@inproceedings{bb219300,
AUTHOR = "Ullah, N. and Mohanta, P.P.",
TITLE = "Thinking Hallucination for Video Captioning",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "IV:623-640",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214305"}
@inproceedings{bb219301,
AUTHOR = "Seo, P.H. and Nagrani, A. and Arnab, A. and Schmid, C.",
TITLE = "End-to-end Generative Pretraining for Multimodal Video Captioning",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "17938-17947",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214306"}
@inproceedings{bb219302,
AUTHOR = "Lin, K. and Li, L.J. and Lin, C.C. and Ahmed, F. and Gan, Z. and Liu, Z.C. and Lu, Y. and Wang, L.J.",
TITLE = "SwinBERT: End-to-End Transformers with Sparse Attention for Video
Captioning",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "17928-17937",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214307"}
@inproceedings{bb219303,
AUTHOR = "Shi, Y. and Yang, X. and Xu, H.Y. and Yuan, C.F. and Li, B. and Hu, W.M. and Zha, Z.J.",
TITLE = "EMScore: Evaluating Video Captioning via Coarse-Grained and
Fine-Grained Embedding Matching",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "17908-17917",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214308"}
@inproceedings{bb219304,
AUTHOR = "Chen, S.X. and Jiang, Y.G.",
TITLE = "Motion Guided Region Message Passing for Video Captioning",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1523-1532",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214309"}
@inproceedings{bb219305,
AUTHOR = "Joshi, P. and Saharia, C. and Singh, V. and Gautam, D. and Ramakrishnan, G. and Jyothi, P.",
TITLE = "A Tale of Two Modalities for Video Captioning",
BOOKTITLE = MMVAMTC19,
YEAR = "2019",
PAGES = "3708-3712",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214310"}
@inproceedings{bb219306,
AUTHOR = "Wang, T. and Zhang, R. and Lu, Z.C. and Zheng, F. and Cheng, R. and Luo, P.",
TITLE = "End-to-End Dense Video Captioning with Parallel Decoding",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "6827-6837",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214311"}
@inproceedings{bb219307,
AUTHOR = "Yang, B. and Zou, Y.X.",
TITLE = "Visual Oriented Encoder: Integrating Multimodal and Multi-Scale
Contexts for Video Captioning",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "188-195",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214312"}
@inproceedings{bb219308,
AUTHOR = "Perez Martin, J. and Bustos, B. and Perez, J.",
TITLE = "Attentive Visual Semantic Specialized Network for Video Captioning",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "5767-5774",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214313"}
@inproceedings{bb219309,
AUTHOR = "Olivastri, S. and Singh, G. and Cuzzolin, F.",
TITLE = "End-to-End Video Captioning",
BOOKTITLE = HVU19,
YEAR = "2019",
PAGES = "1474-1482",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214314"}
@inproceedings{bb219310,
AUTHOR = "Li, L. and Gong, B.",
TITLE = "End-to-End Video Captioning With Multitask Reinforcement Learning",
BOOKTITLE = WACV19,
YEAR = "2019",
PAGES = "339-348",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214315"}
@inproceedings{bb219311,
AUTHOR = "Wang, B. and Ma, L. and Zhang, W. and Liu, W.",
TITLE = "Reconstruction Network for Video Captioning",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7622-7631",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214316"}
@inproceedings{bb219312,
AUTHOR = "Li, Y. and Yao, T. and Pan, Y. and Chao, H. and Mei, T.",
TITLE = "Jointly Localizing and Describing Events for Dense Video Captioning",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7492-7500",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214317"}
@inproceedings{bb219313,
AUTHOR = "Wu, X. and Li, G. and Cao, Q. and Ji, Q. and Lin, L.",
TITLE = "Interpretable Video Captioning via Trajectory Structured Localization",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "6829-6837",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214318"}
@inproceedings{bb219314,
AUTHOR = "Wang, X. and Chen, W. and Wu, J. and Wang, Y. and Wang, W.Y.",
TITLE = "Video Captioning via Hierarchical Reinforcement Learning",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "4213-4222",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214319"}
@inproceedings{bb219315,
AUTHOR = "Zhou, L. and Zhou, Y. and Corso, J.J. and Socher, R. and Xiong, C.",
TITLE = "End-to-End Dense Video Captioning with Masked Transformer",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "8739-8748",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214320"}
@inproceedings{bb219316,
AUTHOR = "Yang, D. and Yuan, C.",
TITLE = "Hierarchical Context Encoding for Events Captioning in Videos",
BOOKTITLE = ICIP18,
YEAR = "2018",
PAGES = "1288-1292",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214321"}
@inproceedings{bb219317,
AUTHOR = "Shen, Z.Q. and Li, J.G. and Su, Z. and Li, M.J. and Chen, Y.R. and Jiang, Y.G. and Xue, X.Y.",
TITLE = "Weakly Supervised Dense Video Captioning",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "5159-5167",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214322"}
@inproceedings{bb219318,
AUTHOR = "Baraldi, L. and Grana, C. and Cucchiara, R.",
TITLE = "Hierarchical Boundary-Aware Neural Encoder for Video Captioning",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "3185-3194",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214323"}
@inproceedings{bb219319,
AUTHOR = "Pan, P.B. and Xu, Z.W. and Yang, Y. and Wu, F. and Zhuang, Y.T.",
TITLE = "Hierarchical Recurrent Neural Encoder for Video Representation with
Application to Captioning",
BOOKTITLE = CVPR16,
YEAR = "2016",
PAGES = "1029-1038",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214324"}
@inproceedings{bb219320,
AUTHOR = "Yu, H.N. and Wang, J. and Huang, Z.H. and Yang, Y. and Xu, W.",
TITLE = "Video Paragraph Captioning Using Hierarchical Recurrent Neural
Networks",
BOOKTITLE = CVPR16,
YEAR = "2016",
PAGES = "4584-4593",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214325"}
@inproceedings{bb219321,
AUTHOR = "Shin, A. and Ohnishi, K. and Harada, T.",
TITLE = "Beyond caption to narrative: Video captioning with multiple sentences",
BOOKTITLE = ICIP16,
YEAR = "2016",
PAGES = "3364-3368",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214326"}
@article{bb219322,
AUTHOR = "Vakali, A. and Hacid, M.S. and Elmagarmid, A.",
TITLE = "MPEG-7 based description schemes for multi-level video content
classification",
JOURNAL = IVC,
VOLUME = "22",
YEAR = "2004",
NUMBER = "5",
MONTH = "May",
PAGES = "367-378",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214327"}
@article{bb219323,
AUTHOR = "Fonseca, P.M. and Pereira, F.",
TITLE = "Automatic video summarization based on MPEG-7 descriptions",
JOURNAL = SP:IC,
VOLUME = "19",
YEAR = "2004",
NUMBER = "8",
MONTH = "September",
PAGES = "685-699",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214328"}
@article{bb219324,
AUTHOR = "Mrak, M. and Calic, J. and Kondoz, A.M.",
TITLE = "Fast analysis of scalable video for adaptive browsing interfaces",
JOURNAL = CVIU,
VOLUME = "113",
YEAR = "2009",
NUMBER = "3",
MONTH = "March",
PAGES = "425-434",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214329"}
@inproceedings{bb219325,
AUTHOR = "Calic, J. and Mrak, M. and Kondoz, A.M.",
TITLE = "Flexible generation of video summaries from layered video bit-streams",
BOOKTITLE = ICIP08,
YEAR = "2008",
PAGES = "2516-2519",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214330"}
@article{bb219326,
AUTHOR = "Herranz, L. and Martinez, J.M.",
TITLE = "An integrated approach to summarization and adaptation using
H.264/MPEG-4 SVC",
JOURNAL = SP:IC,
VOLUME = "24",
YEAR = "2009",
NUMBER = "6",
MONTH = "July",
PAGES = "499-509",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214331"}
@article{bb219327,
AUTHOR = "Herranz, L. and Martinez, J.M.",
TITLE = "On the use of hierarchical prediction structures for efficient summary
generation of H.264/AVC bitstreams",
JOURNAL = SP:IC,
VOLUME = "24",
YEAR = "2009",
NUMBER = "8",
MONTH = "September",
PAGES = "615-629",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214332"}
@article{bb219328,
AUTHOR = "Matos, N. and Pereira, F.",
TITLE = "Automatic creation and evaluation of MPEG-7 compliant summary
descriptions for generic audiovisual content",
JOURNAL = SP:IC,
VOLUME = "23",
YEAR = "2008",
NUMBER = "8",
MONTH = "September",
PAGES = "581-598",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214333"}
@article{bb219329,
AUTHOR = "Ren, J.C. and Jiang, J.M. and Feng, Y.",
TITLE = "Activity-driven content adaptation for effective video summarization",
JOURNAL = JVCIR,
VOLUME = "21",
YEAR = "2010",
NUMBER = "8",
MONTH = "November",
PAGES = "930-938",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214334"}
@article{bb219330,
AUTHOR = "Almeida, J. and Leite, N.J. and da Silva Torres, R.",
TITLE = "VISON: VIdeo Summarization for ONline applications",
JOURNAL = PRL,
VOLUME = "33",
YEAR = "2012",
NUMBER = "4",
MONTH = "March",
PAGES = "397-409",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214335"}
@inproceedings{bb219331,
AUTHOR = "Almeida, J. and Leite, N.J. and da Silva Torres, R.",
TITLE = "Comparison of video sequences with histograms of motion patterns",
BOOKTITLE = ICIP11,
YEAR = "2011",
PAGES = "3673-3676",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214336"}
@inproceedings{bb219332,
AUTHOR = "Almeida, J. and Leite, N.J. and da Silva Torres, R.",
TITLE = "Rapid Cut Detection on Compressed Video",
BOOKTITLE = CIARP11,
YEAR = "2011",
PAGES = "71-78",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214337"}
@article{bb219333,
AUTHOR = "Basavarajaiah, M. and Sharma, P.",
TITLE = "Survey of Compressed Domain Video Summarization Techniques",
JOURNAL = Surveys,
VOLUME = "52",
YEAR = "2019",
NUMBER = "6",
MONTH = "October",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214338"}
@inproceedings{bb219334,
AUTHOR = "Lee, J.H. and Kim, W.Y.",
TITLE = "Video Summarization and Retrieval System Using Face Recognition and
MPEG-7 Descriptors",
BOOKTITLE = CIVR04,
YEAR = "2004",
PAGES = "170-178",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214339"}
@inproceedings{bb219335,
AUTHOR = "Soysal, M. and Alatan, A.A.",
TITLE = "Combining MPEG-7 Based Visual Experts for Reaching Semantics",
BOOKTITLE = VLBV03,
YEAR = "2003",
PAGES = "66-75",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214340"}
@inproceedings{bb219336,
AUTHOR = "Divakaran, A. and Peker, K.A. and Radhakrishnan, R. and Xiong, Z.Y. and Cabasson, R.",
TITLE = "Video Summarization using MPEG-7 Motion Activity and Audio Descriptors",
BOOKTITLE = VideoMining03,
YEAR = "2003",
PAGES = "Chapter 4",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214341"}
@inproceedings{bb219337,
AUTHOR = "Sugano, M. and Nakajima, Y. and Yanagihara, H.",
TITLE = "Automated MPEG audio-video summarization and description",
BOOKTITLE = ICIP02,
YEAR = "2002",
PAGES = "I: 956-959",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214342"}
@inproceedings{bb219338,
AUTHOR = "Jaimes, A. and Echigo, T. and Teraguchi, M. and Satoh, F.",
TITLE = "Learning personalized video highlights from detailed MPEG-7 metadata",
BOOKTITLE = ICIP02,
YEAR = "2002",
PAGES = "I: 133-136",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214343"}
@inproceedings{bb219339,
AUTHOR = "Lin, C.Y. and Tseng, B.L. and Naphade, M.R. and Natsev, A.P. and Smith, J.R.",
TITLE = "VideoAL: A novel end-to-end MPEG-7 video automatic labeling system",
BOOKTITLE = ICIP03,
YEAR = "2003",
PAGES = "III: 53-56",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214344"}
@inproceedings{bb219340,
AUTHOR = "Kim, J.G. and Chang, H.S. and Kim, J.W. and Kim, H.M.",
TITLE = "Efficient Camera Motion Characterization for MPEG Video Indexing",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP11",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214345"}
@inproceedings{bb219341,
AUTHOR = "DeMenthon, D.F. and Megret, R.",
TITLE = "Spatio-temporal Segmentation of Video by
Hierarchical Mean Shift Analysis",
BOOKTITLE = UMD,
YEAR = "2002",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214346"}
@inproceedings{bb219342,
AUTHOR = "Megret, R. and DeMenthon, D.F.",
TITLE = "A Survey of Spatio-temporal Grouping Techniques",
BOOKTITLE = UMD,
YEAR = "2002",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214347"}
@inproceedings{bb219343,
AUTHOR = "DeMenthon, D.F. and Latecki, L.J. and Rosenfeld, A. and Stueckelberg, M.V.",
TITLE = "Relevance Ranking of Video Data using
Hidden Markov Model Distances and Polygon Simplification",
BOOKTITLE = UMD,
YEAR = "2001",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214348"}
@inproceedings{bb219344,
AUTHOR = "DeMenthon, D.F. and Kobla, V. and Doermann, D.",
TITLE = "Video Summarization by Curve Simplification",
BOOKTITLE = UMD,
YEAR = "1998",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214349"}
@inproceedings{bb219345,
AUTHOR = "Yoon, K. and DeMenthon, D.F. and Doermann, D.",
TITLE = "Event Detection from MPEG Video in the Compressed Domain",
BOOKTITLE = ICPR00,
YEAR = "2000",
PAGES = "Vol I: 819-822",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT214350"}
@article{bb219346,
AUTHOR = "Doulamis, A.D. and Doulamis, N.D. and Kollias, S.D.",
TITLE = "A fuzzy video content representation for video summarization and
content-based retrieval",
JOURNAL = SP,
VOLUME = "80",
YEAR = "2000",
NUMBER = "6",
MONTH = "June",
PAGES = "1049-1067",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214351"}
@article{bb219347,
AUTHOR = "Kollias, S.D. and Doulamis, N.D. and Doulamis, A.D.",
TITLE = "A fuzzy video content representation for video summarization and
content-based retrieval",
JOURNAL = SP,
VOLUME = "82",
YEAR = "2002",
NUMBER = "4",
MONTH = "April",
PAGES = "545",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214351"}
@article{bb219348,
AUTHOR = "Doulamis, N.D. and Doulamis, A.D. and Avrithis, Y.S. and Ntalianis, K.S. and Kollias, S.D.",
TITLE = "Efficient Summarization of Stereoscopic Video Sequences",
JOURNAL = CirSysVideo,
VOLUME = "10",
YEAR = "2000",
NUMBER = "4",
MONTH = "June",
PAGES = "501-157",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214352"}
@inproceedings{bb219349,
AUTHOR = "Ntalianis, K.S. and Doulamis, A.D. and Tsapatsoulis, N.",
TITLE = "Implicit visual concept modeling in image/video annotation",
BOOKTITLE = ARTEMIS10,
YEAR = "2010",
PAGES = "33-38",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214353"}
@inproceedings{bb219350,
AUTHOR = "Doulamis, A.D. and Ntalianis, K.S.",
TITLE = "On the Fly Semantic Annotation and Modelling of Multimedia",
BOOKTITLE = WSSIP09,
YEAR = "2009",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214354"}
@inproceedings{bb219351,
AUTHOR = "Doulamis, N.D. and Doulamis, A.D. and Avrithis, Y.S. and Kollias, S.D.",
TITLE = "Video content representation using optimal extraction of frames and
scenes",
BOOKTITLE = ICIP98,
YEAR = "1998",
PAGES = "I: 875-879",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214355"}
@article{bb219352,
AUTHOR = "Amir, A. and Ashour, G. and Srinivasan, S.",
TITLE = "Automatic generation of conference video proceedings",
JOURNAL = JVCIR,
VOLUME = "15",
YEAR = "2004",
NUMBER = "3",
MONTH = "September",
PAGES = "467-488",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214356"}
@article{bb219353,
AUTHOR = "Metze, F. and Ding, D. and Younessian, E. and Hauptmann, A.G.",
TITLE = "Beyond audio and video retrieval:
Topic-oriented multimedia summarization",
JOURNAL = MultInfoRetr,
VOLUME = "2",
YEAR = "2013",
NUMBER = "2",
MONTH = "June",
PAGES = "131-144",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214357"}
@inproceedings{bb219354,
AUTHOR = "Ding, D. and Metze, F. and Rawat, S. and Schulam, P.F. and Burger, S. and Younessian, E. and Bao, L. and Christel, M.G. and Hauptmann, A.G.",
TITLE = "Beyond audio and video retrieval: Towards multimedia summarization",
BOOKTITLE = ICMR12,
YEAR = "2012",
PAGES = "2",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214358"}
@article{bb219355,
AUTHOR = "Bian, J.W. and Yang, Y. and Zhang, H.W. and Chua, T.S.",
TITLE = "Multimedia Summarization for Social Events in Microblog Stream",
JOURNAL = MultMed,
VOLUME = "17",
YEAR = "2015",
NUMBER = "2",
MONTH = "February",
PAGES = "216-228",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214359"}
@article{bb219356,
AUTHOR = "Kuanar, S.K. and Ranga, K.B. and Chowdhury, A.S.",
TITLE = "Multi-View Video Summarization Using Bipartite Matching Constrained
Optimum-Path Forest Clustering",
JOURNAL = MultMed,
VOLUME = "17",
YEAR = "2015",
NUMBER = "8",
MONTH = "August",
PAGES = "1166-1173",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214360"}
@article{bb219357,
AUTHOR = "Tan, C.C. and Ngo, C.W.",
TITLE = "On the use of commonsense ontology for multimedia event recounting",
JOURNAL = MultInfoRetr,
VOLUME = "5",
YEAR = "2016",
NUMBER = "2",
MONTH = "June",
PAGES = "73-88",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214361"}
@article{bb219358,
AUTHOR = "Wu, F. and Fang, H. and Li, X. and Tang, S. and Lu, W. and Yang, Y. and Zhu, W. and Zhuang, Y.",
TITLE = "Aspect Learning for Multimedia Summarization via Nonparametric
Bayesian",
JOURNAL = CirSysVideo,
VOLUME = "26",
YEAR = "2016",
NUMBER = "10",
MONTH = "October",
PAGES = "1931-1942",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214362"}
@article{bb219359,
AUTHOR = "Jiang, Y.G. and Wu, Z.X. and Tang, J.H. and Li, Z.C. and Xue, X.Y. and Chang, S.F.",
TITLE = "Modeling Multimodal Clues in a Hybrid Deep Learning Framework for
Video Classification",
JOURNAL = MultMed,
VOLUME = "20",
YEAR = "2018",
NUMBER = "11",
MONTH = "November",
PAGES = "3137-3147",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214363"}
@article{bb219360,
AUTHOR = "Wu, Z.X. and Li, H.D. and Zheng, Y.B. and Xiong, C.M. and Jiang, Y.G. and Davis, L.S.",
TITLE = "A Coarse-to-Fine Framework for Resource Efficient Video Recognition",
JOURNAL = IJCV,
VOLUME = "129",
YEAR = "2021",
NUMBER = "11",
MONTH = "November",
PAGES = "2965-2977",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214364"}
@article{bb219361,
AUTHOR = "Tian, F. and Wang, Q. and Li, X. and Sun, N.",
TITLE = "Heterogeneous multimedia cooperative annotation based on multimodal
correlation learning",
JOURNAL = JVCIR,
VOLUME = "58",
YEAR = "2019",
PAGES = "544-553",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214365"}
@article{bb219362,
AUTHOR = "Du, X.T. and Yuan, J. and Hu, L. and Dai, Y.",
TITLE = "Description generation of open-domain videos incorporating multimodal
features and bidirectional encoder",
JOURNAL = VC,
VOLUME = "35",
YEAR = "2018",
NUMBER = "12",
MONTH = "December",
PAGES = "1703-1712",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214366"}
@article{bb219363,
AUTHOR = "Li, J. and Wong, Y. and Zhao, Q. and Kankanhalli, M.S.",
TITLE = "Video Storytelling: Textual Summaries for Events",
JOURNAL = MultMed,
VOLUME = "22",
YEAR = "2020",
NUMBER = "2",
MONTH = "February",
PAGES = "554-565",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214367"}
@article{bb219364,
AUTHOR = "Cascianelli, S. and Costante, G. and Devo, A. and Ciarfuglia, T.A. and Valigi, P. and Fravolini, M.L.",
TITLE = "The Role of the Input in Natural Language Video Description",
JOURNAL = MultMed,
VOLUME = "22",
YEAR = "2020",
NUMBER = "1",
MONTH = "January",
PAGES = "271-283",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214368"}
@article{bb219365,
AUTHOR = "Zhang, Y.Z. and Liu, Y. and Kang, W. and Zheng, Y.X.",
TITLE = "MAR-Net: Motion-Assisted Reconstruction Network for Unsupervised
Video Summarization",
JOURNAL = SPLetters,
VOLUME = "30",
YEAR = "2023",
PAGES = "1282-1286",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214369"}
@inproceedings{bb219366,
AUTHOR = "Bouritsas, G. and Koutras, P. and Zlatintsi, A. and Maragos, P.",
TITLE = "Multimodal Visual Concept Learning with Weakly Supervised Techniques",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "4914-4923",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214370"}
@inproceedings{bb219367,
AUTHOR = "Wang, J. and Wang, W. and Huang, Y. and Wang, L. and Tan, T.",
TITLE = "M3: Multimodal Memory Modelling for Video Captioning",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7512-7520",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214371"}
@inproceedings{bb219368,
AUTHOR = "Kang, S.H. and Kim, J.Y. and Choi, H. and Kim, S.J. and Yoo, C.D.",
TITLE = "Pivot Correlational Neural Network for Multimodal Video Categorization",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "XIV: 402-417",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214372"}
@inproceedings{bb219369,
AUTHOR = "Mazaheri, A. and Shah, M.",
TITLE = "Visual Text Correction",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "XIII: 159-175",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214373"}
@inproceedings{bb219370,
AUTHOR = "Rudinac, S. and Chua, T.S. and Diaz Ferreyra, N. and Friedland, G. and Gornostaja, T. and Huet, B. and Kaptein, R. and Linden, K. and Moens, M.F. and Peltonen, J. and Redi, M. and Schedl, M. and Shamma, D.A. and Smeaton, A. and Xie, L.X.",
TITLE = "Rethinking Summarization and Storytelling for Modern Social Multimedia",
BOOKTITLE = MMMod18,
YEAR = "2018",
PAGES = "I:632-644",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214374"}
@inproceedings{bb219371,
AUTHOR = "Hori, C. and Hori, T. and Lee, T.Y. and Zhang, Z.M. and Harsham, B. and Hershey, J.R. and Marks, T.K. and Sumi, K.",
TITLE = "Attention-Based Multimodal Fusion for Video Description",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "4203-4212",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214375"}
@inproceedings{bb219372,
AUTHOR = "Gupta, R.K. and Yang, Y.P.",
TITLE = "Leveraging Multi-modal Analyses and Online Knowledge Base for Video
Aboutness Generation",
BOOKTITLE = ISVC16,
YEAR = "2016",
PAGES = "II: 55-64",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214376"}
@inproceedings{bb219373,
AUTHOR = "Vallet, F. and Essid, S. and Carrive, J. and Richard, G.",
TITLE = "Robust visual features for the multimodal identification of
unregistered speakers in TV talk-shows",
BOOKTITLE = ICIP10,
YEAR = "2010",
PAGES = "1469-1472",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214377"}
@inproceedings{bb219374,
AUTHOR = "Bailer, W. and Thallinger, G.",
TITLE = "A framework for multimedia content abstraction and its application to
rushes exploration",
BOOKTITLE = CIVR07,
YEAR = "2007",
PAGES = "146-153",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214378"}
@inproceedings{bb219375,
AUTHOR = "Tesic, J. and Smith, J.R.",
TITLE = "Efficient Summarizing of Multimedia Archives Using Cluster Labeling",
BOOKTITLE = CIVR06,
YEAR = "2006",
PAGES = "518-520",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT214379"}
@inproceedings{bb219376,
AUTHOR = "Mauldin, M.L. and Smith, M.A. and Stevens, S.M. and Wactlar, H.D. and Christel, M.G. and Reddy, D.R.",
TITLE = "System and method for skimming digital audio/video data",
BOOKTITLE = US_Patent,
YEAR = "1997",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214380"}
@article{bb219377,
AUTHOR = "Almeida, J. and Leite, N.J. and da Silva Torres, R.",
TITLE = "Online video summarization on compressed domain",
JOURNAL = JVCIR,
VOLUME = "24",
YEAR = "2013",
NUMBER = "6",
MONTH = "August",
PAGES = "729-738",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214381"}
@article{bb219378,
AUTHOR = "Sreeja, M.U. and Kovoor, B.C.",
TITLE = "Towards genre-specific frameworks for video summarisation: A survey",
JOURNAL = JVCIR,
VOLUME = "62",
YEAR = "2019",
PAGES = "340-358",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214382"}
@article{bb219379,
AUTHOR = "Vivekraj, V.K. and Sen, D. and Raman, B.",
TITLE = "Video Skimming: Taxonomy and Comprehensive Survey",
JOURNAL = Surveys,
VOLUME = "52",
YEAR = "2019",
NUMBER = "5",
MONTH = "October",
PAGES = "Article No 106",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214383"}
@article{bb219380,
AUTHOR = "Kumar, K.",
TITLE = "EVS-DK: Event video skimming using deep keyframe",
JOURNAL = JVCIR,
VOLUME = "58",
YEAR = "2019",
PAGES = "345-352",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214384"}
@article{bb219381,
AUTHOR = "Silva, M.M. and Ramos, W.L.S. and Campos, M.F.M. and Nascimento, E.R.",
TITLE = "A Sparse Sampling-Based Framework for Semantic Fast-Forward of
First-Person Videos",
JOURNAL = PAMI,
VOLUME = "43",
YEAR = "2021",
NUMBER = "4",
MONTH = "April",
PAGES = "1438-1444",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214385"}
@inproceedings{bb219382,
AUTHOR = "Silva, M.M. and Ramos, W.L.S. and Ferreira, J.P.K. and Chamone, F. and Campos, M.F.M. and Nascimento, E.R.",
TITLE = "A Weighted Sparse Sampling and Smoothing Frame Transition Approach
for Semantic Fast-Forward First-Person Videos",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "2383-2392",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214386"}
@inproceedings{bb219383,
AUTHOR = "Silva, M.M. and Ramos, W.L.S. and Ferreira, J.P.K. and Campos, M.F.M. and Nascimento, E.R.",
TITLE = "Towards Semantic Fast-Forward and Stabilized Egocentric Videos",
BOOKTITLE = Egocentric16,
YEAR = "2016",
PAGES = "I: 557-571",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214387"}
@inproceedings{bb219384,
AUTHOR = "Ramos, W.L.S. and Silva, M.M. and Campos, M.F.M. and Nascimento, E.R.",
TITLE = "Fast-forward video based on semantic extraction",
BOOKTITLE = ICIP16,
YEAR = "2016",
PAGES = "3334-3338",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214388"}
@inproceedings{bb219385,
AUTHOR = "Ramos, W.L.S. and Silva, M.M. and Araujo, E. and Marcolino, L.S. and Nascimento, E.R.",
TITLE = "Straight to the Point: Fast-Forwarding Videos via Reinforcement
Learning Using Textual Data",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "10928-10937",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214389"}
@article{bb219386,
AUTHOR = "Sun, X.Y. and Wang, H.L. and He, B.",
TITLE = "MABAN: Multi-Agent Boundary-Aware Network for Natural Language Moment
Retrieval",
JOURNAL = IP,
VOLUME = "30",
YEAR = "2021",
PAGES = "5589-5599",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214390"}
@article{bb219387,
AUTHOR = "Lan, S. and Wang, Z. and Wei, E. and Roy Chowdhury, A.K. and Zhu, Q.",
TITLE = "Collaborative Multi-Agent Video Fast-Forwarding",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "1041-1054",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214391"}
@inproceedings{bb219388,
AUTHOR = "Lan, S. and Panda, R. and Zhu, Q. and Roy Chowdhury, A.K.",
TITLE = "FFNet: Video Fast-Forwarding via Reinforcement Learning",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "6771-6780",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214392"}
@inproceedings{bb219389,
AUTHOR = "Vivekraj, V.K. and Balasubramanian, R. and Sen, D.",
TITLE = "Vector R-ordering based selection of segments for video skimming",
BOOKTITLE = ICPR16,
YEAR = "2016",
PAGES = "871-876",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214393"}
@inproceedings{bb219390,
AUTHOR = "Christel, M.G. and Lin, W.H. and Maher, B.",
TITLE = "Evaluating audio skimming and frame rate acceleration for summarizing
BBC rushes",
BOOKTITLE = CIVR08,
YEAR = "2008",
PAGES = "407-416",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214394"}
@inproceedings{bb219391,
AUTHOR = "Sundaram, H. and Chang, S.F.",
TITLE = "Video skims: taxonomies and an optimal generation framework",
BOOKTITLE = ICIP02,
YEAR = "2002",
PAGES = "II: 21-24",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214395"}
@inproceedings{bb219392,
AUTHOR = "Sundaram, H. and Chang, S.F.",
TITLE = "Constrained Utility Maximizations for Generating Visual Skims",
BOOKTITLE = CBAIVL01,
YEAR = "2001",
PAGES = "124",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214396"}
@inproceedings{bb219393,
AUTHOR = "Ma, Y.F. and Zbang, H.J.",
TITLE = "A model of motion attention for video skimming",
BOOKTITLE = ICIP02,
YEAR = "2002",
PAGES = "I: 129-132",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214397"}
@inproceedings{bb219394,
AUTHOR = "di Lecce, V. and Dimauro, G. and Guerriero, A. and Impedovo, S. and Pirlo, G. and Salzo, A.",
TITLE = "Image basic features indexing techniques for video skimming",
BOOKTITLE = CIAP99,
YEAR = "1999",
PAGES = "715-720",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214398"}
@inproceedings{bb219395,
AUTHOR = "Smith, M.A. and Kanade, T.",
TITLE = "Video Skimming and Characterization through the Combination of
Image and Language Understanding Techniques",
BOOKTITLE = CVPR97,
YEAR = "1997",
PAGES = "775-781",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214399"}
@inproceedings{bb219396,
AUTHOR = "Kanade, T. and Smith, M.A.",
TITLE = "Video Skimming and Characterization through the Combination of
Image and Language Understanding Techniques",
BOOKTITLE = DARPA97,
YEAR = "1997",
PAGES = "357-366",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214399"}
@inproceedings{bb219397,
AUTHOR = "Kanade, T. and Smith, M.A.",
TITLE = "Video Skimming and Characterization through the Combination of
Image and Language Understanding Techniques",
BOOKTITLE = CMU-CS-TR,
YEAR = "1997",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214399"}
@inproceedings{bb219398,
AUTHOR = "Smith, M.A. and Kanade, T.",
TITLE = "Video Skimming for Quick Browsing based on Audio and
Image Characterization",
BOOKTITLE = CMU-CS-TR,
YEAR = "1995",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT214400"}
@article{bb219399,
AUTHOR = "Brostow, G.J. and Fauqueur, J. and Cipolla, R.",
TITLE = "Semantic object classes in video:
A high-definition ground truth database",
JOURNAL = PRL,
VOLUME = "30",
YEAR = "2009",
NUMBER = "2",
MONTH = "January",
PAGES = "88-97",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT214402"}
Last update:Apr 18, 2024 at 11:38:49