@inproceedings{bb237500,
        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#TT232412"}

@article{bb237501,
        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#TT232413"}

@article{bb237502,
        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#TT232414"}

@inproceedings{bb237503,
        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#TT232415"}

@article{bb237504,
        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#TT232416"}

@article{bb237505,
        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#TT232417"}

@article{bb237506,
        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#TT232418"}

@article{bb237507,
        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#TT232419"}

@article{bb237508,
        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#TT232420"}

@article{bb237509,
        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#TT232421"}

@article{bb237510,
        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#TT232422"}

@article{bb237511,
        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#TT232423"}

@article{bb237512,
        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#TT232424"}

@article{bb237513,
        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#TT232425"}

@article{bb237514,
        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#TT232426"}

@article{bb237515,
        AUTHOR = "Yu, L.J. and Zhao, X. and Xie, L. and Liang, H.R. and Liang, R.H.",
        TITLE = "Hierarchical multi-modal video summarization with dynamic sampling",
        JOURNAL = IET-IPR,
        VOLUME = "18",
        YEAR = "2024",
        NUMBER = "14",
        PAGES = "4577-4588",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT232427"}

@article{bb237516,
        AUTHOR = "Sartinas, E.G. and Psarakis, E.Z. and Kosmopoulos, D.I.",
        TITLE = "A 3D wrist motion-based sign language video summarization technique",
        JOURNAL = PRL,
        VOLUME = "189",
        YEAR = "2025",
        PAGES = "23-30",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mms4.html#TT232428"}

@inproceedings{bb237517,
        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#TT232429"}

@inproceedings{bb237518,
        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#TT232430"}

@inproceedings{bb237519,
        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#TT232431"}

@inproceedings{bb237520,
        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#TT232432"}

@inproceedings{bb237521,
        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#TT232433"}

@inproceedings{bb237522,
        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#TT232434"}

@inproceedings{bb237523,
        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#TT232435"}

@inproceedings{bb237524,
        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#TT232436"}

@inproceedings{bb237525,
        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#TT232437"}

@inproceedings{bb237526,
        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#TT232438"}

@inproceedings{bb237527,
        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#TT232439"}

@article{bb237528,
        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#TT232440"}

@article{bb237529,
        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#TT232441"}

@article{bb237530,
        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#TT232442"}

@article{bb237531,
        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#TT232443"}

@article{bb237532,
        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#TT232444"}

@inproceedings{bb237533,
        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#TT232445"}

@inproceedings{bb237534,
        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#TT232446"}

@inproceedings{bb237535,
        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#TT232447"}

@inproceedings{bb237536,
        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#TT232448"}

@article{bb237537,
        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#TT232449"}

@article{bb237538,
        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#TT232450"}

@inproceedings{bb237539,
        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#TT232451"}

@inproceedings{bb237540,
        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#TT232452"}

@inproceedings{bb237541,
        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#TT232453"}

@inproceedings{bb237542,
        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#TT232454"}

@inproceedings{bb237543,
        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#TT232455"}

@inproceedings{bb237544,
        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#TT232456"}

@inproceedings{bb237545,
        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#TT232457"}

@inproceedings{bb237546,
        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#TT232458"}

@inproceedings{bb237547,
        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#TT232458"}

@inproceedings{bb237548,
        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#TT232458"}

@inproceedings{bb237549,
        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#TT232459"}

@article{bb237550,
        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#TT232461"}

@inproceedings{bb237551,
        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#TT232462"}

@article{bb237552,
        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#TT232463"}

@article{bb237553,
        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#TT232464"}

@article{bb237554,
        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#TT232465"}

@article{bb237555,
        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#TT232466"}

@article{bb237556,
        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#TT232467"}

@article{bb237557,
        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#TT232468"}

@article{bb237558,
        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#TT232469"}

@inproceedings{bb237559,
        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#TT232470"}

@article{bb237560,
        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#TT232471"}

@article{bb237561,
        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#TT232472"}

@article{bb237562,
        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#TT232473"}

@article{bb237563,
        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#TT232474"}

@inproceedings{bb237564,
        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#TT232475"}

@article{bb237565,
        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#TT232476"}

@article{bb237566,
        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#TT232477"}

@article{bb237567,
        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#TT232478"}

@article{bb237568,
        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#TT232479"}

@article{bb237569,
        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#TT232480"}

@article{bb237570,
        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#TT232481"}

@article{bb237571,
        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#TT232482"}

@article{bb237572,
        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#TT232483"}

@article{bb237573,
        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#TT232484"}

@article{bb237574,
        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#TT232485"}

@article{bb237575,
        AUTHOR = "Chen, Z.Y. 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#TT232486"}

@article{bb237576,
        AUTHOR = "Chen, Z.L. and Wang, L. and Wang, P. and Gao, P.",
        TITLE = "Question-Aware Global-Local Video Understanding Network for
Audio-Visual Question Answering",
        JOURNAL = CirSysVideo,
        VOLUME = "34",
        YEAR = "2024",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "4109-4119",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232487"}

@article{bb237577,
        AUTHOR = "Cao, H.Z. and Xu, Y.C. and Mao, K.Z. and Xie, L.H. and Yin, J.X. and See, S. and Xu, Q.W. and Yang, J.F.",
        TITLE = "Self-Supervised Video Representation Learning by Video Incoherence
Detection",
        JOURNAL = Cyber,
        VOLUME = "54",
        YEAR = "2024",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "3810-3822",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232488"}

@article{bb237578,
        AUTHOR = "Zhang, Z.Q. and Ma, Z. and Yuan, C.F. and Chen, Y.X. and Wang, P. and Qi, Z.A. and Hao, C.L. and Li, B. and Shan, Y. and Hu, W.M. and Maybank, S.J.",
        TITLE = "Chinese Title Generation for Short Videos:
Dataset, Metric and Algorithm",
        JOURNAL = PAMI,
        VOLUME = "46",
        YEAR = "2024",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "5192-5208",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232489"}

@article{bb237579,
        AUTHOR = "Bi, S. and Hu, Z.P. and Zhang, H. and Di, J. and Sun, Z.",
        TITLE = "Motion-guided spatiotemporal multitask feature discrimination for
self-supervised video representation learning",
        JOURNAL = PR,
        VOLUME = "155",
        YEAR = "2024",
        PAGES = "110713",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232490"}

@article{bb237580,
        AUTHOR = "Pang, B. and Peng, G. and Li, Y.Z. and Lu, C.",
        TITLE = "Markov Progressive Framework, a Universal Paradigm for Modeling Long
Videos",
        JOURNAL = PAMI,
        VOLUME = "46",
        YEAR = "2024",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "9749-9765",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232491"}

@article{bb237581,
        AUTHOR = "Li, D. and Jin, J.D. and Zhang, Y.H. and Zhong, Y.L. and Wu, Y.Y. and Chen, L. and Wang, X. and Luo, B.",
        TITLE = "Semantic-aware frame-event fusion based pattern recognition via large
vision-language models",
        JOURNAL = PR,
        VOLUME = "158",
        YEAR = "2025",
        PAGES = "111080",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232492"}

@article{bb237582,
        AUTHOR = "You, Z. and Wen, Z.Q. and Chen, Y.F. and Li, X. and Zeng, R.H. and Wang, Y.W. and Tan, M.K.",
        TITLE = "Toward Long Video Understanding via Fine-Detailed Video Story
Generation",
        JOURNAL = CirSysVideo,
        VOLUME = "35",
        YEAR = "2025",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "4592-4607",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232493"}

@article{bb237583,
        AUTHOR = "Wu, W.H. and Wang, X.H. and Luo, H.P. and Wang, J.D. and Yang, Y. and Ouyang, W.L.",
        TITLE = "Cap4Video++: Enhancing Video Understanding With Auxiliary Captions",
        JOURNAL = PAMI,
        VOLUME = "47",
        YEAR = "2025",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "5223-5237",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232494"}

@inproceedings{bb237584,
        AUTHOR = "Das, S. and Mujavarsheik, B. and Lyngkhoi, R.E.Z. and Saha, S. and Maurya, A.",
        TITLE = "Deciphering the Complaint Aspects: Towards an Aspect-Based Complaint
Identification Model with Video Complaint Dataset in Finance",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "7195-7204",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232495"}

@inproceedings{bb237585,
        AUTHOR = "Liu, H. and Nakashima, Y. and Babaguchi, N.",
        TITLE = "Paladin: Understanding Video Intentions in Political Advertisement
Videos",
        BOOKTITLE = WACV25,
        YEAR = "2025",
        PAGES = "8239-8248",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232496"}

@inproceedings{bb237586,
        AUTHOR = "Bae, K. and Ahn, G. and Kim, Y. and Choi, J.",
        TITLE = "DEVIAS: Learning Disentangled Video Representations of Action and Scene",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "LXVIII: 431-448",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232497"}

@inproceedings{bb237587,
        AUTHOR = "Salehi, M. and Dorkenwald, M. and Thoker, F.M. and Gavves, E. and Snoek, C.G.M. and Asano, Y.M.",
        TITLE = "Sigma: Sinkhorn-guided Masked Video Modeling",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XXIV: 293-312",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232498"}

@inproceedings{bb237588,
        AUTHOR = "Xie, B.Z. and Zhang, S.C. and Zhou, Z. and Li, B. and Zhang, Y.H. and Hessel, J. and Yang, J.K. and Liu, Z.W.",
        TITLE = "FUNQA: Towards Surprising Video Comprehension",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "I: 39-57",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232499"}

@inproceedings{bb237589,
        AUTHOR = "Korbar, B. and Xian, Y.Q. and Tonioni, A. and Zisserman, A. and Tombari, F.",
        TITLE = "Text-conditioned Resampler For Long Form Video Understanding",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "LXXXVI: 271-288",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232500"}

@inproceedings{bb237590,
        AUTHOR = "Wang, X.H. and Zhang, Y.H. and Zohar, O. and Yeung Levy, S.",
        TITLE = "Videoagent: Long-form Video Understanding with Large Language Model as
Agent",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "LXXX: 58-76",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232501"}

@inproceedings{bb237591,
        AUTHOR = "Choi, M. and Goel, H. and Omama, M. and Yang, Y.H. and Shah, S. and Chinchali, S.",
        TITLE = "Towards Neuro-symbolic Video Understanding",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "LXXVIII: 220-236",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232502"}

@inproceedings{bb237592,
        AUTHOR = "Weng, Y. and Han, M.F. and He, H.Y. and Chang, X.J. and Zhuang, B.",
        TITLE = "LongVLM: Efficient Long Video Understanding via Large Language Models",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XXXIII: 453-470",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232503"}

@inproceedings{bb237593,
        AUTHOR = "Fan, Y. and Ma, X.J. and Wu, R.J. and Du, Y.T. and Li, J.Q. and Gao, Z. and Li, Q.",
        TITLE = "Videoagent: A Memory-augmented Multimodal Agent for Video Understanding",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XXII: 75-92",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232504"}

@inproceedings{bb237594,
        AUTHOR = "Wang, S.J. and Zhao, Q. and Do, M.Q. and Agarwal, N. and Lee, K. and Sun, C.",
        TITLE = "VAMOS: Versatile Action Models for Video Understanding",
        BOOKTITLE = ECCV24,
        YEAR = "2024",
        PAGES = "XII: 142-160",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232505"}

@inproceedings{bb237595,
        AUTHOR = "Lebreton, P. and Le Callet, P. and Birkbeck, N. and Wang, Y.L. and Adsumilli, B.",
        TITLE = "A Dataset for Understanding Open UGC Video Datasets",
        BOOKTITLE = ICIP24,
        YEAR = "2024",
        PAGES = "165-171",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232506"}

@inproceedings{bb237596,
        AUTHOR = "Wu, J.T. and Mo, S.T. and Atito, S. and Feng, Z.H. and Kittler, J.V. and Husain, S.S. and Awais, M.",
        TITLE = "Masked Momentum Contrastive Learning for Semantic Understanding by
Observation",
        BOOKTITLE = ICIP24,
        YEAR = "2024",
        PAGES = "263-269",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232507"}

@inproceedings{bb237597,
        AUTHOR = "Yun, H. and Ahn, J. and Kim, M. and Kim, E.S.",
        TITLE = "Compositional Video Understanding with Spatiotemporal Structure-based
Transformers",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "18751-18760",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232508"}

@inproceedings{bb237598,
        AUTHOR = "Papalampidi, P. and Koppula, S. and Pathak, S. and Chiu, J. and Heyward, J. and Patraucean, V. and Shen, J.J. and Miech, A. and Zisserman, A. and Nematzdeh, A.",
        TITLE = "A Simple Recipe for Contrastively Pre-Training Video-First Encoders
Beyond 16 Frames",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "14386-14397",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232509"}

@inproceedings{bb237599,
        AUTHOR = "Wang, A.D. and Wu, B. and Chen, S. and Chen, Z.F. and Guan, H.T. and Lee, W.N. and Li, L.E. and Gan, C.",
        TITLE = "SOK-Bench: A Situated Video Reasoning Benchmark with Aligned
Open-World Knowledge",
        BOOKTITLE = CVPR24,
        YEAR = "2024",
        PAGES = "13384-13394",
        BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT232510"}