@article{bb247900,
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/applicat825mo1.html#TT242742"}
@inproceedings{bb247901,
AUTHOR = "Xie, L.X. and Divakaran, A. and Chang, S.F.",
TITLE = "Unsupervised learning of video structures in videos using hierarchical
statistical models to detect events",
BOOKTITLE = US_Patent,
YEAR = "2007",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242743"}
@article{bb247902,
AUTHOR = "Lehane, B. and O'Connor, N.E. and Lee, H.W. and Smeaton, A.F.",
TITLE = "Indexing of Fictional Video Content for Event Detection and
Summarisation",
JOURNAL = JIVP,
VOLUME = "2007",
YEAR = "2007",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242744"}
@inproceedings{bb247903,
AUTHOR = "Salway, A. and Lehane, B. and O'Connor, N.E.",
TITLE = "Associating characters with events in films",
BOOKTITLE = CIVR07,
YEAR = "2007",
PAGES = "510-517",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242745"}
@inproceedings{bb247904,
AUTHOR = "Lehane, B. and O'Connor, N.E. and Murphy, N.",
TITLE = "Dialogue Sequence Detection in Movies",
BOOKTITLE = CIVR05,
YEAR = "2005",
PAGES = "286-296",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242746"}
@inproceedings{bb247905,
AUTHOR = "Rui, Y. and Gupta, A. and Acero, A.",
TITLE = "Annotating programs for automatic summary generation",
BOOKTITLE = US_Patent,
YEAR = "2006",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242747"}
@inproceedings{bb247906,
AUTHOR = "Chen, W. and Chen, J.Y.",
TITLE = "Method and apparatus for summarizing and indexing the contents
of an audio-visual presentation",
BOOKTITLE = US_Patent,
YEAR = "2008",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242748"}
@article{bb247907,
AUTHOR = "Murtagh, F. and Ganz, A. and McKie, S.",
TITLE = "The structure of narrative: The case of film scripts",
JOURNAL = PR,
VOLUME = "42",
YEAR = "2009",
NUMBER = "2",
MONTH = "February",
PAGES = "302-312",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242749"}
@article{bb247908,
AUTHOR = "Chen, B.W. and Wang, J.C. and Wang, J.F.",
TITLE = "A Novel Video Summarization Based on Mining the Story-Structure and
Semantic Relations Among Concept Entities",
JOURNAL = MultMed,
VOLUME = "11",
YEAR = "2009",
NUMBER = "2",
MONTH = "February",
PAGES = "295-312",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242750"}
@article{bb247909,
AUTHOR = "Benini, S. and Migliorati, P. and Leonardi, R.",
TITLE = "Hierarchical structuring of video previews by Leading-Cluster-Analysis",
JOURNAL = SIViP,
VOLUME = "4",
YEAR = "2010",
NUMBER = "4",
MONTH = "November",
PAGES = "435-450",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242751"}
@inproceedings{bb247910,
AUTHOR = "Benini, S. and Migliorati, P. and Leonardi, R.",
TITLE = "Fast dialogue indexing based on structure information",
BOOKTITLE = ICIP08,
YEAR = "2008",
PAGES = "69-72",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242752"}
@inproceedings{bb247911,
AUTHOR = "Benini, S. and Bianchetti, A. and Leonardi, R. and Migliorati, P.",
TITLE = "Extraction of Significant Video Summaries by Dendrogram Analysis",
BOOKTITLE = ICIP06,
YEAR = "2006",
PAGES = "133-136",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242753"}
@article{bb247912,
AUTHOR = "Ellouze, M. and Boujemaa, N. and Alimi, A.M.",
TITLE = "IM(S)2: Interactive movie summarization system",
JOURNAL = JVCIR,
VOLUME = "21",
YEAR = "2010",
NUMBER = "4",
MONTH = "May",
PAGES = "283-294",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242754"}
@inproceedings{bb247913,
AUTHOR = "Kherallah, M. and Karray, H. and Ellouze, M. and Alimi, A.M.",
TITLE = "Toward an interactive device for quick news story browsing",
BOOKTITLE = ICPR08,
YEAR = "2008",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242755"}
@article{bb247914,
AUTHOR = "Zaharieva, M. and Mitrovic, D. and Zeppelzauer, M. and Breiteneder, C.",
TITLE = "Film Analysis of Archived Documentaries",
JOURNAL = MultMedMag,
VOLUME = "18",
YEAR = "2011",
NUMBER = "2",
MONTH = "April",
PAGES = "38-47",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242756"}
@inproceedings{bb247915,
AUTHOR = "Diem, L. and Zaharieva, M.",
TITLE = "Video Content Representation Using Recurring Regions Detection",
BOOKTITLE = MMMod16,
YEAR = "2016",
PAGES = "I: 16-28",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242757"}
@inproceedings{bb247916,
AUTHOR = "Zaharieva, M. and Breiteneder, C.",
TITLE = "Recurring Element Detection in Movies",
BOOKTITLE = MMMod12,
YEAR = "2012",
PAGES = "222-232",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242758"}
@article{bb247917,
AUTHOR = "Vretos, N. and Solachidis, V. and Pitas, I.",
TITLE = "A mutual information based face clustering algorithm for movie content
analysis",
JOURNAL = IVC,
VOLUME = "29",
YEAR = "2011",
NUMBER = "10",
MONTH = "September",
PAGES = "693-705",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242759"}
@book{bb247918,
AUTHOR = "Kompatsiaris, Y. and Merialdo, B. and Lian, S.G.",
TITLE = "TV Content Analysis: Techniques and Applications",
PUBLISHER = "CRC Press",
YEAR = "2012",
MONTH = "May",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242760"}
@article{bb247919,
AUTHOR = "Liang, C. and Xu, C. and Cheng, J. and Min, W. and Lu, H.",
TITLE = "Script-to-Movie: A Computational Framework for Story Movie Composition",
JOURNAL = MultMed,
VOLUME = "15",
YEAR = "2013",
NUMBER = "2",
PAGES = "401-414",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242761"}
@article{bb247920,
AUTHOR = "Tsai, C.M. and Kang, L.W. and Lin, C.W. and Lin, W.S.",
TITLE = "Scene-Based Movie Summarization Via Role-Community Networks",
JOURNAL = CirSysVideo,
VOLUME = "23",
YEAR = "2013",
NUMBER = "11",
PAGES = "1927-1940",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242762"}
@article{bb247921,
AUTHOR = "Evangelopoulos, G. and Zlatintsi, A. and Potamianos, A. and Maragos, P. and Rapantzikos, K. and Skoumas, G. and Avrithis, Y.S.",
TITLE = "Multimodal Saliency and Fusion for Movie Summarization Based on
Aural, Visual, and Textual Attention",
JOURNAL = MultMed,
VOLUME = "15",
YEAR = "2013",
NUMBER = "7",
PAGES = "1553-1568",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242763"}
@article{bb247922,
AUTHOR = "Tapaswi, M. and Bauml, M. and Stiefelhagen, R.",
TITLE = "Aligning plot synopses to videos for story-based retrieval",
JOURNAL = MultInfoRetr,
VOLUME = "4",
YEAR = "2015",
NUMBER = "1",
MONTH = "March",
PAGES = "3-16",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242764"}
@inproceedings{bb247923,
AUTHOR = "Tapaswi, M. and Bauml, M. and Stiefelhagen, R.",
TITLE = "Book2Movie: Aligning video scenes with book chapters",
BOOKTITLE = CVPR15,
YEAR = "2015",
PAGES = "1827-1835",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242765"}
@article{bb247924,
AUTHOR = "Ahmadzade, A.M. and Farsi, H.",
TITLE = "Video Summarization by an Innovative Method in Shot Detection",
JOURNAL = ELCVIA,
VOLUME = "14",
YEAR = "2015",
NUMBER = "1",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242766"}
@article{bb247925,
AUTHOR = "Li, K. and Wang, J. and Wang, H. and Dai, Q.H.",
TITLE = "Structuring Lecture Videos by Automatic Projection Screen
Localization and Analysis",
JOURNAL = PAMI,
VOLUME = "37",
YEAR = "2015",
NUMBER = "6",
MONTH = "June",
PAGES = "1233-1246",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242767"}
@article{bb247926,
AUTHOR = "Chu, W.T. and Yu, C.H. and Wang, H.H.",
TITLE = "Optimized Comics-Based Storytelling for Temporal Image Sequences",
JOURNAL = MultMed,
VOLUME = "17",
YEAR = "2015",
NUMBER = "2",
MONTH = "February",
PAGES = "201-215",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242768"}
@article{bb247927,
AUTHOR = "Mademlis, I. and Tefas, A. and Nikolaidis, N. and Pitas, I.",
TITLE = "Multimodal Stereoscopic Movie Summarization Conforming to Narrative
Characteristics",
JOURNAL = IP,
VOLUME = "25",
YEAR = "2016",
NUMBER = "12",
MONTH = "December",
PAGES = "5828-5840",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242769"}
@article{bb247928,
AUTHOR = "Aparicio, M. and Figueiredo, P. and Raposo, F. and de Matos, D.M. and Ribeiro, R. and Marujo, L.",
TITLE = "Summarization of films and documentaries based on subtitles and
scripts",
JOURNAL = PRL,
VOLUME = "73",
YEAR = "2016",
NUMBER = "1",
PAGES = "7-12",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242770"}
@article{bb247929,
AUTHOR = "Baraldi, L. and Grana, C. and Cucchiara, R.",
TITLE = "Recognizing and Presenting the Storytelling Video Structure With Deep
Multimodal Networks",
JOURNAL = MultMed,
VOLUME = "19",
YEAR = "2017",
NUMBER = "5",
MONTH = "May",
PAGES = "955-968",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242771"}
@article{bb247930,
AUTHOR = "Lu, Q. and Chai, B.J. and Zhang, H.B.",
TITLE = "Storytelling by the StoryCake visualization",
JOURNAL = VC,
VOLUME = "33",
YEAR = "2017",
NUMBER = "10",
MONTH = "October",
PAGES = "1241-1252",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242772"}
@article{bb247931,
AUTHOR = "Somandepalli, K. and Kumar, N. and Guha, T. and Narayanan, S.S.",
TITLE = "Unsupervised Discovery of Character Dictionaries in Animation Movies",
JOURNAL = MultMed,
VOLUME = "20",
YEAR = "2018",
NUMBER = "3",
MONTH = "March",
PAGES = "539-551",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242773"}
@article{bb247932,
AUTHOR = "Berendsen, M.E. and Hamerlinck, J.D. and Webster, G.R.",
TITLE = "Digital Story Mapping to Advance Educational Atlas Design and Enable
Student Engagement",
JOURNAL = IJGI,
VOLUME = "7",
YEAR = "2018",
NUMBER = "3",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242774"}
@article{bb247933,
AUTHOR = "Yang, X.S. and Zhang, T.Z. and Xu, C.S.",
TITLE = "Text2Video:
An End-to-end Learning Framework for Expressing Text With Videos",
JOURNAL = MultMed,
VOLUME = "20",
YEAR = "2018",
NUMBER = "9",
MONTH = "September",
PAGES = "2360-2370",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242775"}
@inproceedings{bb247934,
AUTHOR = "Sun, K. and Lei, Z. and Zhu, J.S. and Hou, X.X. and Liu, B. and Qiu, G.P.",
TITLE = "Character Prediction in TV Series via a Semantic Projection Network",
BOOKTITLE = "MMMod19",
YEAR = "2019",
PAGES = "I:300-311",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242776"}
@article{bb247935,
AUTHOR = "Nabati, M. and Behrad, A.",
TITLE = "Video captioning using boosted and parallel Long Short-Term Memory
networks",
JOURNAL = CVIU,
VOLUME = "190",
YEAR = "2020",
PAGES = "102840",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242777"}
@article{bb247936,
AUTHOR = "Xiao, H.H. and Xu, J.W. and Shi, J.L.",
TITLE = "Exploring diverse and fine-grained caption for video by incorporating
convolutional architecture into LSTM-based model",
JOURNAL = PRL,
VOLUME = "129",
YEAR = "2020",
PAGES = "173-180",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242778"}
@article{bb247937,
AUTHOR = "Han, Y. and Wang, B. and Hong, R. and Wu, F.",
TITLE = "Movie Question Answering via Textual Memory and Plot Graph",
JOURNAL = CirSysVideo,
VOLUME = "30",
YEAR = "2020",
NUMBER = "3",
MONTH = "March",
PAGES = "875-887",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242779"}
@article{bb247938,
AUTHOR = "Zhou, P. and Xu, T. and Yin, Z. and Liu, D. and Chen, E. and Lv, G. and Li, C.",
TITLE = "Character-Oriented Video Summarization With Visual and Textual Cues",
JOURNAL = MultMed,
VOLUME = "22",
YEAR = "2020",
NUMBER = "10",
MONTH = "October",
PAGES = "2684-2697",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242780"}
@inproceedings{bb247939,
AUTHOR = "Fujita, S. and Hirao, T. and Kamigaito, H. and Okumura, M. and Nagata, M.",
TITLE = "Soda: Story Oriented Dense Video Captioning Evaluation Framework",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "VI:517-531",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242781"}
@article{bb247940,
AUTHOR = "Ghose, S. and Prevost, J.J.",
TITLE = "AutoFoley: Artificial Synthesis of Synchronized Sound Tracks for
Silent Videos With Deep Learning",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "1895-1907",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242782"}
@article{bb247941,
AUTHOR = "Apostolidis, E. and Adamantidou, E. and Metsai, A.I. and Mezaris, V. and Patras, I.",
TITLE = "AC-SUM-GAN: Connecting Actor-Critic and Generative Adversarial
Networks for Unsupervised Video Summarization",
JOURNAL = CirSysVideo,
VOLUME = "31",
YEAR = "2021",
NUMBER = "8",
MONTH = "August",
PAGES = "3278-3292",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242783"}
@article{bb247942,
AUTHOR = "Liu, D. and Kamath, N. and Bhattacharya, S. and Puri, R.",
TITLE = "Adaptive Context Reading Network for Movie Scene Detection",
JOURNAL = CirSysVideo,
VOLUME = "31",
YEAR = "2021",
NUMBER = "9",
MONTH = "September",
PAGES = "3559-3574",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242784"}
@article{bb247943,
AUTHOR = "Wang, J.Y. and Xu, M. and Jiang, L. and Song, Y.H.",
TITLE = "Attention-Based Deep Reinforcement Learning for Virtual
Cinematography of 360° Videos",
JOURNAL = MultMed,
VOLUME = "23",
YEAR = "2021",
PAGES = "3227-3238",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242785"}
@article{bb247944,
AUTHOR = "Wu, A. and Han, Y.H. and Zhao, Z. and Yang, Y.",
TITLE = "Hierarchical Memory Decoder for Visual Narrating",
JOURNAL = CirSysVideo,
VOLUME = "31",
YEAR = "2021",
NUMBER = "6",
MONTH = "June",
PAGES = "2438-2449",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242786"}
@article{bb247945,
AUTHOR = "Xie, J.H. and Chen, X.B. and Zhang, T.Y. and Zhang, Y.X. and Lu, S.P. and Cesar, P. and Yang, Y.",
TITLE = "Multimodal-Based and Aesthetic-Guided Narrative Video Summarization",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "4894-4908",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242787"}
@article{bb247946,
AUTHOR = "Papalampidi, P. and Keller, F. and Lapata, M.",
TITLE = "Finding the Right Moment: Human-Assisted Trailer Creation via Task
Composition",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "1",
MONTH = "January",
PAGES = "292-304",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242788"}
@article{bb247947,
AUTHOR = "Lu, Y. and Ni, F.Y. and Wang, H. and Guo, X.F. and Zhu, L.C. and Yang, Z.X. and Song, R.H. and Cheng, L. and Yang, Y.",
TITLE = "Show Me a Video: A Large-Scale Narrated Video Dataset for Coherent
Story Illustration",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "2456-2466",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242789"}
@article{bb247948,
AUTHOR = "Yuan, M.Q. and Jia, G. and Bao, B.K.",
TITLE = "GPT-Based Knowledge Guiding Network for Commonsense Video Captioning",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "5147-5158",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242790"}
@article{bb247949,
AUTHOR = "Wang, Y.Z. and Hu, W.B. and Hong, R.C.",
TITLE = "Iterative Adversarial Attack on Image-Guided Story Ending Generation",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "6117-6130",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242791"}
@article{bb247950,
AUTHOR = "Chen, Z. and Zhang, K. and Cai, H. and Ding, X.Y. and Jiang, C.X. and Chen, Z.Z.",
TITLE = "Audio-visual saliency prediction for movie viewing in immersive
environments: Dataset and benchmarks",
JOURNAL = JVCIR,
VOLUME = "100",
YEAR = "2024",
PAGES = "104095",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242792"}
@article{bb247951,
AUTHOR = "Kaur, P.C. and Ragha, L.",
TITLE = "Optimized deep learning enabled lecture audio video summarization",
JOURNAL = JVCIR,
VOLUME = "104",
YEAR = "2024",
PAGES = "104309",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242793"}
@inproceedings{bb247952,
AUTHOR = "Tao, M. and Bao, B.K. and Tang, H. and Wang, Y.W. and Xu, C.S.",
TITLE = "Storyimager: A Unified and Efficient Framework for Coherent Story
Visualization and Completion",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LVI: 479-495",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242794"}
@article{bb247953,
AUTHOR = "Guo, J.H. and Lu, A. and Wu, Z.Q. and Wang, Z.Y. and Liang, C.",
TITLE = "Who, What, and Where: Composite-Semantics Instance Search for Story
Videos",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "1412-1426",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242795"}
@article{bb247954,
AUTHOR = "Qin, P.G. and Xu, T. and Zhang, C. and Wang, H. and Hu, Y. and Chen, E.",
TITLE = "Scenario-Aware Multimodal Chain-of-Thought Prompting for Rationales
of VideoSocial Relations",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "11598-11612",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242796"}
@inproceedings{bb247955,
AUTHOR = "Xu, L. and Zhu, S. and Li, C.Y. and Kuo, C.W. and Chen, F. and Wang, X.Y. and Chen, G. and Du, D.W. and Yuan, Y. and Wen, L.Y.",
TITLE = "Beyond Raw Videos:
Understanding Edited Videos with Large Multimodal Model",
BOOKTITLE = "AIBench25",
YEAR = "2025",
PAGES = "503-512",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242797"}
@inproceedings{bb247956,
AUTHOR = "Wang, H.L. and Tong, Z. and Zheng, K. and Shen, Y.J. and Wang, L.M.",
TITLE = "Contextual AD Narration with Interleaved Multimodal Sequence",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8372-8383",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242798"}
@inproceedings{bb247957,
AUTHOR = "Kim, S. and Do, S. and Park, J.",
TITLE = "ShowMak3r: Compositional TV Show Reconstruction",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "864-874",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242799"}
@inproceedings{bb247958,
AUTHOR = "Wu, W.J. and Liu, M.Y. and Zhu, Z. and Xia, X. and Feng, H. and Wang, W. and Lin, K.Q.H. and Shen, C.H. and Shou, M.Z.",
TITLE = "MovieBench: A Hierarchical Movie Level Dataset for Long Video
Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "28984-28994",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242800"}
@inproceedings{bb247959,
AUTHOR = "Park, J. and Ye, J. and Lee, S. and Ka, H.W. and Han, D.",
TITLE = "NarrAD: Automatic Generation of Audio Descriptions for Movies with
Rich Narrative Context",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "409-419",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242801"}
@inproceedings{bb247960,
AUTHOR = "Zhang, C.K. and Lei, Y.M. and Liu, Z.M. and Leng, H.T. and Liu, S. and Gao, T.T. and Liu, Q.J. and Wang, Y.H.",
TITLE = "SeriesBench: A Benchmark for Narrative-Driven Drama Series
Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "28995-29004",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242802"}
@inproceedings{bb247961,
AUTHOR = "Lin, K.Q.H. and Zhang, P.C. and Gao, D.F. and Xia, X. and Chen, J. and Gao, Z.T. and Xie, J.H. and Xiao, X.H. and Shou, M.Z.",
TITLE = "Learning Video Context as Interleaved Multimodal Sequences",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLIX: 375-396",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242803"}
@inproceedings{bb247962,
AUTHOR = "Avetisyan, A. and Xie, C. and Howard Jenkins, H. and Yang, T.Y. and Aroudj, S. and Patra, S. and Zhang, F. and Frost, D. and Holland, L. and Orme, C. and Engel, J. and Miller, E. and Newcombe, R. and Balntas, V.",
TITLE = "Scenescript: Reconstructing Scenes with an Autoregressive Structured
Language Model",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXI: 247-263",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242804"}
@inproceedings{bb247963,
AUTHOR = "Shvetsova, N. and Kukleva, A. and Hong, X.D. and Rupprecht, C. and Schiele, B. and Kuehne, H.",
TITLE = "Howtocaption: Prompting LLMs to Transform Video Annotations at Scale",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LVI: 1-18",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242805"}
@inproceedings{bb247964,
AUTHOR = "Tan, J.W. and Wang, H.X. and Li, J.X. and Ou, Z.L. and Qian, Z.B.",
TITLE = "Neighbor Relations Matter in Video Scene Detection",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18473-18482",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242806"}
@inproceedings{bb247965,
AUTHOR = "Raajesh, H. and Desanur, N.R. and Khan, Z. and Tapaswi, M.",
TITLE = "MICap: A Unified Model for Identity-Aware Movie Descriptions",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14011-14021",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242807"}
@inproceedings{bb247966,
AUTHOR = "Argaw, D.M. and Soldan, M. and Pardo, A. and Zhao, C. and Heilbron, F.C. and Chung, J.S. and Ghanem, B.",
TITLE = "Towards Automated Movie Trailer Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7445-7454",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242808"}
@inproceedings{bb247967,
AUTHOR = "Singh, A.K. and Srivastava, D. and Tapaswi, M.",
TITLE = "'Previously on...' from Recaps to Story Summarization",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13635-13646",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242809"}
@inproceedings{bb247968,
AUTHOR = "Pan, X.C. and Qin, P. and Li, Y.H. and Xue, H. and Chen, W.",
TITLE = "Synthesizing Coherent Story with Auto-Regressive Latent Diffusion
Models",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "2908-2918",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242810"}
@inproceedings{bb247969,
AUTHOR = "Zhang, Z.P. and Gu, Y.W. and Plummer, B.A. and Miao, X. and Liu, J.Y. and Wang, H.Y.",
TITLE = "Movie Genre Classification by Language Augmentation and Shot Sampling",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "7260-7270",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242811"}
@inproceedings{bb247970,
AUTHOR = "Ahn, D.C. and Kim, D. and Song, G. and Kim, S.H. and Lee, H.L. and Kang, D. and Choi, J.H.",
TITLE = "Story Visualization by Online Text Augmentation with Context Memory",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "3102-3112",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242812"}
@inproceedings{bb247971,
AUTHOR = "Vacchetti, B. and Argaw, D.M. and Cequtelli, T.",
TITLE = "LEMMS: Label Estimation of Multi-feature Movie Segments",
BOOKTITLE = CVEU23,
YEAR = "2023",
PAGES = "3019-3027",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242813"}
@inproceedings{bb247972,
AUTHOR = "Han, T.D. and Bain, M. and Nagrani, A. and Varol, G. and Xie, W. and Zisserman, A.",
TITLE = "AutoAD II: The Sequel - Who, When, and What in Movie Audio
Description",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "13599-13609",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242814"}
@inproceedings{bb247973,
AUTHOR = "Argaw, D.M. and Lee, J.Y. and Woodson, M. and Kweon, I.S. and Heilbron, F.C.",
TITLE = "Long-range Multimodal Pretraining for Movie Understanding",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "13346-13357",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242815"}
@inproceedings{bb247974,
AUTHOR = "Sadoughi, N. and Li, X.Y. and Vajpayee, A. and Fan, D. and Shuai, B. and Santos Villalobos, H. and Bhat, V. and Mv, R.",
TITLE = "MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic
Video Segmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "23274-23283",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242816"}
@inproceedings{bb247975,
AUTHOR = "Han, T. and Bain, M. and Nagrani, A. and Varol, G. and Xie, W. and Zisserman, A.",
TITLE = "AutoAD: Movie Description in Context",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18930-18940",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242817"}
@inproceedings{bb247976,
AUTHOR = "Rahman, T. and Lee, H. .Y. and Ren, J. and Tulyakov, S. and Mahajan, S. and Sigal, L.",
TITLE = "Make-A-Story: Visual Memory Conditioned Consistent Story Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2493-2502",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242818"}
@inproceedings{bb247977,
AUTHOR = "Malakan, Z.M. and Hassan, G.M. and Jalwana, M.A.A.K. and Aafaq, N. and Mian, A.",
TITLE = "Semantic Attribute Enriched Storytelling from a Sequence of Images",
BOOKTITLE = DICTA21,
YEAR = "2021",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242819"}
@inproceedings{bb247978,
AUTHOR = "Huang, Y.Z. and Bai, X. and Wang, O. and Caba, F. and Agarwala, A.",
TITLE = "Learning Where to Cut from Edited Videos",
BOOKTITLE = CVEU21,
YEAR = "2021",
PAGES = "3208-3216",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242820"}
@inproceedings{bb247979,
AUTHOR = "Gaikwad, B. and Sontakke, A. and Patwardhan, M. and Pedanekar, N. and Karande, S.",
TITLE = "Plots to Previews: Towards Automatic Movie Preview Retrieval using
Publicly Available Meta-data",
BOOKTITLE = CVEU21,
YEAR = "2021",
PAGES = "3198-3207",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242821"}
@inproceedings{bb247980,
AUTHOR = "Yu, Y.J. and Chung, J. and Yun, H.S. and Kim, J.S. and Kim, G.",
TITLE = "Transitional Adaptation of Pretrained Models for Visual Storytelling",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "12653-12663",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242822"}
@inproceedings{bb247981,
AUTHOR = "Reboud, A. and Troncy, R.",
TITLE = "What You Say Is Not What You Do: Studying Visio-Linguistic Models for
TV Series Summarization",
BOOKTITLE = CLVL21,
YEAR = "2021",
PAGES = "3142-3146",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242823"}
@inproceedings{bb247982,
AUTHOR = "Hao, X. and Chettiar, K. and Cheung, B. and Germano, V. and Hamid, R.",
TITLE = "Intro and Recap Detection for Movies and TV Series",
BOOKTITLE = WACV21,
YEAR = "2021",
PAGES = "167-176",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242824"}
@inproceedings{bb247983,
AUTHOR = "Bain, M. and Nagrani, A. and Brown, A. and Zisserman, A.",
TITLE = "Condensed Movies: Story Based Retrieval with Contextual Embeddings",
BOOKTITLE = ACCV20,
YEAR = "2020",
PAGES = "V:460-479",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242825"}
@inproceedings{bb247984,
AUTHOR = "Wang, L. and Liu, D. and Puri, R. and Metaxas, D.N.",
TITLE = "Learning Trailer Moments in Full-length Movies with Co-contrastive
Attention",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XVIII:300-316",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242826"}
@inproceedings{bb247985,
AUTHOR = "Huang, Q.Q. and Xiong, Y. and Rao, A. and Wang, J.Z. and Lin, D.H.",
TITLE = "Movienet: A Holistic Dataset for Movie Understanding",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "IV:709-727",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242827"}
@inproceedings{bb247986,
AUTHOR = "Li, K. and Fang, C. and Wang, Z. and Kim, S. and Jin, H. and Fu, Y.",
TITLE = "Screencast Tutorial Video Understanding",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "12523-12532",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242828"}
@inproceedings{bb247987,
AUTHOR = "Nagrani, A. and Sun, C. and Ross, D. and Sukthankar, R. and Schmid, C. and Zisserman, A.",
TITLE = "Speech2Action: Cross-Modal Supervision for Action Recognition",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "10314-10323",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242829"}
@inproceedings{bb247988,
AUTHOR = "Rao, A. and Xu, L. and Xiong, Y. and Xu, G. and Huang, Q. and Zhou, B. and Lin, D.",
TITLE = "A Local-to-Global Approach to Multi-Modal Movie Scene Segmentation",
BOOKTITLE = CVPR20,
YEAR = "2020",
PAGES = "10143-10152",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242830"}
@inproceedings{bb247989,
AUTHOR = "Zhang, M. and Ye, K. and Hwa, R. and Kovashka, A.",
TITLE = "Story Completion with Explicit Modeling of Commonsense Knowledge",
BOOKTITLE = MVM20,
YEAR = "2020",
PAGES = "1543-1546",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242831"}
@inproceedings{bb247990,
AUTHOR = "Li, W.X. and Pan, G. and Wang, C. and Xing, Z. and Zhou, X.Z. and Dong, X.X. and Zhang, J.W.",
TITLE = "From Coarse to Fine: Hierarchical Structure-aware Video Summarization",
BOOKTITLE = MLCSA20,
YEAR = "2020",
PAGES = "75-87",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242832"}
@inproceedings{bb247991,
AUTHOR = "Liu, Y. and Li, Y. and Yang, F. and Chen, S. and Wang, Y.F.",
TITLE = "Learning Hierarchical Self-Attention for Video Summarization",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "3377-3381",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242833"}
@inproceedings{bb247992,
AUTHOR = "Lee, S. and Sung, J. and Yu, Y. and Kim, G.",
TITLE = "A Memory Network Approach for Story-Based Temporal Summarization of
360° Videos",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "1410-1419",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242834"}
@inproceedings{bb247993,
AUTHOR = "Mo, L.B. and Zhang, C.H. and Ji, Y. and Hu, Z.",
TITLE = "Adversarial Learning for Visual Storytelling with Sense Group Partition",
BOOKTITLE = ACCV18,
YEAR = "2018",
PAGES = "IV:175-190",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242835"}
@inproceedings{bb247994,
AUTHOR = "Ueno, M.",
TITLE = "Structure Analysis on Common Plot in Four-Scene Comic Story Dataset",
BOOKTITLE = MANPU19,
YEAR = "2019",
PAGES = "625-636",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242836"}
@inproceedings{bb247995,
AUTHOR = "Zhang, J.C. and Peng, Y.X.",
TITLE = "Hierarchical Vision-Language Alignment for Video Captioning",
BOOKTITLE = "MMMod19",
YEAR = "2019",
PAGES = "I:42-54",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242837"}
@inproceedings{bb247996,
AUTHOR = "Smeaton, A.F. and Graham, Y. and McGuinness, K. and O'Connor, N.E. and Quinn, S. and Sanchez, E.A.",
TITLE = "Exploring the Impact of Training Data Bias on Automatic Generation of
Video Captions",
BOOKTITLE = "MMMod19",
YEAR = "2019",
PAGES = "I:178-190",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242838"}
@inproceedings{bb247997,
AUTHOR = "Guyot, P. and Malon, T. and Roman Jimenez, G. and Chambon, S. and Charvillat, V. and Crouzil, A. and Peninou, A. and Pinquier, J. and Sedes, F. and Senac, C.",
TITLE = "Audiovisual Annotation Procedure for Multi-view Field Recordings",
BOOKTITLE = "MMMod19",
YEAR = "2019",
PAGES = "I:399-410",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242839"}
@inproceedings{bb247998,
AUTHOR = "Gupta, T. and Schwenk, D. and Farhadi, A. and Hoiem, D. and Kembhavi, A.",
TITLE = "Imagine This! Scripts to Compositions to Videos",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "VIII: 610-626",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242840"}
@inproceedings{bb247999,
AUTHOR = "Chen, Y.Y. and Wang, S.H. and Zhang, W.G. and Huang, Q.M.",
TITLE = "Less Is More: Picking Informative Frames for Video Captioning",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "XIII: 367-384",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT242841"}
Last update:Feb 26, 2026 at 10:58:24