@inproceedings{bb218900,
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#TT213907"}
@inproceedings{bb218901,
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#TT213908"}
@inproceedings{bb218902,
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#TT213909"}
@inproceedings{bb218903,
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#TT213910"}
@inproceedings{bb218904,
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#TT213911"}
@inproceedings{bb218905,
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#TT213912"}
@article{bb218906,
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#TT213913"}
@article{bb218907,
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#TT213913"}
@article{bb218908,
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#TT213914"}
@inproceedings{bb218909,
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#TT213915"}
@inproceedings{bb218910,
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#TT213916"}
@inproceedings{bb218911,
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#TT213917"}
@article{bb218912,
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#TT213918"}
@article{bb218913,
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#TT213919"}
@inproceedings{bb218914,
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#TT213920"}
@article{bb218915,
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#TT213921"}
@article{bb218916,
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#TT213922"}
@article{bb218917,
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#TT213923"}
@article{bb218918,
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#TT213924"}
@article{bb218919,
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#TT213925"}
@article{bb218920,
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#TT213926"}
@article{bb218921,
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#TT213927"}
@article{bb218922,
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#TT213928"}
@article{bb218923,
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#TT213929"}
@article{bb218924,
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#TT213930"}
@article{bb218925,
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#TT213931"}
@inproceedings{bb218926,
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#TT213932"}
@inproceedings{bb218927,
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#TT213933"}
@inproceedings{bb218928,
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#TT213934"}
@inproceedings{bb218929,
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#TT213935"}
@inproceedings{bb218930,
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#TT213936"}
@inproceedings{bb218931,
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#TT213937"}
@inproceedings{bb218932,
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#TT213938"}
@inproceedings{bb218933,
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#TT213939"}
@inproceedings{bb218934,
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#TT213940"}
@inproceedings{bb218935,
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#TT213941"}
@inproceedings{bb218936,
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#TT213942"}
@article{bb218937,
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#TT213943"}
@article{bb218938,
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#TT213944"}
@article{bb218939,
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#TT213945"}
@article{bb218940,
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#TT213946"}
@article{bb218941,
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#TT213947"}
@inproceedings{bb218942,
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#TT213948"}
@inproceedings{bb218943,
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#TT213949"}
@inproceedings{bb218944,
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#TT213950"}
@inproceedings{bb218945,
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#TT213951"}
@article{bb218946,
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#TT213952"}
@article{bb218947,
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#TT213953"}
@inproceedings{bb218948,
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#TT213954"}
@inproceedings{bb218949,
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#TT213955"}
@inproceedings{bb218950,
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#TT213956"}
@inproceedings{bb218951,
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#TT213957"}
@inproceedings{bb218952,
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#TT213958"}
@inproceedings{bb218953,
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#TT213959"}
@inproceedings{bb218954,
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#TT213960"}
@inproceedings{bb218955,
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#TT213961"}
@inproceedings{bb218956,
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#TT213961"}
@inproceedings{bb218957,
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#TT213961"}
@inproceedings{bb218958,
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#TT213962"}
@article{bb218959,
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#TT213964"}
@inproceedings{bb218960,
AUTHOR = "Aodha, O.M. and Brostow, G.J. and Pollefeys, M.",
TITLE = "Segmenting video into classes of algorithm-suitability",
BOOKTITLE = CVPR10,
YEAR = "2010",
PAGES = "1054-1061",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213965"}
@article{bb218961,
AUTHOR = "Suresha, M. and Kuppa, S. and Raghukumar, D.S.",
TITLE = "A study on deep learning spatiotemporal models and feature extraction
techniques for video understanding",
JOURNAL = MultInfoRetr,
VOLUME = "9",
YEAR = "2020",
NUMBER = "2",
MONTH = "June",
PAGES = "81-101",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213966"}
@article{bb218962,
AUTHOR = "Kavoosifar, M.R. and Apiletti, D. and Baralis, E. and Garza, P. and Huet, B.",
TITLE = "Effective video hyperlinking by means of enriched feature sets and
monomodal query combinations",
JOURNAL = MultInfoRetr,
VOLUME = "9",
YEAR = "2020",
NUMBER = "3",
MONTH = "September",
PAGES = "215-227",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213967"}
@article{bb218963,
AUTHOR = "Tang, P.J. and Tan, Y.L. and Li, J.Z. and Tan, B.",
TITLE = "Translating video into language by enhancing visual and language
representations",
JOURNAL = JVCIR,
VOLUME = "72",
YEAR = "2020",
PAGES = "102875",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213968"}
@article{bb218964,
AUTHOR = "Yu, J. and Jiang, X. and Qin, Z. and Zhang, W. and Hu, Y. and Wu, Q.",
TITLE = "Learning Dual Encoding Model for Adaptive Visual Understanding in
Visual Dialogue",
JOURNAL = IP,
VOLUME = "30",
YEAR = "2021",
PAGES = "220-233",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213969"}
@article{bb218965,
AUTHOR = "Duan, J.H. and Xu, H. and Lin, X.Z. and Zhu, S.C. and Du, Y.Z.",
TITLE = "Multi-semantic long-range dependencies capturing for efficient video
representation learning",
JOURNAL = IVC,
VOLUME = "104",
YEAR = "2020",
PAGES = "103988",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213970"}
@article{bb218966,
AUTHOR = "Tan, H.L. and Zhu, H.Y. and Lim, J.H. and Tan, C.",
TITLE = "A comprehensive survey of procedural video datasets",
JOURNAL = CVIU,
VOLUME = "202",
YEAR = "2021",
PAGES = "103107",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213971"}
@article{bb218967,
AUTHOR = "Lin, J. and Gan, C. and Wang, K. and Han, S.",
TITLE = "TSM: Temporal Shift Module for Efficient and Scalable Video
Understanding on Edge Devices",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "5",
MONTH = "May",
PAGES = "2760-2774",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213972"}
@inproceedings{bb218968,
AUTHOR = "Lin, J. and Gan, C. and Han, S.",
TITLE = "TSM: Temporal Shift Module for Efficient Video Understanding",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "7082-7092",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213973"}
@article{bb218969,
AUTHOR = "Zhou, W. and Hou, Y. and Ouyang, K.W. and Zhou, S.L.",
TITLE = "Exploring complementary information of self-supervised pretext tasks
for unsupervised video pre-training",
JOURNAL = IET-CV,
VOLUME = "16",
YEAR = "2022",
NUMBER = "3",
PAGES = "255-265",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213974"}
@article{bb218970,
AUTHOR = "Li, Z.Q. and Wang, W.M. and Li, Z.Y. and Huang, Y.F. and Sato, Y.",
TITLE = "Spatio-Temporal Perturbations for Video Attribution",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "4",
MONTH = "April",
PAGES = "2043-2056",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213975"}
@article{bb218971,
AUTHOR = "Tao, L. and Wang, X.T. and Yamasaki, T.",
TITLE = "An Improved Inter-Intra Contrastive Learning Framework on
Self-Supervised Video Representation",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "8",
MONTH = "August",
PAGES = "5266-5280",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213976"}
@article{bb218972,
AUTHOR = "Huang, L. and Zhang, C. and Zhang, H.Y.",
TITLE = "Self-Adaptive Training: Bridging Supervised and Self-Supervised
Learning",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "3",
MONTH = "March",
PAGES = "1362-1377",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213977"}
@inproceedings{bb218973,
AUTHOR = "Huang, L. and You, S. and Zheng, M.K. and Wang, F. and Qian, C. and Yamasaki, T.",
TITLE = "Learning Where to Learn in Cross-View Self-Supervised Learning",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "14431-14440",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213978"}
@article{bb218974,
AUTHOR = "Hu, Y. and Yin, D.C. and Wang, Y.W. and Chen, Z.Z. and Luo, C.",
TITLE = "Decomposing style, content, and motion for videos",
JOURNAL = JVCIR,
VOLUME = "89",
YEAR = "2022",
PAGES = "103686",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213979"}
@article{bb218975,
AUTHOR = "Hong, M.Y. and Zhang, X.F. and Li, G.R. and Huang, Q.M.",
TITLE = "Fine-Grained Feature Generation for Generalized Zero-Shot Video
Classification",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "1599-1612",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213980"}
@article{bb218976,
AUTHOR = "Jin, X. and Feng, R. and Sun, S. and Feng, R. and He, T.Y. and Chen, Z.B.",
TITLE = "Semantical video coding: Instill static-dynamic clues into structured
bitstream for AI tasks",
JOURNAL = JVCIR,
VOLUME = "93",
YEAR = "2023",
PAGES = "103816",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213981"}
@article{bb218977,
AUTHOR = "Schiappa, M.C. and Rawat, Y.S. and Shah, M.",
TITLE = "Self-Supervised Learning for Videos: A Survey",
JOURNAL = Surveys,
VOLUME = "55",
YEAR = "2023",
NUMBER = "13s",
MONTH = "July",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213982"}
@article{bb218978,
AUTHOR = "Yang, X.M. and Xiong, S. and Wu, K.W. and Shan, D.F. and Xie, Z.",
TITLE = "Attentive spatial-temporal contrastive learning for self-supervised
video representation",
JOURNAL = IVC,
VOLUME = "137",
YEAR = "2023",
PAGES = "104765",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213983"}
@article{bb218979,
AUTHOR = "Miao, J.X. and Wei, Y.C. and Wang, X.H. and Yang, Y.",
TITLE = "Temporal Pixel-Level Semantic Understanding Through the VSPW Dataset",
JOURNAL = PAMI,
VOLUME = "45",
YEAR = "2023",
NUMBER = "9",
MONTH = "September",
PAGES = "11297-11308",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213984"}
@article{bb218980,
AUTHOR = "Hu, D. and Wang, Z. and Nie, F.P. and Wang, R. and Li, X.L.",
TITLE = "Self-Supervised Learning for Heterogeneous Audiovisual Scene Analysis",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "3534-3545",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213985"}
@article{bb218981,
AUTHOR = "Namitha, K. and Geetha, M. and Athi, N.",
TITLE = "An Improved Interaction Estimation and Optimization Method for
Surveillance Video Synopsis",
JOURNAL = MultMedMag,
VOLUME = "30",
YEAR = "2023",
NUMBER = "3",
MONTH = "July",
PAGES = "25-36",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213986"}
@article{bb218982,
AUTHOR = "Assefa, M. and Jiang, W. and Alemu, K.G. and Yilma, G. and Adhikari, D. and Ayalew, M. and Seid, A.M. and Erbad, A.",
TITLE = "Actor-Aware Self-Supervised Learning for Semi-Supervised Video
Representation Learning",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "11",
MONTH = "November",
PAGES = "6679-6692",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213987"}
@article{bb218983,
AUTHOR = "Hu, Y.F. and Gao, J.Y. and Xu, C.S.",
TITLE = "Learning Multi-Expert Distribution Calibration for Long-Tailed Video
Classification",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "555-567",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213988"}
@article{bb218984,
AUTHOR = "Chen, Z. and Wang, H.L. and Chen, C.W.",
TITLE = "Self-Supervised Video Representation Learning by Serial Restoration
With Elastic Complexity",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "2235-2248",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213989"}
@inproceedings{bb218985,
AUTHOR = "Tian, Y. and Lu, G. and Zhai, G.T. and Gao, Z.Y.",
TITLE = "Non-Semantics Suppressed Mask Learning for Unsupervised Video
Semantic Compression",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "13564-13576",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213990"}
@inproceedings{bb218986,
AUTHOR = "Li, K.C. and Wang, Y.L. and He, Y. and Li, Y.Z. and Wang, Y. and Wang, L.M. and Qiao, Y.",
TITLE = "UniFormerV2: Unlocking the Potential of Image ViTs for Video
Understanding",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "1632-1643",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213991"}
@inproceedings{bb218987,
AUTHOR = "Afham, M. and Shukla, S.N. and Poursaeed, O. and Zhang, P. and Shah, A. and Lim, S.",
TITLE = "Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for
Long-form Video Understanding",
BOOKTITLE = REDLCV23,
YEAR = "2023",
PAGES = "1181-1186",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213992"}
@inproceedings{bb218988,
AUTHOR = "Strafforello, O. and Schutte, K. and van Gemert, J.C.",
TITLE = "Are current long-term video understanding datasets long-term?",
BOOKTITLE = CVEU23,
YEAR = "2023",
PAGES = "2959-2968",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213993"}
@inproceedings{bb218989,
AUTHOR = "Zhao, Y.C. and Luo, C. and Tang, C.X. and Chen, D.D. and Codella, N. and Zha, Z.J.",
TITLE = "Streaming Video Model",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14602-14612",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213994"}
@inproceedings{bb218990,
AUTHOR = "Maiya, S.R. and Girish, S. and Ehrlich, M. and Wang, H.Y. and Lee, K.S. and Poirson, P. and Wu, P.X. and Wang, C. and Shrivastava, A.",
TITLE = "NIRVANA: Neural Implicit Representations of Videos with Adaptive
Networks and Autoregressive Patch-Wise Modeling",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14378-14387",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213995"}
@inproceedings{bb218991,
AUTHOR = "Zhang, Y.T. and Bai, Y. and Liu, C. and Wang, H. and Li, S. and Fu, Y.",
TITLE = "Frame Flexible Network",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10504-10513",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213996"}
@inproceedings{bb218992,
AUTHOR = "Dessalene, E. and Maynord, M. and Fermuller, C. and Aloimonos, Y.F.",
TITLE = "Therbligs in Action: Video Understanding through Motion Primitives",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10618-10626",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213997"}
@inproceedings{bb218993,
AUTHOR = "Zhao, Y. and Misra, I. and Krahenbuhl, P. and Girdhar, R.",
TITLE = "Learning Video Representations from Large Language Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6586-6597",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213998"}
@inproceedings{bb218994,
AUTHOR = "Wang, R. and Chen, D.D. and Wu, Z.X. and Chen, Y.P. and Dai, X. and Liu, M.C. and Yuan, L. and Jiang, Y.G.",
TITLE = "Masked Video Distillation: Rethinking Masked Feature Modeling for
Self-supervised Video Representation Learning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6312-6322",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT213999"}
@inproceedings{bb218995,
AUTHOR = "Yang, X.T. and Chu, F.J. and Feiszli, M. and Goyal, R. and Torresani, L. and Tran, D.",
TITLE = "Relational Space-Time Query in Long-Form Videos",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6398-6408",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT214000"}
@inproceedings{bb218996,
AUTHOR = "Foo, L.G. and Gong, J. and Fan, Z.P. and Liu, J.",
TITLE = "System-Status-Aware Adaptive Network for Online Streaming Video
Understanding",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10514-10523",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT214001"}
@inproceedings{bb218997,
AUTHOR = "Dong, S. and Hu, H.Z. and Lian, D.Z. and Luo, W.X. and Qian, Y.C. and Gao, S.H.",
TITLE = "Weakly Supervised Video Representation Learning with Unaligned Text
for Sequential Videos",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2437-2447",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT214002"}
@inproceedings{bb218998,
AUTHOR = "Wang, J. and Zhu, W.T. and Wang, P. and Yu, X. and Liu, L. and Omar, M. and Hamid, R.",
TITLE = "Selective Structured State-Spaces for Long-Form Video Understanding",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6387-6397",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT214003"}
@inproceedings{bb218999,
AUTHOR = "Zhang, H. and Liu, D. and Zheng, Q. and Su, B.",
TITLE = "Modeling Video as Stochastic Processes for Fine-Grained Video
Representation Learning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2225-2234",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT214004"}
Last update:Apr 10, 2024 at 09:54:40