@article{bb249600,
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#TT244440"}
@article{bb249601,
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#TT244441"}
@inproceedings{bb249602,
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#TT244442"}
@article{bb249603,
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#TT244443"}
@article{bb249604,
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#TT244444"}
@inproceedings{bb249605,
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#TT244445"}
@inproceedings{bb249606,
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#TT244446"}
@inproceedings{bb249607,
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#TT244447"}
@inproceedings{bb249608,
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#TT244448"}
@inproceedings{bb249609,
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#TT244449"}
@inproceedings{bb249610,
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#TT244450"}
@inproceedings{bb249611,
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#TT244451"}
@inproceedings{bb249612,
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#TT244452"}
@inproceedings{bb249613,
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#TT244453"}
@inproceedings{bb249614,
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#TT244454"}
@inproceedings{bb249615,
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#TT244455"}
@inproceedings{bb249616,
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#TT244456"}
@inproceedings{bb249617,
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#TT244457"}
@inproceedings{bb249618,
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#TT244458"}
@inproceedings{bb249619,
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#TT244459"}
@inproceedings{bb249620,
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#TT244460"}
@inproceedings{bb249621,
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#TT244461"}
@inproceedings{bb249622,
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#TT244462"}
@inproceedings{bb249623,
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#TT244463"}
@inproceedings{bb249624,
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#TT244464"}
@inproceedings{bb249625,
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#TT244465"}
@inproceedings{bb249626,
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#TT244466"}
@inproceedings{bb249627,
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#TT244467"}
@inproceedings{bb249628,
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#TT244468"}
@inproceedings{bb249629,
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#TT244469"}
@inproceedings{bb249630,
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#TT244470"}
@inproceedings{bb249631,
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#TT244471"}
@inproceedings{bb249632,
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#TT244472"}
@inproceedings{bb249633,
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#TT244473"}
@inproceedings{bb249634,
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#TT244474"}
@inproceedings{bb249635,
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#TT244475"}
@inproceedings{bb249636,
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#TT244476"}
@inproceedings{bb249637,
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#TT244477"}
@inproceedings{bb249638,
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#TT244478"}
@inproceedings{bb249639,
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#TT244479"}
@inproceedings{bb249640,
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#TT244480"}
@inproceedings{bb249641,
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#TT244481"}
@inproceedings{bb249642,
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#TT244482"}
@inproceedings{bb249643,
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#TT244483"}
@inproceedings{bb249644,
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#TT244484"}
@inproceedings{bb249645,
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#TT244485"}
@inproceedings{bb249646,
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#TT244486"}
@inproceedings{bb249647,
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#TT244487"}
@inproceedings{bb249648,
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#TT244488"}
@inproceedings{bb249649,
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#TT244489"}
@inproceedings{bb249650,
AUTHOR = "Iyyer, M. and Manjunatha, V. and Guha, A. and Vyas, Y. and Boyd Graber, J. and Daume, H. and Davis, L.S.",
TITLE = "The Amazing Mysteries of the Gutter:
Drawing Inferences Between Panels in Comic Book Narratives",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "6478-6487",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244490"}
@inproceedings{bb249651,
AUTHOR = "Khan, U.A. and Ejaz, N. and Martinez del Amor, M.A. and Sparenberg, H.",
TITLE = "Movies tags extraction using deep learning",
BOOKTITLE = AVSS17,
YEAR = "2017",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244491"}
@inproceedings{bb249652,
AUTHOR = "Zhong, G. and Tsai, Y.H. and Liu, S. and Su, Z. and Yang, M.H.",
TITLE = "Learning Video-Story Composition via Recurrent Neural Network",
BOOKTITLE = WACV18,
YEAR = "2018",
PAGES = "1727-1735",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244492"}
@inproceedings{bb249653,
AUTHOR = "Na, S. and Lee, S.H. and Kim, J.S. and Kim, G.",
TITLE = "A Read-Write Memory Network for Movie Story Understanding",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "677-685",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244493"}
@inproceedings{bb249654,
AUTHOR = "Naim, I. and Al Mamun, A. and Song, Y.C. and Luo, J. and Kautz, H. and Gildea, D.",
TITLE = "Aligning movies with scripts by exploiting temporal ordering
constraints",
BOOKTITLE = ICPR16,
YEAR = "2016",
PAGES = "1786-1791",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244494"}
@inproceedings{bb249655,
AUTHOR = "Tapaswi, M. and Zhu, Y. and Stiefelhagen, R. and Torralba, A.B. and Urtasun, R. and Fidler, S.",
TITLE = "MovieQA: Understanding Stories in Movies through Question-Answering",
BOOKTITLE = CVPR16,
YEAR = "2016",
PAGES = "4631-4640",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244495"}
@inproceedings{bb249656,
AUTHOR = "Suchan, J. and Bhatt, M.",
TITLE = "The geometry of a scene:
On deep semantics for visual perception driven cognitive film, studies",
BOOKTITLE = WACV16,
YEAR = "2016",
PAGES = "1-9",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244496"}
@inproceedings{bb249657,
AUTHOR = "Qu, B.Q. and Vallet, F. and Carrive, J. and Gravier, G.",
TITLE = "Content-Based Discovery of Multiple Structures from Episodes of
Recurrent TV Programs Based on Grammatical Inference",
BOOKTITLE = MMMod15,
YEAR = "2015",
PAGES = "I: 140-154",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244497"}
@inproceedings{bb249658,
AUTHOR = "Song, Y. and Vallmitjana, J. and Stent, A. and Jaimes, A.",
TITLE = "TVSum: Summarizing web videos using titles",
BOOKTITLE = CVPR15,
YEAR = "2015",
PAGES = "5179-5187",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244498"}
@inproceedings{bb249659,
AUTHOR = "Koutras, P. and Zlatintsi, A. and Iosif, E. and Katsamanis, A. and Maragos, P. and Potamianos, A.",
TITLE = "Predicting audio-visual salient events based on visual, audio and
text modalities for movie summarization",
BOOKTITLE = ICIP15,
YEAR = "2015",
PAGES = "4361-4365",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244499"}
@inproceedings{bb249660,
AUTHOR = "Eberts, M. and Ulges, A. and Schwanecke, U.",
TITLE = "AMIGO - automatic indexing of lecture footage",
BOOKTITLE = ICDAR15,
YEAR = "2015",
PAGES = "1206-1210",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244500"}
@inproceedings{bb249661,
AUTHOR = "Zhu, Y. and Kiros, R. and Zemel, R. and Salakhutdinov, R. and Urtasun, R. and Torralba, A.B. and Fidler, S.",
TITLE = "Aligning Books and Movies: Towards Story-Like Visual Explanations by
Watching Movies and Reading Books",
BOOKTITLE = ICCV15,
YEAR = "2015",
PAGES = "19-27",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244501"}
@inproceedings{bb249662,
AUTHOR = "Xu, P. and Tax, D.M.J. and Hanjalic, A.",
TITLE = "A structure-based video representation for web video categorization",
BOOKTITLE = ICPR12,
YEAR = "2012",
PAGES = "433-436",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244502"}
@inproceedings{bb249663,
AUTHOR = "Hanjalic, A. and Xu, L.Q.",
TITLE = "User-Oriented Affective Video Content Analysis",
BOOKTITLE = CBAIVL01,
YEAR = "2001",
PAGES = "50",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244503"}
@inproceedings{bb249664,
AUTHOR = "Shrestha, A. and Zhu, Y. and Miller, B. and Zhao, Y.",
TITLE = "Storygraph: Telling Stories from Spatio-temporal Data",
BOOKTITLE = ISVC13,
YEAR = "2013",
PAGES = "II:693-702",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244504"}
@inproceedings{bb249665,
AUTHOR = "Lu, Z. and Grauman, K.",
TITLE = "Story-Driven Summarization for Egocentric Video",
BOOKTITLE = CVPR13,
YEAR = "2013",
PAGES = "2714-2721",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244505"}
@inproceedings{bb249666,
AUTHOR = "Chowdhury, A.S. and Kuanar, S.K. and Panda, R. and Das, M.N.",
TITLE = "Video storyboard design using Delaunay graphs",
BOOKTITLE = ICPR12,
YEAR = "2012",
PAGES = "3108-3111",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244506"}
@inproceedings{bb249667,
AUTHOR = "Fu, W. and Wang, J.Q. and Zhu, X.B. and Lu, H.Q. and Ma, S.D.",
TITLE = "Video Reshuffling with Narratives toward Effective Video Browsing",
BOOKTITLE = ICIG11,
YEAR = "2011",
PAGES = "821-826",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244507"}
@inproceedings{bb249668,
AUTHOR = "Jain, M. and Jawahar, C.V.",
TITLE = "Characteristic pattern discovery in videos",
BOOKTITLE = ICCVGIP10,
YEAR = "2010",
PAGES = "306-313",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244508"}
@inproceedings{bb249669,
AUTHOR = "Ding, L. and Yilmaz, A.",
TITLE = "Learning Relations among Movie Characters: A Social Network Perspective",
BOOKTITLE = ECCV10,
YEAR = "2010",
PAGES = "IV: 410-423",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244509"}
@inproceedings{bb249670,
AUTHOR = "Rodriguez, M.",
TITLE = "CRAM: Compact representation of actions in movies",
BOOKTITLE = CVPR10,
YEAR = "2010",
PAGES = "3328-3335",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244510"}
@inproceedings{bb249671,
AUTHOR = "Zhao, Z.C. and Ge, X.J.",
TITLE = "A computable structure model for Hollywood film",
BOOKTITLE = ICIP10,
YEAR = "2010",
PAGES = "877-880",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244511"}
@inproceedings{bb249672,
AUTHOR = "Zhang, S.L. and Tian, Q. and Huang, Q.M. and Gao, W. and Li, S.P.",
TITLE = "Utilizing affective analysis for efficient movie browsing",
BOOKTITLE = ICIP09,
YEAR = "2009",
PAGES = "1853-1856",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244512"}
@inproceedings{bb249673,
AUTHOR = "Gupta, A. and Srinivasan, P. and Shi, J.B. and Davis, L.S.",
TITLE = "Understanding videos, constructing plots learning a visually grounded
storyline model from annotated videos",
BOOKTITLE = CVPR09,
YEAR = "2009",
PAGES = "2012-2019",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244513"}
@inproceedings{bb249674,
AUTHOR = "Evangelopoulos, G. and Rapantzikos, K. and Potamianos, A. and Maragos, P. and Zlatintsi, A. and Avrithis, Y.S.",
TITLE = "Movie summarization based on audiovisual saliency detection",
BOOKTITLE = ICIP08,
YEAR = "2008",
PAGES = "2528-2531",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244514"}
@inproceedings{bb249675,
AUTHOR = "Lee, F. and Bailer, W.",
TITLE = "Organizing rushes video by visually similar setting",
BOOKTITLE = CIVR08,
YEAR = "2008",
PAGES = "279-288",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244515"}
@inproceedings{bb249676,
AUTHOR = "Bailer, W. and Dumont, E. and Essid, S. and Merialdo, B.",
TITLE = "A collaborative approach to automatic rushes video summarization",
BOOKTITLE = ICIP08,
YEAR = "2008",
PAGES = "29-32",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244516"}
@inproceedings{bb249677,
AUTHOR = "Liu, A.A. and Tang, S. and Zhang, Y.D. and Song, Y. and Li, J.T. and Yang, Z.X.",
TITLE = "A hierarchical framework for movie content analysis:
Let computers watch films like humans",
BOOKTITLE = SLAM08,
YEAR = "2008",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244517"}
@inproceedings{bb249678,
AUTHOR = "Kawai, Y. and Sumiyoshi, H. and Yagi, N.",
TITLE = "Automated production of TV program trailer using electronic program
guide",
BOOKTITLE = CIVR07,
YEAR = "2007",
PAGES = "49-56",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244518"}
@inproceedings{bb249679,
AUTHOR = "Lu, X.A. and Zhai, J.F. and Gomila, C.",
TITLE = "A New Spatial Activity Metric for Film Contents",
BOOKTITLE = ICIP07,
YEAR = "2007",
PAGES = "VI: 473-476",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244519"}
@inproceedings{bb249680,
AUTHOR = "Choi, J. and Oh, T.H. and Kweon, I.S.",
TITLE = "Video-Story Composition via Plot Analysis",
BOOKTITLE = CVPR16,
YEAR = "2016",
PAGES = "3122-3130",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244520"}
@inproceedings{bb249681,
AUTHOR = "Geng, Y.L. and Xu, D. and Feng, S.H.",
TITLE = "Hierarchical Video Summarization Based on Video Structure and Highlight",
BOOKTITLE = SSPR06,
YEAR = "2006",
PAGES = "226-234",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244521"}
@inproceedings{bb249682,
AUTHOR = "Schweitzer, H.",
TITLE = "Computing Content-Plots for Video",
BOOKTITLE = ECCV02,
YEAR = "2002",
PAGES = "IV: 491 ff.",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244522"}
@inproceedings{bb249683,
AUTHOR = "Phung, D.Q. and Dorai, C. and Verikatesh, S.",
TITLE = "Narrative structure analysis with education and training videos for
e-learning",
BOOKTITLE = ICPR02,
YEAR = "2002",
PAGES = "II: 835-838",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825mo1.html#TT244523"}
@article{bb249684,
AUTHOR = "Sudhir, G. and Lee, J.C.M.",
TITLE = "Video Annotation by Motion Interpretation Using Optical-Flow Streams",
JOURNAL = JVCIR,
VOLUME = "7",
YEAR = "1996",
NUMBER = "4",
MONTH = "December",
PAGES = "354-368",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244524"}
@article{bb249685,
AUTHOR = "Carrer, M. and Ligresti, L. and Ahanger, G. and Little, T.D.C.",
TITLE = "An Annotation Engine for Supporting Video Database Population",
JOURNAL = MultToolApp,
VOLUME = "5",
YEAR = "1997",
NUMBER = "3",
MONTH = "November",
PAGES = "233-258",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244525"}
@article{bb249686,
AUTHOR = "Tan, Y.P. and Saur, D.D. and Kulkarni, S.R. and Ramadge, P.J.",
TITLE = "Rapid Estimation of Camera Motion from Compressed Video with
Application to Video Annotation",
JOURNAL = CirSysVideo,
VOLUME = "10",
YEAR = "2000",
NUMBER = "1",
MONTH = "February",
PAGES = "133",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244526"}
@inproceedings{bb249687,
AUTHOR = "Purnaveja, A. and Chaddha, N. and Vellanki, S.P. and del Val, D. and Gupta, A. and Wang, E.Y.B.",
TITLE = "Production of a video stream with synchronized annotations
over a computer network",
BOOKTITLE = US_Patent,
YEAR = "2001",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244527"}
@article{bb249688,
AUTHOR = "Chang, E. and Goh, K. and Sychay, G. and Wu, G.",
TITLE = "CBSA: content-based soft annotation for multimodal image retrieval
using bayes point machines",
JOURNAL = CirSysVideo,
VOLUME = "13",
YEAR = "2003",
NUMBER = "1",
MONTH = "January",
PAGES = "26-38",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244528"}
@article{bb249689,
AUTHOR = "Dorado, A. and Calic, J. and Izquierdo, E.",
TITLE = "A rule-based video annotation system",
JOURNAL = CirSysVideo,
VOLUME = "14",
YEAR = "2004",
NUMBER = "5",
MONTH = "May",
PAGES = "622-633",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244529"}
@article{bb249690,
AUTHOR = "Carneiro, G. and Chan, A.B. and Moreno, P.J. and Vasconcelos, N.M.",
TITLE = "Supervised Learning of Semantic Classes for Image Annotation and
Retrieval",
JOURNAL = PAMI,
VOLUME = "29",
YEAR = "2007",
NUMBER = "3",
MONTH = "March",
PAGES = "394-410",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244530"}
@inproceedings{bb249691,
AUTHOR = "Carneiro, G. and Vasconcelos, N.M.",
TITLE = "Formulating Semantic Image Annotation as a Supervised Learning Problem",
BOOKTITLE = CVPR05,
YEAR = "2005",
PAGES = "II: 163-168",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244531"}
@article{bb249692,
AUTHOR = "Anjulan, A. and Canagarajah, C.N.",
TITLE = "Object based video retrieval with local region tracking",
JOURNAL = SP:IC,
VOLUME = "22",
YEAR = "2007",
NUMBER = "7-8",
MONTH = "August",
PAGES = "607-621",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244532"}
@inproceedings{bb249693,
AUTHOR = "Anjulan, A. and Canagarajah, C.N.",
TITLE = "A Novel Video Mining System",
BOOKTITLE = ICIP07,
YEAR = "2007",
PAGES = "I: 185-188",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244533"}
@inproceedings{bb249694,
AUTHOR = "Anjulan, A. and Canagarajah, C.N.",
TITLE = "Video Object Mining with Local Region Tracking",
BOOKTITLE = MCAM07,
YEAR = "2007",
PAGES = "172-183",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244534"}
@inproceedings{bb249695,
AUTHOR = "Anjulan, A. and Canagarajah, C.N.",
TITLE = "Video Scene Retrieval Based on Local Region Features",
BOOKTITLE = ICIP06,
YEAR = "2006",
PAGES = "3177-3180",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244535"}
@inproceedings{bb249696,
AUTHOR = "Anjulan, A. and Canagarajah, C.N.",
TITLE = "A Novel Framework for Robust Annotation and Retrieval in Video
Sequences",
BOOKTITLE = CIVR06,
YEAR = "2006",
PAGES = "183-192",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244536"}
@article{bb249697,
AUTHOR = "Ionescu, B. and Coquin, D. and Lambert, P. and Buzuloiu, V.",
TITLE = "A Fuzzy Color-Based Approach for Understanding Animated Movies Content
in the Indexing Task",
JOURNAL = JIVP,
VOLUME = "2008",
YEAR = "2008",
NUMBER = "2008",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244537"}
@inproceedings{bb249698,
AUTHOR = "Ionescu, B. and Seyerlehner, K. and Rasche, C. and Vertan, C. and Lambert, P.",
TITLE = "Content-Based Video Description for Automatic Video Genre
Categorization",
BOOKTITLE = MMMod12,
YEAR = "2012",
PAGES = "51-62",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244538"}
@article{bb249699,
AUTHOR = "Anjulan, A. and Canagarajah, C.N.",
TITLE = "A Unified Framework for Object Retrieval and Mining",
JOURNAL = CirSysVideo,
VOLUME = "19",
YEAR = "2009",
NUMBER = "1",
MONTH = "January",
PAGES = "63-76",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825an1.html#TT244539"}
Last update:May 24, 2026 at 14:46:09