visual97,
        YEAR = "1997",
        PAGES = "xx",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196582"}

@inproceedings{bb201428,
        AUTHOR = "Mitsunaga, T. and Yokoyama, T. and Totsuka, T.",
        TITLE = "Key extraction by image differentiation",
        BOOKTITLE = ICIP95,
        YEAR = "1995",
        PAGES = "II: 248-251",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825.html#TT196583"}

@article{bb201429,
        AUTHOR = "Kim, H.K.",
        TITLE = "Efficient Automatic Text Location Method and Content-Based Indexing and
Structuring of Video Database",
        JOURNAL = JVCIR,
        VOLUME = "7",
        YEAR = "1996",
        NUMBER = "4",
        MONTH = "December",
        PAGES = "336-344",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196584"}

@article{bb201430,
        AUTHOR = "Viswanathan, M. and Beigi, H.S.M. and Dharanipragada, S. and Maali, F. and Tritschler, A.",
        TITLE = "Multimedia Document Retrieval Using Speech and Speaker Recognition",
        JOURNAL = IJDAR,
        VOLUME = "2",
        YEAR = "1999",
        NUMBER = "4",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196585"}

@article{bb201431,
        AUTHOR = "Wu, V. and Manmatha, R. and Riseman, E.M.",
        TITLE = "TextFinder: An Automatic System to Detect and Recognize Text in Images",
        JOURNAL = PAMI,
        VOLUME = "21",
        YEAR = "1999",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "1224-1229",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196586"}

@inproceedings{bb201432,
        AUTHOR = "Wu, V. and Manmatha, R. and Riseman, E.M.",
        TITLE = "TextFinder",
        BOOKTITLE = UMass,
        YEAR = "1999",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196587"}

@inproceedings{bb201433,
        AUTHOR = "Wu, V. and Manmatha, R.",
        TITLE = "Extracting Text From Greyscale Images",
        BOOKTITLE = UMass,
        YEAR = "1995",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196588"}

@inproceedings{bb201434,
        AUTHOR = "Wu, V. and Manmatha, R. and Riseman, E.M.",
        TITLE = "Finding Text In Images",
        BOOKTITLE = UMass,
        YEAR = "1997",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196589"}

@article{bb201435,
        AUTHOR = "Zhong, Y. and Zhang, H.J. and Jain, A.K.",
        TITLE = "Automatic Caption Localization in Compressed Video",
        JOURNAL = PAMI,
        VOLUME = "22",
        YEAR = "2000",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "385-392",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196590"}

@inproceedings{bb201436,
        AUTHOR = "Jain, A.K. and Zhang, H.J. and Zhong, Y.",
        TITLE = "Automatic Caption Localization in Compressed Video",
        BOOKTITLE = ICIP99,
        YEAR = "1999",
        PAGES = "II:96-100",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196590"}

@article{bb201437,
        AUTHOR = "Kim, K.I. and Jung, K.C. and Park, S.H. and Kim, H.J.",
        TITLE = "Support vector machine-based text detection in digital video",
        JOURNAL = PR,
        VOLUME = "34",
        YEAR = "2001",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "527-529",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196591"}

@article{bb201438,
        AUTHOR = "Lee, C.W. and Jung, K.C. and Kim, H.J.",
        TITLE = "Automatic text detection and removal in video sequences",
        JOURNAL = PRL,
        VOLUME = "24",
        YEAR = "2003",
        NUMBER = "15",
        MONTH = "November",
        PAGES = "2607-2623",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196592"}

@article{bb201439,
        AUTHOR = "Welsh, S. and Conway, D.",
        TITLE = "Encoding Video Narration as Text",
        JOURNAL = RealTimeImg,
        VOLUME = "6",
        YEAR = "2000",
        NUMBER = "5",
        MONTH = "October",
        PAGES = "391-405",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196593"}

@inproceedings{bb201440,
        AUTHOR = "Syeda Mahmood, T.F. and Srinivasan, S. and Amir, A. and Ponceleon, D. and Blanchard, B. and Petkovic, D.",
        TITLE = "CueVideo: a system for cross-modal search and browse of video databases",
        BOOKTITLE = CVPR00,
        YEAR = "2000",
        PAGES = "II: 786-787",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196594"}

@article{bb201441,
        AUTHOR = "Adams, W.H. and Iyengar, G. and Lin, C.Y. and Naphade, M.R. and Neti, C. and Nock, H.J. and Smith, J.R.",
        TITLE = "Semantic Indexing of Multimedia Content Using Visual, Audio, and Text
Cues",
        JOURNAL = JASP,
        VOLUME = "2003",
        YEAR = "2003",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "170",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196595"}

@article{bb201442,
        AUTHOR = "Lyu, M.R. and Song, J.Q. and Cai, M.",
        TITLE = "A comprehensive method for multilingual video text detection,
localization, and extraction",
        JOURNAL = CirSysVideo,
        VOLUME = "15",
        YEAR = "2005",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "243-255",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196596"}

@article{bb201443,
        AUTHOR = "de Jong, F.M.G. and Westerveld, T. and de Vries, A.P.",
        TITLE = "Multimedia Search Without Visual Analysis:
The Value of Linguistic and Contextual Information",
        JOURNAL = CirSysVideo,
        VOLUME = "17",
        YEAR = "2007",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "365-371",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196597"}

@article{bb201444,
        AUTHOR = "Dimitrova, N. and Agnihotri, L. and Wei, G.",
        TITLE = "Video Classification Using Object Tracking",
        JOURNAL = IJIG,
        VOLUME = "1",
        YEAR = "2001",
        NUMBER = "3",
        MONTH = "July",
        PAGES = "487-505",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196598"}

@inproceedings{bb201445,
        AUTHOR = "Martino, J.A. and Dimitrova, N. and Elenbaas, J.H. and Rutgers, J.",
        TITLE = "Histogram method for characterizing video content",
        BOOKTITLE = US_Patent,
        YEAR = "2002",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196599"}

@inproceedings{bb201446,
        AUTHOR = "Wei, G. and Agnihotri, L. and Dimitrova, N.",
        TITLE = "TV Program Classification Based on Face and Text Processing",
        BOOKTITLE = ICME00,
        YEAR = "2000",
        PAGES = "III: 1345-1348",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196600"}

@inproceedings{bb201447,
        AUTHOR = "Agnihotri, L. and Dimitrova, N.",
        TITLE = "Text Detection for Video Analysis",
        BOOKTITLE = CBAIVL99,
        YEAR = "1999",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196601"}

@article{bb201448,
        AUTHOR = "Wang, J. and Zhou, Y.H.",
        TITLE = "An Unsupervised Approach for Video Text Localization",
        JOURNAL = IEICE,
        VOLUME = "E89-D",
        YEAR = "2006",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "1582-1585",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196602"}

@article{bb201449,
        AUTHOR = "Wang, F. and Ngo, C.W. and Pong, T.C.",
        TITLE = "Structuring low-quality videotaped lectures for cross-reference
browsing by video text analysis",
        JOURNAL = PR,
        VOLUME = "41",
        YEAR = "2008",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "3257-3269",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196603"}

@article{bb201450,
        AUTHOR = "Wang, Y. and Mei, T. and Gong, S.G. and Hua, X.S.",
        TITLE = "Combining global, regional and contextual features for automatic image
annotation",
        JOURNAL = PR,
        VOLUME = "42",
        YEAR = "2009",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "259-266",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196604"}

@inproceedings{bb201451,
        AUTHOR = "Wang, Y. and Gong, S.G.",
        TITLE = "Refining image annotation using contextual relations between words",
        BOOKTITLE = CIVR07,
        YEAR = "2007",
        PAGES = "425-432",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196605"}

@inproceedings{bb201452,
        AUTHOR = "Mei, T. and Wang, Y. and Hua, X.S. and Gong, S.G. and Li, S.P.",
        TITLE = "Coherent image annotation by learning semantic distance",
        BOOKTITLE = CVPR08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196606"}

@article{bb201453,
        AUTHOR = "Jiang, Y.G. and Ngo, C.W.",
        TITLE = "Visual word proximity and linguistics for semantic video indexing and
near-duplicate retrieval",
        JOURNAL = CVIU,
        VOLUME = "113",
        YEAR = "2009",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "405-414",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196607"}

@article{bb201454,
        AUTHOR = "Wei, X.Y. and Ngo, C.W. and Jiang, Y.G.",
        TITLE = "Selection of Concept Detectors for Video Search by Ontology-Enriched
Semantic Spaces",
        JOURNAL = MultMed,
        VOLUME = "10",
        YEAR = "2008",
        NUMBER = "6",
        MONTH = "October",
        PAGES = "1085-1096",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196608"}

@article{bb201455,
        AUTHOR = "Wei, X.Y. and Jiang, Y.G. and Ngo, C.W.",
        TITLE = "Concept-Driven Multi-Modality Fusion for Video Search",
        JOURNAL = CirSysVideo,
        VOLUME = "21",
        YEAR = "2011",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "62-73",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196609"}

@inproceedings{bb201456,
        AUTHOR = "Jiang, Y.G. and Ngo, C.W. and Yang, J.",
        TITLE = "Towards optimal bag-of-features for object categorization and semantic
video retrieval",
        BOOKTITLE = CIVR07,
        YEAR = "2007",
        PAGES = "494-501",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196610"}

@article{bb201457,
        AUTHOR = "Tsai, T.H. and Chen, Y.C. and Fang, C.L.",
        TITLE = "2DVTE: A two-directional videotext extractor for rapid and elaborate
design",
        JOURNAL = PR,
        VOLUME = "42",
        YEAR = "2009",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1496-1510",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196611"}

@article{bb201458,
        AUTHOR = "Zhao, X. and Lin, K.H. and Fu, Y. and Hu, Y. and Liu, Y. and Huang, T.S.",
        TITLE = "Text From Corners:
A Novel Approach to Detect Text and Caption in Videos",
        JOURNAL = IP,
        VOLUME = "20",
        YEAR = "2011",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "790-799",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196612"}

@article{bb201459,
        AUTHOR = "Mensink, T. and Verbeek, J. and Csurka, G.",
        TITLE = "Tree-Structured CRF Models for Interactive Image Labeling",
        JOURNAL = PAMI,
        VOLUME = "35",
        YEAR = "2013",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "476-489",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196613"}

@inproceedings{bb201460,
        AUTHOR = "Mensink, T. and Verbeek, J. and Csurka, G.",
        TITLE = "Learning structured prediction models for interactive image labeling",
        BOOKTITLE = CVPR11,
        YEAR = "2011",
        PAGES = "833-840",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196614"}

@inproceedings{bb201461,
        AUTHOR = "Mensink, T. and Verbeek, J. and Csurka, G.",
        TITLE = "Trans Media Relevance Feedback for Image Autoannotation",
        BOOKTITLE = BMVC10,
        YEAR = "2010",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196615"}

@inproceedings{bb201462,
        AUTHOR = "Mensink, T. and Verbeek, J.",
        TITLE = "Improving People Search Using Query Expansions:
How Friends Help to Find People",
        BOOKTITLE = ECCV08,
        YEAR = "2008",
        PAGES = "II: 86-99",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196616"}

@article{bb201463,
        AUTHOR = "Hsia, S.C. and Chang Jian, N.T.",
        TITLE = "Efficient scrolling videotext detection with adaptive temporal
differential approach",
        JOURNAL = IET-IPR,
        VOLUME = "8",
        YEAR = "2014",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "455-463",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196617"}

@article{bb201464,
        AUTHOR = "Jung, C. and Jiao, L.C.",
        TITLE = "Korean-English bilingual videotext recognition for news headline
generation based on a split-merge strategy",
        JOURNAL = RealTimeIP,
        VOLUME = "11",
        YEAR = "2016",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "167-177",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196618"}

@article{bb201465,
        AUTHOR = "Christie, G. and Laddha, A. and Agrawal, A. and Antol, S. and Goyal, Y. and Kochersberger, K. and Batra, D.",
        TITLE = "Resolving vision and language ambiguities together:
Joint segmentation & prepositional attachment resolution in 
captioned scenes",
        JOURNAL = CVIU,
        VOLUME = "163",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "101-112",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196619"}

@article{bb201466,
        AUTHOR = "Xu, Y. and Shan, S.Y. and Qiu, Z.M. and Jia, Z.P. and Shen, Z.Y. and Wang, Y.P. and Shi, M.F. and Chang, E.I.C.",
        TITLE = "End-to-end subtitle detection and recognition for videos in East
Asian languages via CNN ensemble",
        JOURNAL = SP:IC,
        VOLUME = "60",
        YEAR = "2018",
        NUMBER = "1",
        PAGES = "131-143",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196620"}

@article{bb201467,
        AUTHOR = "Chen, L.H. and Su, C.W.",
        TITLE = "Video Caption Extraction Using Spatio-Temporal Slices",
        JOURNAL = IJIG,
        VOLUME = "18",
        YEAR = "2018",
        NUMBER = "02",
        PAGES = "1850009",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196621"}

@article{bb201468,
        AUTHOR = "Dong, J. and Li, X. and Snoek, C.G.M.",
        TITLE = "Predicting Visual Features From Text for Image and Video Caption
Retrieval",
        JOURNAL = MultMed,
        VOLUME = "20",
        YEAR = "2018",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "3377-3388",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196622"}

@article{bb201469,
        AUTHOR = "Wong, K. and Chan, C.S. and Maungmaung, A.P.",
        TITLE = "Lightweight Authentication for MP4 Format Container Using Subtitle
Track",
        JOURNAL = IEICE,
        VOLUME = "E103-D",
        YEAR = "2020",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "2-10",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196623"}

@article{bb201470,
        AUTHOR = "Yan, H.Y. and Xu, X.",
        TITLE = "End-to-end video subtitle recognition via a deep Residual Neural
Network",
        JOURNAL = PRL,
        VOLUME = "131",
        YEAR = "2020",
        PAGES = "368-375",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196624"}

@article{bb201471,
        AUTHOR = "Liao, Z.Y. and Xian, Y.K. and Li, J.F. and Zhang, C.X. and Zhao, S.J.",
        TITLE = "Time-sync comments denoising via graph convolutional and contextual
encoding",
        JOURNAL = PRL,
        VOLUME = "135",
        YEAR = "2020",
        PAGES = "256-263",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196625"}

@article{bb201472,
        AUTHOR = "Yan, Z. and Yang, C. and Hu, L. and Zhao, J. and Jiang, L.C. and Gong, J.Y.",
        TITLE = "The Integration of Linguistic and Geospatial Features Using Global
Context Embedding for Automated Text Geocoding",
        JOURNAL = IJGI,
        VOLUME = "10",
        YEAR = "2021",
        NUMBER = "9",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196626"}

@article{bb201473,
        AUTHOR = "Malali, N. and Keller, Y.",
        TITLE = "Learning to Embed Semantic Similarity for Joint Image-Text Retrieval",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "10252-10260",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196627"}

@inproceedings{bb201474,
        AUTHOR = "Cheng, M.J. and Sun, Y.P. and Wang, L.C. and Zhu, X.W. and Yao, K. and Chen, J. and Song, G. and Han, J.Y. and Liu, J.T. and Ding, E. and Wang, J.D.",
        TITLE = "ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval",
        BOOKTITLE = CVPR22,
        YEAR = "2022",
        PAGES = "5174-5183",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196628"}

@inproceedings{bb201475,
        AUTHOR = "Wang, W.B. and Wang, R.P. and Chen, X.L.",
        TITLE = "Topic Scene Graph Generation by Attention Distillation from Caption",
        BOOKTITLE = ICCV21,
        YEAR = "2021",
        PAGES = "15880-15890",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196629"}

@inproceedings{bb201476,
        AUTHOR = "Wang, J. and Tang, J.H. and Yang, M.K. and Bai, X. and Luo, J.B.",
        TITLE = "Improving OCR-based Image Captioning by Incorporating Geometrical
Relationship",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "1306-1315",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196630"}

@inproceedings{bb201477,
        AUTHOR = "Wang, S.J. and Yao, Z. and Wang, R.P. and Wu, Z.Q. and Chen, X.L.",
        TITLE = "FAIEr: Fidelity and Adequacy Ensured Image Caption Evaluation",
        BOOKTITLE = CVPR21,
        YEAR = "2021",
        PAGES = "14045-14054",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196631"}

@inproceedings{bb201478,
        AUTHOR = "Yang, S.T. and Huang, K.H. and Howe, B.",
        TITLE = "JECL: Joint Embedding and Cluster Learning for Image-Text Pairs",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "8344-8351",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196632"}

@inproceedings{bb201479,
        AUTHOR = "Lei, J. and Yu, L.C. and Berg, T.L. and Bansal, M.",
        TITLE = "TVR: A Large-scale Dataset for Video-subtitle Moment Retrieval",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXI:447-463",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196633"}

@inproceedings{bb201480,
        AUTHOR = "Sariyildiz, M.B. and Perez, J. and Larlus, D.",
        TITLE = "Learning Visual Representations with Caption Annotations",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "VIII:153-170",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196634"}

@inproceedings{bb201481,
        AUTHOR = "Li, X.J. and Yin, X. and Li, C.Y. and Zhang, P.C. and Hu, X.W. and Zhang, L. and Wang, L.J. and Hu, H.D. and Dong, L. and Wei, F. and Choi, Y.J. and Gao, J.F.",
        TITLE = "OSCAR: Object-Semantics Aligned Pre-Training for Vision-Language Tasks",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXX: 121-137",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196635"}

@inproceedings{bb201482,
        AUTHOR = "Chen, Y.C. and Li, L.J. and Yu, L.C. and El Kholy, A. and Ahmed, F. and Gan, Z. and Cheng, Y. and Liu, J.J.",
        TITLE = "Uniter: Universal Image-Text Representation Learning",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXX: 104-120",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196636"}

@inproceedings{bb201483,
        AUTHOR = "Sawatzky, J. and Banerjee, D. and Gall, J.",
        TITLE = "Harvesting Information from Captions for Weakly Supervised Semantic
Segmentation",
        BOOKTITLE = CroMoL19,
        YEAR = "2019",
        PAGES = "4481-4490",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196637"}

@inproceedings{bb201484,
        AUTHOR = "Ramanishka, V. and Das, A. and Zhang, J. and Saenko, K.",
        TITLE = "Top-Down Visual Saliency Guided by Captions",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "3135-3144",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196638"}

@inproceedings{bb201485,
        AUTHOR = "Yan, F. and Mikolajczyk, K.",
        TITLE = "Deep correlation for matching images and text",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "3441-3450",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196639"}

@inproceedings{bb201486,
        AUTHOR = "Yan, F. and Mikolajczyk, K.",
        TITLE = "Leveraging High Level Visual Information for Matching Images and
Captions",
        BOOKTITLE = ACCV14,
        YEAR = "2014",
        PAGES = "I: 613-627",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196640"}

@inproceedings{bb201487,
        AUTHOR = "Cai, H.P. and Yan, F. and Mikolajczyk, K.",
        TITLE = "Learning weights for codebook in image classification and retrieval",
        BOOKTITLE = CVPR10,
        YEAR = "2010",
        PAGES = "2320-2327",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196641"}

@inproceedings{bb201488,
        AUTHOR = "Dawkins, M. and Perera, A. and Hoogs, A.",
        TITLE = "Real-time heads-up display detection in video",
        BOOKTITLE = AVSS14,
        YEAR = "2014",
        PAGES = "230-235",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196642"}

@inproceedings{bb201489,
        AUTHOR = "Wen, S. and Song, Y.H. and Zhang, Y.L. and Yu, Y.",
        TITLE = "A Phase-Based Approach for Caption Detection in Videos",
        BOOKTITLE = ACCV12,
        YEAR = "2012",
        PAGES = "II:408-419",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196643"}

@inproceedings{bb201490,
        AUTHOR = "Vilaplana, V. and Marques, F. and Leon, M. and Gasull, A.",
        TITLE = "Object detection and segmentation on a hierarchical region-based image
representation",
        BOOKTITLE = ICIP10,
        YEAR = "2010",
        PAGES = "3933-3936",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196644"}

@inproceedings{bb201491,
        AUTHOR = "Leon, M. and Vilaplana, V. and Gasull, A. and Marques, F.",
        TITLE = "Caption text extraction for indexing purposes using a hierarchical
region-based image model",
        BOOKTITLE = ICIP09,
        YEAR = "2009",
        PAGES = "1869-1872",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196645"}

@inproceedings{bb201492,
        AUTHOR = "Zhang, D.Q. and Bhagavathy, S. and Llach, J.",
        TITLE = "Temporally consistent caption detection in videos using a
spatiotemporal 3D method",
        BOOKTITLE = ICIP09,
        YEAR = "2009",
        PAGES = "1881-1884",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196646"}

@inproceedings{bb201493,
        AUTHOR = "Gupta, S. and Mooney, R.J.",
        TITLE = "Using closed captions to train activity recognizers that improve video
retrieval",
        BOOKTITLE = VCL-ViSU09,
        YEAR = "2009",
        PAGES = "30-37",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196647"}

@inproceedings{bb201494,
        AUTHOR = "Haubold, A. and Natsev, A.P.",
        TITLE = "Web-based information content and its application to concept-based
video retrieval",
        BOOKTITLE = CIVR08,
        YEAR = "2008",
        PAGES = "437-446",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196648"}

@inproceedings{bb201495,
        AUTHOR = "Zhang, J. and Goldgof, D. and Kasturi, R.",
        TITLE = "A new edge-based text verification approach for video",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196649"}

@inproceedings{bb201496,
        AUTHOR = "Bai, H.L. and Sun, J. and Naoi, S. and Katsuyama, Y. and Hotta, Y. and Fujimoto, K.",
        TITLE = "Video caption duration extraction",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196650"}

@inproceedings{bb201497,
        AUTHOR = "Chen, J.D. and Saund, E. and Wang, Y.Z.",
        TITLE = "Image objects and multi-scale features for annotation detection",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196651"}

@inproceedings{bb201498,
        AUTHOR = "Shivakumara, P. and Huang, W.H. and Tan, C.L.",
        TITLE = "Efficient video text detection using edge features",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196652"}

@inproceedings{bb201499,
        AUTHOR = "Huang, W.H. and Shivakumara, P. and Tan, C.L.",
        TITLE = "Detecting moving text in video using temporal information",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT196653"}

Last update:Dec 4, 2022 at 15:58:45