@inproceedings{bb177900,
        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#TT173224"}

@article{bb177901,
        AUTHOR = "Bian, J.W. and Yang, Y. and Zhang, H. 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#TT173225"}

@article{bb177902,
        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#TT173226"}

@article{bb177903,
        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#TT173227"}

@article{bb177904,
        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#TT173228"}

@article{bb177905,
        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#TT173229"}

@article{bb177906,
        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#TT173230"}

@article{bb177907,
        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#TT173231"}

@article{bb177908,
        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#TT173232"}

@article{bb177909,
        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#TT173233"}

@inproceedings{bb177910,
        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#TT173234"}

@inproceedings{bb177911,
        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#TT173235"}

@inproceedings{bb177912,
        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#TT173236"}

@inproceedings{bb177913,
        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#TT173237"}

@inproceedings{bb177914,
        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#TT173238"}

@inproceedings{bb177915,
        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#TT173239"}

@inproceedings{bb177916,
        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#TT173240"}

@inproceedings{bb177917,
        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#TT173241"}

@inproceedings{bb177918,
        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#TT173242"}

@inproceedings{bb177919,
        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#TT173243"}

@inproceedings{bb177920,
        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#TT173244"}

@article{bb177921,
        AUTHOR = "Li, Y. and Narayanan, S.S. and Kuo, C.C.J.",
        TITLE = "Adaptive Speaker Identification with Audio-Visual Cues for Movie Content
Analysis",
        JOURNAL = PRL,
        VOLUME = "25",
        YEAR = "2004",
        NUMBER = "7",
        MONTH = "May",
        PAGES = "777-791",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT173245"}

@article{bb177922,
        AUTHOR = "Li, Y. and Narayanan, S.S. and Kuo, C.C.J.",
        TITLE = "Content-Based Movie Analysis and Indexing Based on Audio-Visual Cues",
        JOURNAL = CirSysVideo,
        VOLUME = "14",
        YEAR = "2004",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "1073-1085",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT173246"}

@inproceedings{bb177923,
        AUTHOR = "Li, Y. and Narayanan, S.S. and Kuo, C.C.J.",
        TITLE = "Movie Content Analysis, Indexing and Skimming Via 
Multimodal Information",
        BOOKTITLE = VideoMining03,
        YEAR = "2003",
        PAGES = "Chapter 5",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT173247"}

@article{bb177924,
        AUTHOR = "Li, Y. and Kuo, C.C.J.",
        TITLE = "A robust video scene extraction approach to movie content abstraction",
        JOURNAL = IJIST,
        VOLUME = "13",
        YEAR = "2003",
        NUMBER = "5",
        PAGES = "236-244",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vsk1.html#TT173248"}

@article{bb177925,
        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#TT173249"}

@article{bb177926,
        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#TT173250"}

@article{bb177927,
        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#TT173251"}

@article{bb177928,
        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#TT173252"}

@article{bb177929,
        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#TT173253"}

@inproceedings{bb177930,
        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#TT173254"}

@inproceedings{bb177931,
        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#TT173255"}

@inproceedings{bb177932,
        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#TT173256"}

@inproceedings{bb177933,
        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#TT173257"}

@inproceedings{bb177934,
        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#TT173258"}

@inproceedings{bb177935,
        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#TT173259"}

@inproceedings{bb177936,
        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#TT173260"}

@inproceedings{bb177937,
        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#TT173261"}

@inproceedings{bb177938,
        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#TT173262"}

@inproceedings{bb177939,
        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#TT173263"}

@inproceedings{bb177940,
        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#TT173264"}

@inproceedings{bb177941,
        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#TT173265"}

@inproceedings{bb177942,
        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#TT173265"}

@inproceedings{bb177943,
        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#TT173265"}

@inproceedings{bb177944,
        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#TT173266"}

@article{bb177945,
        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#TT173268"}

@inproceedings{bb177946,
        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#TT173269"}

@article{bb177947,
        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#TT173270"}

@article{bb177948,
        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#TT173271"}

@article{bb177949,
        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#TT173272"}

@article{bb177950,
        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#TT173273"}

@article{bb177951,
        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#TT173274"}

@article{bb177952,
        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#TT173275"}

@inproceedings{bb177953,
        AUTHOR = "Duan, H.D. and Zhao, Y. and Xiong, Y.J. and Liu, W.T. and Lin, D.",
        TITLE = "Omni-sourced Webly-supervised Learning for Video Recognition",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XV:670-688",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173276"}

@inproceedings{bb177954,
        AUTHOR = "Jha, A. and Kumar, A. and Pande, S. and Banerjee, B. and Chaudhuri, S.",
        TITLE = "MT-UNET: A Novel U-Net Based Multi-Task Architecture For Visual Scene
Understanding",
        BOOKTITLE = ICIP20,
        YEAR = "2020",
        PAGES = "2191-2195",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173277"}

@inproceedings{bb177955,
        AUTHOR = "Diba, A. and Fayyaz, M. and Sharma, V. and Paluri, M. and Gall, J. and Stiefelhagen, R. and Van Gool, L.J.",
        TITLE = "Large Scale Holistic Video Understanding",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "V:593-610",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173278"}

@inproceedings{bb177956,
        AUTHOR = "Pont Tuset, J. and Uijlings, J. and Changpinyo, S. and Soricut, R. and Ferrari, V.",
        TITLE = "Connecting Vision and Language with Localized Narratives",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "V:647-664",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173279"}

@inproceedings{bb177957,
        AUTHOR = "Hu, A. and Cotter, F. and Mohan, N. and Gurau, C. and Kendall, A.",
        TITLE = "Probabilistic Future Prediction for Video Scene Understanding",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVI: 767-785",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173280"}

@inproceedings{bb177958,
        AUTHOR = "Mavroudi, E. and Haro, B.B. and Vidal, R.",
        TITLE = "Representation Learning on Visual-Symbolic Graphs for Video
Understanding",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XXIX: 71-90",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173281"}

@inproceedings{bb177959,
        AUTHOR = "Sener, F. and Singhania, D. and Yao, A.",
        TITLE = "Temporal Aggregate Representations for Long-range Video Understanding",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVI: 154-171",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173282"}

@inproceedings{bb177960,
        AUTHOR = "Kwon, H. and Kim, M. and Kwak, S. and Cho, M.",
        TITLE = "Motionsqueeze: Neural Motion Feature Learning for Video Understanding",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVI: 345-362",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173283"}

@inproceedings{bb177961,
        AUTHOR = "Tosi, F. and Aleotti, F. and Ramirez, P.Z. and Poggi, M. and Salti, S. and di Stefano, L. and Mattoccia, S.",
        TITLE = "Distilled Semantics for Comprehensive Scene Understanding from Videos",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "4653-4664",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173284"}

@inproceedings{bb177962,
        AUTHOR = "Piergiovanni, A.J. and Angelova, A. and Ryoo, M.S.",
        TITLE = "Evolving Losses for Unsupervised Video Representation Learning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "130-139",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173285"}

@inproceedings{bb177963,
        AUTHOR = "Xiong, Y. and Huang, Q. and Guo, L. and Zhou, H. and Zhou, B. and Lin, D.",
        TITLE = "A Graph-Based Framework to Bridge Movies and Synopses",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4591-4600",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173286"}

@inproceedings{bb177964,
        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#TT173287"}

@inproceedings{bb177965,
        AUTHOR = "Kanehira, A. and Takemoto, K. and Inayoshi, S. and Harada, T.",
        TITLE = "Multimodal Explanations by Predicting Counterfactuality in Videos",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "8586-8594",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173288"}

@inproceedings{bb177966,
        AUTHOR = "Kanehira, A. and Harada, T.",
        TITLE = "Learning to Explain With Complemental Examples",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "8595-8603",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173289"}

@inproceedings{bb177967,
        AUTHOR = "Zhou, L. and Kalantidis, Y. and Chen, X.L. and Corso, J.J. and Rohrbach, M.",
        TITLE = "Grounded Video Description",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "6571-6580",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173290"}

@inproceedings{bb177968,
        AUTHOR = "Liu, X.Y. and Lee, J.Y. and Jin, H.L.",
        TITLE = "Learning Video Representations From Correspondence Proposals",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "4268-4276",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173291"}

@inproceedings{bb177969,
        AUTHOR = "Alayrac, J.B. and Carreira, J. and Zisserman, A.",
        TITLE = "The Visual Centrifuge: Model-Free Layered Video Representations",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "2452-2461",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173292"}

@inproceedings{bb177970,
        AUTHOR = "Xiong, B. and Kalantidis, Y. and Ghadiyaram, D. and Grauman, K.",
        TITLE = "Less Is More: Learning Highlight Detection From Video Duration",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "1258-1267",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173293"}

@inproceedings{bb177971,
        AUTHOR = "Zhang, D. and Dai, X. and Wang, X. and Wang, Y.F. and Davis, L.S.",
        TITLE = "MAN: Moment Alignment Network for Natural Language Moment Retrieval via
Iterative Graph Adjustment",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "1247-1257",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173294"}

@inproceedings{bb177972,
        AUTHOR = "Fan, L. and Huang, W. and Gan, C. and Ermon, S. and Gong, B. and Huang, J.",
        TITLE = "End-to-End Learning of Motion Representation for Video Understanding",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6016-6025",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173295"}

@inproceedings{bb177973,
        AUTHOR = "Huang, D. and Ramanathan, V. and Mahajan, D. and Torresani, L. and Paluri, M. and Fei Fei, L. and Niebles, J.C.",
        TITLE = "What Makes a Video a Video: Analyzing Temporal Information in Video
Understanding Models and Datasets",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "7366-7375",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173296"}

@inproceedings{bb177974,
        AUTHOR = "Mahdisoltani, F. and Memisevic, R. and Fleet, D.J.",
        TITLE = "Hierarchical Video Understanding",
        BOOKTITLE = WiCV-E18,
        YEAR = "2018",
        PAGES = "IV:659-663",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173297"}

@inproceedings{bb177975,
        AUTHOR = "Shin, K.S. and Jeon, J. and Lee, S. and Lim, B. and Jeong, M.S. and Nang, J.",
        TITLE = "Approach for Video Classification with Multi-label on YouTube-8M
Dataset",
        BOOKTITLE = Large-Scale18,
        YEAR = "2018",
        PAGES = "IV:317-324",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173298"}

@inproceedings{bb177976,
        AUTHOR = "Skalic, M. and Austin, D.",
        TITLE = "Building A Size Constrained Predictive Models for Video Classification",
        BOOKTITLE = Large-Scale18,
        YEAR = "2018",
        PAGES = "IV:297-305",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173299"}

@inproceedings{bb177977,
        AUTHOR = "Garg, S.",
        TITLE = "Learning Video Features for Multi-label Classification",
        BOOKTITLE = Large-Scale18,
        YEAR = "2018",
        PAGES = "IV:325-337",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173300"}

@inproceedings{bb177978,
        AUTHOR = "Cho, C. and Antin, B. and Arora, S. and Ashrafi, S. and Duan, P. and Huynh, D.T. and James, L. and Nguyen, H.T. and Solgi, M. and Than, C.V.",
        TITLE = "Large-Scale Video Classification with Feature Space Augmentation
Coupled with Learned Label Relations and Ensembling",
        BOOKTITLE = Large-Scale18,
        YEAR = "2018",
        PAGES = "IV:338-346",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173301"}

@inproceedings{bb177979,
        AUTHOR = "Lin, R.C. and Xiao, J. and Fan, J.P.",
        TITLE = "NeXtVLAD: An Efficient Neural Network to Aggregate Frame-Level Features
for Large-Scale Video Classification",
        BOOKTITLE = Large-Scale18,
        YEAR = "2018",
        PAGES = "IV:206-218",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173302"}

@inproceedings{bb177980,
        AUTHOR = "Tang, Y.Y. and Zhang, X. and Wang, J.W. and Chen, S.X. and Ma, L. and Jiang, Y.G.",
        TITLE = "Non-local NetVLAD Encoding for Video Classification",
        BOOKTITLE = Large-Scale18,
        YEAR = "2018",
        PAGES = "IV:219-228",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173303"}

@inproceedings{bb177981,
        AUTHOR = "Kmiec, S. and Bae, J. and An, R.",
        TITLE = "Learnable Pooling Methods for Video Classification",
        BOOKTITLE = Large-Scale18,
        YEAR = "2018",
        PAGES = "IV:229-238",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173304"}

@inproceedings{bb177982,
        AUTHOR = "Liu, T. and Liu, B.",
        TITLE = "Constrained-Size Tensorflow Models for YouTube-8M Video Understanding
Challenge",
        BOOKTITLE = Large-Scale18,
        YEAR = "2018",
        PAGES = "IV:239-249",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173305"}

@inproceedings{bb177983,
        AUTHOR = "Lee, J. and Natsev, A.P. and Reade, W. and Sukthankar, R. and Toderici, G.",
        TITLE = "The 2nd YouTube-8M Large-Scale Video Understanding Challenge",
        BOOKTITLE = Large-Scale18,
        YEAR = "2018",
        PAGES = "IV:193-205",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173306"}

@inproceedings{bb177984,
        AUTHOR = "Zolfaghari, M. and Singh, K. and Brox, T.",
        TITLE = "ECO: Efficient Convolutional Network for Online Video Understanding",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "II: 713-730",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173307"}

@inproceedings{bb177985,
        AUTHOR = "Sah, S. and Nguyen, T. and Dominguez, M. and Such, F.P. and Ptucha, R.",
        TITLE = "Temporally Steered Gaussian Attention for Video Understanding",
        BOOKTITLE = DeepLearn-T17,
        YEAR = "2017",
        PAGES = "2208-2216",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173308"}

@inproceedings{bb177986,
        AUTHOR = "Jiang, Y.G. and Ye, G. and Chang, S.F. and Ellis, D. and Loui, A.C.",
        TITLE = "Consumer video understanding: a benchmark database and an evaluation of
human and machine performance",
        BOOKTITLE = ICMR11,
        YEAR = "2011",
        PAGES = "29",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173309"}

@inproceedings{bb177987,
        AUTHOR = "Yang, Y. and Liu, J.G. and Shah, M.",
        TITLE = "Video Scene Understanding Using Multi-scale Analysis",
        BOOKTITLE = ICCV09,
        YEAR = "2009",
        PAGES = "1669-1676",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT173310"}

@article{bb177988,
        AUTHOR = "Kim, C. and Hwang, J.N.",
        TITLE = "Object-based video abstraction for video surveillance systems",
        JOURNAL = CirSysVideo,
        VOLUME = "12",
        YEAR = "2002",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "1128-1138",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173311"}

@inproceedings{bb177989,
        AUTHOR = "Kim, C. and Hwang, J.N.",
        TITLE = "Object-based Video Abstraction Using Cluster Analysis",
        BOOKTITLE = ICIP01,
        YEAR = "2001",
        PAGES = "II: 657-660",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173312"}

@article{bb177990,
        AUTHOR = "Pritch, Y. and Rav Acha, A. and Peleg, S.",
        TITLE = "Nonchronological Video Synopsis and Indexing",
        JOURNAL = PAMI,
        VOLUME = "30",
        YEAR = "2008",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "1971-1984",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173313"}

@inproceedings{bb177991,
        AUTHOR = "Rav Acha, A. and Pritch, Y. and Peleg, S.",
        TITLE = "Making a Long Video Short: Dynamic Video Synopsis",
        BOOKTITLE = CVPR06,
        YEAR = "2006",
        PAGES = "I: 435-441",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173314"}

@inproceedings{bb177992,
        AUTHOR = "Pritch, Y. and Kav Venaki, E. and Peleg, S.",
        TITLE = "Shift-map image editing",
        BOOKTITLE = ICCV09,
        YEAR = "2009",
        PAGES = "151-158",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173315"}

@inproceedings{bb177993,
        AUTHOR = "Pritch, Y. and Ratovitch, S. and Hendel, A. and Peleg, S.",
        TITLE = "Clustered Synopsis of Surveillance Video",
        BOOKTITLE = AVSBS09,
        YEAR = "2009",
        PAGES = "195-200",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173316"}

@inproceedings{bb177994,
        AUTHOR = "Peleg, S.",
        TITLE = "Keynote lecture 2: Video synopsis",
        BOOKTITLE = AVSS13,
        YEAR = "2013",
        PAGES = "XVII-XVII",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173317"}

@article{bb177995,
        AUTHOR = "Xiang, T. and Gong, S.G.",
        TITLE = "Optimising dynamic graphical models for video content analysis",
        JOURNAL = CVIU,
        VOLUME = "112",
        YEAR = "2008",
        NUMBER = "3",
        MONTH = "December",
        PAGES = "310-323",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173318"}

@inproceedings{bb177996,
        AUTHOR = "Alexiou, I. and Xiang, T. and Gong, S.G.",
        TITLE = "Exploring synonyms as context in zero-shot action recognition",
        BOOKTITLE = ICIP16,
        YEAR = "2016",
        PAGES = "4190-4194",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173319"}

@inproceedings{bb177997,
        AUTHOR = "Alexiou, I. and Xiang, T. and Gong, S.G.",
        TITLE = "Learning a joint discriminative-generative model for action
recognition",
        BOOKTITLE = WSSIP15,
        YEAR = "2015",
        PAGES = "1-4",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173320"}

@article{bb177998,
        AUTHOR = "Mehmood, K. and Mrak, M. and Calic, J. and Kondoz, A.M.",
        TITLE = "Object tracking in surveillance videos using compressed domain features
from scalable bit-streams",
        JOURNAL = SP:IC,
        VOLUME = "24",
        YEAR = "2009",
        NUMBER = "10",
        MONTH = "November",
        PAGES = "814-824",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173321"}

@article{bb177999,
        AUTHOR = "Hoferlin, M. and Hoferlin, B. and Heidemann, G. and Weiskopf, D.",
        TITLE = "Interactive Schematic Summaries for Faceted Exploration
of Surveillance Video",
        JOURNAL = MultMed,
        VOLUME = "15",
        YEAR = "2013",
        NUMBER = "4",
        PAGES = "908-920",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825su1.html#TT173322"}

Last update:May 10, 2021 at 18:51:10