@inproceedings{bb219500,
        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#TT214500"}

@article{bb219501,
        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#TT214501"}

@inproceedings{bb219502,
        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#TT214501"}

@article{bb219503,
        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#TT214502"}

@article{bb219504,
        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#TT214503"}

@article{bb219505,
        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#TT214504"}

@inproceedings{bb219506,
        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#TT214505"}

@article{bb219507,
        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#TT214506"}

@article{bb219508,
        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#TT214507"}

@article{bb219509,
        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#TT214508"}

@article{bb219510,
        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#TT214509"}

@inproceedings{bb219511,
        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#TT214510"}

@inproceedings{bb219512,
        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#TT214511"}

@inproceedings{bb219513,
        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#TT214512"}

@article{bb219514,
        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#TT214513"}

@article{bb219515,
        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#TT214514"}

@article{bb219516,
        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#TT214515"}

@inproceedings{bb219517,
        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#TT214516"}

@inproceedings{bb219518,
        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#TT214517"}

@article{bb219519,
        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#TT214518"}

@article{bb219520,
        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#TT214519"}

@article{bb219521,
        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#TT214520"}

@inproceedings{bb219522,
        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#TT214521"}

@article{bb219523,
        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#TT214522"}

@article{bb219524,
        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#TT214523"}

@article{bb219525,
        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#TT214524"}

@inproceedings{bb219526,
        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#TT214525"}

@inproceedings{bb219527,
        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#TT214526"}

@inproceedings{bb219528,
        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#TT214527"}

@article{bb219529,
        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#TT214528"}

@article{bb219530,
        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#TT214529"}

@article{bb219531,
        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#TT214530"}

@article{bb219532,
        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#TT214531"}

@article{bb219533,
        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#TT214532"}

@article{bb219534,
        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#TT214533"}

@article{bb219535,
        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#TT214534"}

@article{bb219536,
        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#TT214535"}

@article{bb219537,
        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#TT214536"}

@article{bb219538,
        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#TT214537"}

@inproceedings{bb219539,
        AUTHOR = "Wu, W.H. and Luo, H.P. and Fang, B. and Wang, J.D. and Ouyang, W.L.",
        TITLE = "Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "10704-10713",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214538"}

@article{bb219540,
        AUTHOR = "Fang, H. and Xiong, P.F. and Xu, L. and Luo, W.H.",
        TITLE = "Transferring Image-CLIP to Video-Text Retrieval via Temporal
Relations",
        JOURNAL = MultMed,
        VOLUME = "25",
        YEAR = "2023",
        PAGES = "7772-7785",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214539"}

@inproceedings{bb219541,
        AUTHOR = "Huang, S. and Huang, S. and Lu, L. and Hu, P.F. and Wang, L.J. and Wang, X. and Kang, J. and Liang, W. and Jin, L.W. and Liu, Y.L. and Wu, Y.Q. and Liu, Y.",
        TITLE = "ICPR 2022 Challenge on Multi-Modal Subtitle Recognition",
        BOOKTITLE = "ICPR22",
        YEAR = "2022",
        PAGES = "4974-4980",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214540"}

@inproceedings{bb219542,
        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#TT214541"}

@inproceedings{bb219543,
        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#TT214542"}

@inproceedings{bb219544,
        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#TT214543"}

@inproceedings{bb219545,
        AUTHOR = "Wang, S.J. and Yao, Z.W. 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#TT214544"}

@inproceedings{bb219546,
        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#TT214545"}

@inproceedings{bb219547,
        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#TT214546"}

@inproceedings{bb219548,
        AUTHOR = "Wang, W.H. and Bao, H. and Dong, L. and Bjorck, J. and Peng, Z.L. and Liu, Q. and Aggarwal, K. and Mohammed, O.K. and Singhal, S. and Som, S. and Wei, F.",
        TITLE = "Image as a Foreign Language:
BEIT Pretraining for Vision and Vision-Language Tasks",
        BOOKTITLE = CVPR23,
        YEAR = "2023",
        PAGES = "19175-19186",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214547"}

@inproceedings{bb219549,
        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#TT214548"}

@inproceedings{bb219550,
        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#TT214549"}

@inproceedings{bb219551,
        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#TT214550"}

@inproceedings{bb219552,
        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#TT214551"}

@inproceedings{bb219553,
        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#TT214552"}

@inproceedings{bb219554,
        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#TT214553"}

@inproceedings{bb219555,
        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#TT214554"}

@inproceedings{bb219556,
        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#TT214555"}

@inproceedings{bb219557,
        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#TT214556"}

@inproceedings{bb219558,
        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#TT214557"}

@inproceedings{bb219559,
        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#TT214558"}

@inproceedings{bb219560,
        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#TT214559"}

@inproceedings{bb219561,
        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#TT214560"}

@inproceedings{bb219562,
        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#TT214561"}

@inproceedings{bb219563,
        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#TT214562"}

@inproceedings{bb219564,
        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#TT214563"}

@inproceedings{bb219565,
        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#TT214564"}

@inproceedings{bb219566,
        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#TT214565"}

@inproceedings{bb219567,
        AUTHOR = "Kim, D. and Sohn, K.H.",
        TITLE = "Static text region detection in video sequences using color and
orientation consistencies",
        BOOKTITLE = ICPR08,
        YEAR = "2008",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214566"}

@inproceedings{bb219568,
        AUTHOR = "Jung, C.K. and Lee, S.Y. and Kim, J.",
        TITLE = "Robust detection of key captions for sports video understanding",
        BOOKTITLE = ICIP08,
        YEAR = "2008",
        PAGES = "2520-2523",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214567"}

@inproceedings{bb219569,
        AUTHOR = "Aytar, Y. and Shah, M. and Luo, J.B.",
        TITLE = "Utilizing semantic word similarity measures for video retrieval",
        BOOKTITLE = CVPR08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214568"}

@inproceedings{bb219570,
        AUTHOR = "Kuettel, D. and Guillaumin, M. and Ferrari, V.",
        TITLE = "Combining Image-Level and Segment-Level Models for Automatic Annotation",
        BOOKTITLE = MMMod12,
        YEAR = "2012",
        PAGES = "16-28",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214569"}

@inproceedings{bb219571,
        AUTHOR = "Guillaumin, M. and Mensink, T. and Verbeek, J. and Schmid, C.",
        TITLE = "TagProp: Discriminative metric learning in nearest neighbor models for
image auto-annotation",
        BOOKTITLE = ICCV09,
        YEAR = "2009",
        PAGES = "309-316",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214570"}

@inproceedings{bb219572,
        AUTHOR = "Guillaumin, M. and Mensink, T. and Verbeek, J. and Schmid, C.",
        TITLE = "Automatic face naming with caption-based supervision",
        BOOKTITLE = CVPR08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214571"}

@inproceedings{bb219573,
        AUTHOR = "Mathe, S. and Fazly, A. and Dickinson, S.J. and Stevenson, S.",
        TITLE = "Learning the abstract motion semantics of verbs from captioned videos",
        BOOKTITLE = SLAM08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214572"}

@inproceedings{bb219574,
        AUTHOR = "Jamieson, M. and Dickinson, S.J. and Stevenson, S. and Wachsmuth, S.",
        TITLE = "Using Language to Drive the Perceptual Grouping of Local Image Features",
        BOOKTITLE = CVPR06,
        YEAR = "2006",
        PAGES = "II: 2102-2109",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214573"}

@inproceedings{bb219575,
        AUTHOR = "Stone, Z. and Zickler, T.E. and Darrell, T.J.",
        TITLE = "Autotagging Facebook: Social network context improves photo annotation",
        BOOKTITLE = InterNet08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214574"}

@inproceedings{bb219576,
        AUTHOR = "Aradhye, H. and Myers, G.",
        TITLE = "Exploiting Videotext Events for Improved Videotext Detection",
        BOOKTITLE = ICDAR07,
        YEAR = "2007",
        PAGES = "894-898",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214575"}

@inproceedings{bb219577,
        AUTHOR = "Wachenfeld, S. and Fleischer, S. and Jiang, X.Y.",
        TITLE = "A Multiple Classifier Approach for the Recognition of Screen-Rendered
Text",
        BOOKTITLE = CAIP07,
        YEAR = "2007",
        PAGES = "921-928",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214576"}

@inproceedings{bb219578,
        AUTHOR = "Wachenfeld, S. and Klein, H.U. and Jiang, X.Y.",
        TITLE = "Recognition of Screen-Rendered Text",
        BOOKTITLE = ICPR06,
        YEAR = "2006",
        PAGES = "II: 1086-1089",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214577"}

@inproceedings{bb219579,
        AUTHOR = "Wang, Y.W. and Su, L.M. and Ye, Q.X.",
        TITLE = "A Robust Caption Detecting Algorithm on MPEG Compressed Video",
        BOOKTITLE = MCAM07,
        YEAR = "2007",
        PAGES = "195-202",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214578"}

@inproceedings{bb219580,
        AUTHOR = "Wang, Y.K. and Chen, J.M.",
        TITLE = "Detecting Video Texts Using Spatial-Temporal Wavelet Transform",
        BOOKTITLE = ICPR06,
        YEAR = "2006",
        PAGES = "IV: 754-757",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214579"}

@inproceedings{bb219581,
        AUTHOR = "Ravulapalli, S.I. and Sarkar, S.",
        TITLE = "Association of Sound to Motion in Video using Perceptual Organization",
        BOOKTITLE = ICPR06,
        YEAR = "2006",
        PAGES = "I: 1216-1219",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214580"}

@inproceedings{bb219582,
        AUTHOR = "Velivelli, A. and Huang, T.S.",
        TITLE = "Automatic Video Annotation by Mining Speech Transcripts",
        BOOKTITLE = SLAM06,
        YEAR = "2006",
        PAGES = "115",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214581"}

@inproceedings{bb219583,
        AUTHOR = "Su, Y.M. and Hsieh, C.H.",
        TITLE = "A Novel Caption Extraction Scheme for Various Sports Captions",
        BOOKTITLE = ICPR06,
        YEAR = "2006",
        PAGES = "II: 1054-1057",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214582"}

@inproceedings{bb219584,
        AUTHOR = "Misra, C. and Sural, S.",
        TITLE = "Content Based Image and Video Retrieval Using Embedded Text",
        BOOKTITLE = ACCV06,
        YEAR = "2006",
        PAGES = "II:111-120",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214583"}

@inproceedings{bb219585,
        AUTHOR = "Natarajan, P. and Elmieh, B. and Schwartz, R. and Makhoul, J.",
        TITLE = "Videotext OCR using hidden Markov models",
        BOOKTITLE = ICDAR01,
        YEAR = "2001",
        PAGES = "947-951",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214584"}

@inproceedings{bb219586,
        AUTHOR = "Lefevre, S. and Vincent, N.",
        TITLE = "Caption localisation in video sequences by fusion of multiple detectors",
        BOOKTITLE = ICDAR05,
        YEAR = "2005",
        PAGES = "I: 106-110",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214585"}

@inproceedings{bb219587,
        AUTHOR = "Miyamori, H. and Nakamura, S. and Tanaka, K.",
        TITLE = "Automatic Indexing of Broadcast Content Using its Live Chat on the Web",
        BOOKTITLE = ICIP05,
        YEAR = "2005",
        PAGES = "III: 1248-1251",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214586"}

@inproceedings{bb219588,
        AUTHOR = "Kidron, E. and Schechner, Y.Y. and Elad, M.",
        TITLE = "Pixels that Sound",
        BOOKTITLE = CVPR05,
        YEAR = "2005",
        PAGES = "I: 88-95",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214587"}

@inproceedings{bb219589,
        AUTHOR = "Garcia Mateos, G. and Garcia Merono, A. and Vicente Chicote, C. and Ruiz, A. and Lopez de Teruel, P.E.",
        TITLE = "Time and Date OCR in CCTV Video",
        BOOKTITLE = CIAP05,
        YEAR = "2005",
        PAGES = "703-710",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214588"}

@inproceedings{bb219590,
        AUTHOR = "Xie, L.X. and Kennedy, L.S. and Chang, S.F. and Divakaran, A. and Sun, H. and Lin, C.Y.",
        TITLE = "Discovering meaningful multimedia patterns with audio-visual concepts
and associated text",
        BOOKTITLE = ICIP04,
        YEAR = "2004",
        PAGES = "IV: 2383-2386",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214589"}

@inproceedings{bb219591,
        AUTHOR = "Kutics, A. and O'Connell, C. and Nakagawa, A.",
        TITLE = "Segment-based image classifcaton using Layered-SOM",
        BOOKTITLE = ICIP13,
        YEAR = "2013",
        PAGES = "2430-2434",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214590"}

@inproceedings{bb219592,
        AUTHOR = "Kutics, A. and Nakagawa, A. and Arai, S. and Tanaka, H. and Ohtsuka, S.",
        TITLE = "Relating words and image segments on multiple layers for effective
browsing and retrieval",
        BOOKTITLE = ICIP04,
        YEAR = "2004",
        PAGES = "IV: 2203-2206",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214591"}

@inproceedings{bb219593,
        AUTHOR = "Nakagawa, A. and Kutics, A. and Tanaka, K. and Nakajima, M.",
        TITLE = "Combining words and object-based visual features in image retrieval",
        BOOKTITLE = CIAP03,
        YEAR = "2003",
        PAGES = "354-359",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214592"}

@inproceedings{bb219594,
        AUTHOR = "Kutics, A. and Nakagawa, A. and Nakajima, M.",
        TITLE = "Image retrieval via connecting words to salient objects",
        BOOKTITLE = ICIP03,
        YEAR = "2003",
        PAGES = "III: 17-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214593"}

@inproceedings{bb219595,
        AUTHOR = "Declerck, T. and Kuper, J. and Saggion, H. and Samiotou, A. and Wittenburg, P. and Contreras, J.",
        TITLE = "Contribution of NLP to the Content Indexing of Multimedia Documents",
        BOOKTITLE = CIVR04,
        YEAR = "2004",
        PAGES = "610-618",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214594"}

@inproceedings{bb219596,
        AUTHOR = "Wang, R.R. and Jin, W.J. and Wu, L.D.",
        TITLE = "A novel video caption detection approach using multi-frame integration",
        BOOKTITLE = ICPR04,
        YEAR = "2004",
        PAGES = "I: 449-452",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214595"}

@inproceedings{bb219597,
        AUTHOR = "Nakamura, A. and Yamamoto, K.",
        TITLE = "Caption text recognition in video frames by MAP matching",
        BOOKTITLE = ICDAR03,
        YEAR = "2003",
        PAGES = "650-655",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214596"}

@inproceedings{bb219598,
        AUTHOR = "Luo, B. and Tang, X. and Liu, J.Z. and Zhang, H.J.",
        TITLE = "Video caption detection and extraction using temporal information",
        BOOKTITLE = ICIP03,
        YEAR = "2003",
        PAGES = "I: 297-300",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214597"}

@inproceedings{bb219599,
        AUTHOR = "Hauptmann, A.G. and Jin, R. and Ng, T.D.",
        TITLE = "Multi-modal information retrieval
from broadcast video using OCR and speech recognition",
        BOOKTITLE = "JCDL02",
        YEAR = "2002",
        PAGES = "160-161",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat826.html#TT214598"}

Last update:Mar 25, 2024 at 16:07:51