@inproceedings{bb243900,
AUTHOR = "Kanehira, A. and Takemoto, K. and Inayoshi, S. and Harada, T.",
TITLE = "Multimodal Explanations by Predicting Counterfactuality in Videos",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "8586-8594",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238792"}
@inproceedings{bb243901,
AUTHOR = "Kanehira, A. and Harada, T.",
TITLE = "Learning to Explain With Complemental Examples",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "8595-8603",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238793"}
@inproceedings{bb243902,
AUTHOR = "Zhou, L. and Kalantidis, Y. and Chen, X.L. and Corso, J.J. and Rohrbach, M.",
TITLE = "Grounded Video Description",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "6571-6580",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238794"}
@inproceedings{bb243903,
AUTHOR = "Liu, X.Y. and Lee, J.Y. and Jin, H.L.",
TITLE = "Learning Video Representations From Correspondence Proposals",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "4268-4276",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238795"}
@inproceedings{bb243904,
AUTHOR = "Xiong, B. and Kalantidis, Y. and Ghadiyaram, D. and Grauman, K.",
TITLE = "Less Is More: Learning Highlight Detection From Video Duration",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "1258-1267",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238796"}
@inproceedings{bb243905,
AUTHOR = "Zhang, D. and Dai, X. and Wang, X. and Wang, Y.F. and Davis, L.S.",
TITLE = "MAN: Moment Alignment Network for Natural Language Moment Retrieval via
Iterative Graph Adjustment",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "1247-1257",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238797"}
@inproceedings{bb243906,
AUTHOR = "Fan, L. and Huang, W. and Gan, C. and Ermon, S. and Gong, B. and Huang, J.",
TITLE = "End-to-End Learning of Motion Representation for Video Understanding",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "6016-6025",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238798"}
@inproceedings{bb243907,
AUTHOR = "Huang, D. and Ramanathan, V. and Mahajan, D. and Torresani, L. and Paluri, M. and Fei Fei, L. and Niebles, J.C.",
TITLE = "What Makes a Video a Video: Analyzing Temporal Information in Video
Understanding Models and Datasets",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7366-7375",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238799"}
@inproceedings{bb243908,
AUTHOR = "Mahdisoltani, F. and Memisevic, R. and Fleet, D.J.",
TITLE = "Hierarchical Video Understanding",
BOOKTITLE = WiCV-E18,
YEAR = "2018",
PAGES = "IV:659-663",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238800"}
@inproceedings{bb243909,
AUTHOR = "Shin, K.S. and Jeon, J. and Lee, S. and Lim, B. and Jeong, M.S. and Nang, J.",
TITLE = "Approach for Video Classification with Multi-label on YouTube-8M
Dataset",
BOOKTITLE = Large-Scale18,
YEAR = "2018",
PAGES = "IV:317-324",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238801"}
@inproceedings{bb243910,
AUTHOR = "Skalic, M. and Austin, D.",
TITLE = "Building A Size Constrained Predictive Models for Video Classification",
BOOKTITLE = Large-Scale18,
YEAR = "2018",
PAGES = "IV:297-305",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238802"}
@inproceedings{bb243911,
AUTHOR = "Garg, S.",
TITLE = "Learning Video Features for Multi-label Classification",
BOOKTITLE = Large-Scale18,
YEAR = "2018",
PAGES = "IV:325-337",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238803"}
@inproceedings{bb243912,
AUTHOR = "Cho, C. and Antin, B. and Arora, S. and Ashrafi, S. and Duan, P.L. and Huynh, D.T. and James, L. and Nguyen, H.T. and Solgi, M. and Than, C.V.",
TITLE = "Large-Scale Video Classification with Feature Space Augmentation
Coupled with Learned Label Relations and Ensembling",
BOOKTITLE = Large-Scale18,
YEAR = "2018",
PAGES = "IV:338-346",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238804"}
@inproceedings{bb243913,
AUTHOR = "Lin, R.C. and Xiao, J. and Fan, J.P.",
TITLE = "NeXtVLAD: An Efficient Neural Network to Aggregate Frame-Level Features
for Large-Scale Video Classification",
BOOKTITLE = Large-Scale18,
YEAR = "2018",
PAGES = "IV:206-218",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238805"}
@inproceedings{bb243914,
AUTHOR = "Tang, Y.Y. and Zhang, X. and Wang, J.W. and Chen, S.X. and Ma, L. and Jiang, Y.G.",
TITLE = "Non-local NetVLAD Encoding for Video Classification",
BOOKTITLE = Large-Scale18,
YEAR = "2018",
PAGES = "IV:219-228",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238806"}
@inproceedings{bb243915,
AUTHOR = "Kmiec, S. and Bae, J. and An, R.J.",
TITLE = "Learnable Pooling Methods for Video Classification",
BOOKTITLE = Large-Scale18,
YEAR = "2018",
PAGES = "IV:229-238",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238807"}
@inproceedings{bb243916,
AUTHOR = "Liu, T.Q. and Liu, B.",
TITLE = "Constrained-Size Tensorflow Models for YouTube-8M Video Understanding
Challenge",
BOOKTITLE = Large-Scale18,
YEAR = "2018",
PAGES = "IV:239-249",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238808"}
@inproceedings{bb243917,
AUTHOR = "Lee, J. and Natsev, A.P. and Reade, W. and Sukthankar, R. and Toderici, G.",
TITLE = "The 2nd YouTube-8M Large-Scale Video Understanding Challenge",
BOOKTITLE = Large-Scale18,
YEAR = "2018",
PAGES = "IV:193-205",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238809"}
@inproceedings{bb243918,
AUTHOR = "Zolfaghari, M. and Singh, K. and Brox, T.",
TITLE = "ECO: Efficient Convolutional Network for Online Video Understanding",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "II: 713-730",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238810"}
@inproceedings{bb243919,
AUTHOR = "Sah, S. and Nguyen, T. and Dominguez, M. and Such, F.P. and Ptucha, R.",
TITLE = "Temporally Steered Gaussian Attention for Video Understanding",
BOOKTITLE = DeepLearn-T17,
YEAR = "2017",
PAGES = "2208-2216",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238811"}
@inproceedings{bb243920,
AUTHOR = "Jiang, Y.G. and Ye, G. and Chang, S.F. and Ellis, D. and Loui, A.C.",
TITLE = "Consumer video understanding: a benchmark database and an evaluation of
human and machine performance",
BOOKTITLE = ICMR11,
YEAR = "2011",
PAGES = "29",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238812"}
@inproceedings{bb243921,
AUTHOR = "Yang, Y. and Liu, J.G. and Shah, M.",
TITLE = "Video Scene Understanding Using Multi-scale Analysis",
BOOKTITLE = ICCV09,
YEAR = "2009",
PAGES = "1669-1676",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vu1.html#TT238813"}
@article{bb243922,
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/applicat825lovu2.html#TT238814"}
@article{bb243923,
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/applicat825lovu2.html#TT238815"}
@inproceedings{bb243924,
AUTHOR = "Liu, S.M. and Zhao, C. and Xu, T.Q. and Ghanem, B.",
TITLE = "BOLT: Boost Large Vision-Language Model Without Training for
Long-Form Video Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3318-3327",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238816"}
@inproceedings{bb243925,
AUTHOR = "Jang, H. and Yu, S. and Shin, J. and Abbeel, P. and Seo, Y.",
TITLE = "Efficient Long Video Tokenization via Coordinate-based Patch
Reconstruction",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "22853-22863",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238817"}
@inproceedings{bb243926,
AUTHOR = "Man, Y.B. and Huang, Y. and Zhang, C.M. and Li, B.Z. and Niu, W. and Yin, M.",
TITLE = "AdaCM2: On Understanding Extremely Long-Term Video with Adaptive
Cross-Modality Memory Reduction",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8534-8544",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238818"}
@inproceedings{bb243927,
AUTHOR = "Ren, W.M. and Yang, H. and Min, J. and Wei, C. and Chen, W.",
TITLE = "VISTA: Enhancing Long-Duration and High-Resolution Video
Understanding by VIdeo SpatioTemporal Augmentation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3804-3814",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238819"}
@inproceedings{bb243928,
AUTHOR = "Wang, Z.Y. and Yu, S. and Stengel Eskin, E. and Yoon, J. and Cheng, F. and Bertasius, G. and Bansal, M.",
TITLE = "VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning
on Long Videos",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3272-3282",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238820"}
@inproceedings{bb243929,
AUTHOR = "Ye, J.H. and Wang, Z. and Sun, H. and Chandrasegaran, K. and Durante, Z. and Eyzaguirre, C. and Bisk, Y. and Niebles, J.C. and Adeli, E. and Fei Fei, L. and Wu, J.J. and Li, M.",
TITLE = "Re-thinking Temporal Search for Long-Form Video Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8579-8591",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238821"}
@inproceedings{bb243930,
AUTHOR = "Wang, L. and Chen, Y.J. and Tran, D. and Boddeti, V.N. and Chu, W.S.",
TITLE = "SEAL: SEmantic Attention Learning for Long Video Representation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "26192-26201",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238822"}
@inproceedings{bb243931,
AUTHOR = "Pan, Y. and Zhang, C. and Bertasius, G.",
TITLE = "Basket: A Large-Scale Video Dataset for Fine-Grained Skill Estimation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "28952-28962",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238823"}
@inproceedings{bb243932,
AUTHOR = "Zhou, J.J. and Shu, Y. and Zhao, B. and Wu, B. and Liang, Z.Y. and Xiao, S.T. and Qin, M.H. and Yang, X. and Xiong, Y.P. and Zhang, B. and Huang, T.J. and Liu, Z.",
TITLE = "MLVU: Benchmarking Multi-task Long Video Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13691-13701",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238824"}
@inproceedings{bb243933,
AUTHOR = "Shu, Y. and Liu, Z. and Zhang, P. and Qin, M.H. and Zhou, J.J. and Liang, Z.Y. and Huang, T.J. and Zhao, B.",
TITLE = "Video-XL: Extra-Long Vision Language Model for Hour-Scale Video
Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "26160-26169",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238825"}
@inproceedings{bb243934,
AUTHOR = "Tang, X. and Qiu, J. and Xie, L.X. and Tian, Y.J. and Jiao, J.B. and Ye, Q.X.",
TITLE = "Adaptive Keyframe Sampling for Long Video Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29118-29128",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238826"}
@inproceedings{bb243935,
AUTHOR = "Ventura, L. and Yang, A. and Schmid, C. and Varol, G.",
TITLE = "Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18947-18958",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238827"}
@inproceedings{bb243936,
AUTHOR = "Geng, T.T. and Zhang, J. and Wang, Q. and Wang, T. and Duan, J.M. and Zheng, F.",
TITLE = "LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware
Omni-Modal Perception of Long Videos",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18959-18969",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238828"}
@inproceedings{bb243937,
AUTHOR = "Kim, J. and Kim, H. and Lee, H. and Ro, Y.M.",
TITLE = "SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval
and Routing in Long-Form Video Analysis",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3352-3362",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238829"}
@inproceedings{bb243938,
AUTHOR = "Song, E. and Chai, W.H. and Wang, G. and Zhang, Y.C. and Zhou, H.Y. and Wu, F. and Chi, H.Z. and Guo, X. and Ye, T. and Zhang, Y.T. and Lu, Y. and Hwang, J.N. and Wang, G.A.",
TITLE = "MovieChat: From Dense Token to Sparse Memory for Long Video
Understanding",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18221-18232",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238830"}
@inproceedings{bb243939,
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/applicat825lovu2.html#TT238831"}
@inproceedings{bb243940,
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/applicat825lovu2.html#TT238832"}
@inproceedings{bb243941,
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/applicat825lovu2.html#TT238833"}
@inproceedings{bb243942,
AUTHOR = "He, B. and Li, H. and Jang, Y.K. and Jia, M.L. and Cao, X.F. and Shah, A. and Shrivastava, A. and Lim, S.N.",
TITLE = "MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video
Understanding",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13504-13514",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238834"}
@inproceedings{bb243943,
AUTHOR = "Zhang, C.Y. and Lin, K. and Yang, Z.Y. and Wang, J.F. and Li, L.J. and Lin, C.C. and Liu, Z.C. and Wang, L.J.",
TITLE = "MM-Narrator: Narrating Long-form Videos with Multimodal In-Context
Learning",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13647-13657",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238835"}
@inproceedings{bb243944,
AUTHOR = "Ren, S. and Yao, L. and Li, S.C. and Sun, X. and Hou, L.",
TITLE = "TimeChat: A Time-sensitive Multimodal Large Language Model for Long
Video Understanding",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14313-14323",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238836"}
@inproceedings{bb243945,
AUTHOR = "Xu, M. and Gould, S.",
TITLE = "Temporally Consistent Unbalanced Optimal Transport for Unsupervised
Action Segmentation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "14618-14627",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238837"}
@inproceedings{bb243946,
AUTHOR = "Rodin, I. and Furnari, A. and Min, K. and Tripathi, S. and Farinella, G.M.",
TITLE = "Action Scene Graphs for Long-Form Understanding of Egocentric Videos",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "18622-18632",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238838"}
@inproceedings{bb243947,
AUTHOR = "Ataallah, K. and Shen, X.Q. and Abdelrahman, E. and Sleiman, E. and Zhuge, M.C. and Ding, J. and Zhu, D. and Schmidhuber, J. and Elhoseiny, M.",
TITLE = "Goldfish: Vision-language Understanding of Arbitrarily Long Videos",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXIX: 251-267",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238839"}
@inproceedings{bb243948,
AUTHOR = "Afham, M. and Shukla, S.N. and Poursaeed, O. and Zhang, P. and Shah, A. and Lim, S.",
TITLE = "Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for
Long-form Video Understanding",
BOOKTITLE = REDLCV23,
YEAR = "2023",
PAGES = "1181-1186",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238840"}
@inproceedings{bb243949,
AUTHOR = "Strafforello, O. and Schutte, K. and van Gemert, J.C.",
TITLE = "Are current long-term video understanding datasets long-term?",
BOOKTITLE = CVEU23,
YEAR = "2023",
PAGES = "2959-2968",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238841"}
@inproceedings{bb243950,
AUTHOR = "Yang, X.T. and Chu, F.J. and Feiszli, M. and Goyal, R. and Torresani, L. and Tran, D.",
TITLE = "Relational Space-Time Query in Long-Form Videos",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6398-6408",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238842"}
@inproceedings{bb243951,
AUTHOR = "Wang, J. and Zhu, W.T. and Wang, P. and Yu, X. and Liu, L. and Omar, M. and Hamid, R.",
TITLE = "Selective Structured State-Spaces for Long-Form Video Understanding",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6387-6397",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238843"}
@inproceedings{bb243952,
AUTHOR = "Islam, M.M. and Bertasius, G.",
TITLE = "Long Movie Clip Classification with State-Space Video Models",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXXV:87-104",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238844"}
@inproceedings{bb243953,
AUTHOR = "Wu, C.Y. and Krahenbuhl, P.",
TITLE = "Towards Long-Form Video Understanding",
BOOKTITLE = CVPR21,
YEAR = "2021",
PAGES = "1884-1894",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825lovu2.html#TT238845"}
@article{bb243954,
AUTHOR = "Kim, C. and Hwang, J.N.",
TITLE = "Object-based video abstraction for video surveillance systems",
JOURNAL = CirSysVideo,
VOLUME = "12",
YEAR = "2002",
NUMBER = "12",
MONTH = "December",
PAGES = "1128-1138",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238846"}
@inproceedings{bb243955,
AUTHOR = "Kim, C. and Hwang, J.N.",
TITLE = "Object-based Video Abstraction Using Cluster Analysis",
BOOKTITLE = ICIP01,
YEAR = "2001",
PAGES = "II: 657-660",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238847"}
@article{bb243956,
AUTHOR = "Pritch, Y. and Rav Acha, A. and Peleg, S.",
TITLE = "Nonchronological Video Synopsis and Indexing",
JOURNAL = PAMI,
VOLUME = "30",
YEAR = "2008",
NUMBER = "11",
MONTH = "November",
PAGES = "1971-1984",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238848"}
@inproceedings{bb243957,
AUTHOR = "Rav Acha, A. and Pritch, Y. and Peleg, S.",
TITLE = "Making a Long Video Short: Dynamic Video Synopsis",
BOOKTITLE = CVPR06,
YEAR = "2006",
PAGES = "I: 435-441",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238849"}
@inproceedings{bb243958,
AUTHOR = "Pritch, Y. and Kav Venaki, E. and Peleg, S.",
TITLE = "Shift-map image editing",
BOOKTITLE = ICCV09,
YEAR = "2009",
PAGES = "151-158",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238850"}
@inproceedings{bb243959,
AUTHOR = "Pritch, Y. and Ratovitch, S. and Hendel, A. and Peleg, S.",
TITLE = "Clustered Synopsis of Surveillance Video",
BOOKTITLE = AVSBS09,
YEAR = "2009",
PAGES = "195-200",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238851"}
@inproceedings{bb243960,
AUTHOR = "Peleg, S.",
TITLE = "Keynote lecture 2: Video synopsis",
BOOKTITLE = AVSS13,
YEAR = "2013",
PAGES = "XVII-XVII",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238852"}
@article{bb243961,
AUTHOR = "Xiang, T. and Gong, S.G.",
TITLE = "Optimising dynamic graphical models for video content analysis",
JOURNAL = CVIU,
VOLUME = "112",
YEAR = "2008",
NUMBER = "3",
MONTH = "December",
PAGES = "310-323",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238853"}
@inproceedings{bb243962,
AUTHOR = "Alexiou, I. and Xiang, T. and Gong, S.G.",
TITLE = "Exploring synonyms as context in zero-shot action recognition",
BOOKTITLE = ICIP16,
YEAR = "2016",
PAGES = "4190-4194",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238854"}
@inproceedings{bb243963,
AUTHOR = "Alexiou, I. and Xiang, T. and Gong, S.G.",
TITLE = "Learning a joint discriminative-generative model for action
recognition",
BOOKTITLE = WSSIP15,
YEAR = "2015",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238855"}
@article{bb243964,
AUTHOR = "Mehmood, K. and Mrak, M. and Calic, J. and Kondoz, A.M.",
TITLE = "Object tracking in surveillance videos using compressed domain features
from scalable bit-streams",
JOURNAL = SP:IC,
VOLUME = "24",
YEAR = "2009",
NUMBER = "10",
MONTH = "November",
PAGES = "814-824",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238856"}
@article{bb243965,
AUTHOR = "Hoferlin, M. and Hoferlin, B. and Heidemann, G. and Weiskopf, D.",
TITLE = "Interactive Schematic Summaries for Faceted Exploration
of Surveillance Video",
JOURNAL = MultMed,
VOLUME = "15",
YEAR = "2013",
NUMBER = "4",
PAGES = "908-920",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238857"}
@inproceedings{bb243966,
AUTHOR = "Hoferlin, M. and Hoferlin, B. and Weiskopf, D. and Heidemann, G.",
TITLE = "Interactive schematic summaries for exploration of surveillance video",
BOOKTITLE = ICMR11,
YEAR = "2011",
PAGES = "9",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238858"}
@article{bb243967,
AUTHOR = "Wang, S.Z. and Wang, Z.Y. and Hu, R.M.",
TITLE = "Surveillance video synopsis in the compressed domain for fast video
browsing",
JOURNAL = JVCIR,
VOLUME = "24",
YEAR = "2013",
NUMBER = "8",
PAGES = "1431-1442",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238859"}
@article{bb243968,
AUTHOR = "Chen, Y. and Zhang, B.L.",
TITLE = "Surveillance video summarisation by jointly applying moving object
detection and tracking",
JOURNAL = IJCVR,
VOLUME = "4",
YEAR = "2014",
NUMBER = "3",
PAGES = "212-234",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238860"}
@article{bb243969,
AUTHOR = "Huang, C.R. and Chung, P.C.J. and Yang, D.K. and Chen, H.C. and Huang, G.J.",
TITLE = "Maximum a Posteriori Probability Estimation for Online Surveillance
Video Synopsis",
JOURNAL = CirSysVideo,
VOLUME = "24",
YEAR = "2014",
NUMBER = "8",
MONTH = "August",
PAGES = "1417-1429",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238861"}
@article{bb243970,
AUTHOR = "Cooharojananone, N. and Kasamwattanarote, S. and Lipikorn, R. and Satoh, S.",
TITLE = "Automated real-time video surveillance summarization framework",
JOURNAL = RealTimeIP,
VOLUME = "10",
YEAR = "2015",
NUMBER = "3",
MONTH = "September",
PAGES = "513-532",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238862"}
@article{bb243971,
AUTHOR = "Li, X. and Wang, Z. and Lu, X.",
TITLE = "Surveillance Video Synopsis via Scaling Down Objects",
JOURNAL = IP,
VOLUME = "25",
YEAR = "2016",
NUMBER = "2",
MONTH = "February",
PAGES = "740-755",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238863"}
@article{bb243972,
AUTHOR = "Li, X. and Wang, Z. and Lu, X.",
TITLE = "Video Synopsis in Complex Situations",
JOURNAL = IP,
VOLUME = "27",
YEAR = "2018",
NUMBER = "8",
MONTH = "August",
PAGES = "3798-3812",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238864"}
@inproceedings{bb243973,
AUTHOR = "Wang, S.Z. and Yang, J.W. and Zhao, Y.Y. and Cai, A.N. and Li, S.Z.",
TITLE = "A surveillance video analysis and storage scheme for scalable synopsis
browsing",
BOOKTITLE = VS11,
YEAR = "2011",
PAGES = "1947-1954",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238865"}
@inproceedings{bb243974,
AUTHOR = "Cote, M. and Jean, F. and Albu, A.B. and Capson, D.",
TITLE = "Video summarization for remote invigilation of online exams",
BOOKTITLE = WACV16,
YEAR = "2016",
PAGES = "1-9",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238866"}
@article{bb243975,
AUTHOR = "Zhang, S. and Zhu, Y.Y. and Roy Chowdhury, A.K.",
TITLE = "Context-Aware Surveillance Video Summarization",
JOURNAL = IP,
VOLUME = "25",
YEAR = "2016",
NUMBER = "11",
MONTH = "November",
PAGES = "5469-5478",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238867"}
@article{bb243976,
AUTHOR = "Salehin, M.M. and Paul, M.",
TITLE = "Adaptive fusion of human visual sensitive features for surveillance
video summarization",
JOURNAL = JOSA-A,
VOLUME = "34",
YEAR = "2017",
NUMBER = "5",
MONTH = "May",
PAGES = "814-826",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238868"}
@article{bb243977,
AUTHOR = "Panda, R. and Roy Chowdhury, A.K.",
TITLE = "Multi-View Surveillance Video Summarization via Joint Embedding and
Sparse Optimization",
JOURNAL = MultMed,
VOLUME = "19",
YEAR = "2017",
NUMBER = "9",
MONTH = "September",
PAGES = "2010-2021",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238869"}
@article{bb243978,
AUTHOR = "Tani, M.Y.K. and Ghomari, A. and Lablack, A. and Bilasco, I.M.",
TITLE = "OVIS: ontology video surveillance indexing and retrieval system",
JOURNAL = MultInfoRetr,
VOLUME = "6",
YEAR = "2017",
NUMBER = "4",
MONTH = "December",
PAGES = "295-316",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238870"}
@article{bb243979,
AUTHOR = "Gao, Z. and Lu, G.L. and Yan, P. and Wang, L.",
TITLE = "Retrospective analysis of time series for frame selection in
surveillance video summarization",
JOURNAL = SIViP,
VOLUME = "11",
YEAR = "2017",
NUMBER = "4",
MONTH = "May",
PAGES = "581-588",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238871"}
@article{bb243980,
AUTHOR = "Zhang, Y. and Tao, R. and Wang, Y.",
TITLE = "Motion-State-Adaptive Video Summarization via Spatiotemporal Analysis",
JOURNAL = CirSysVideo,
VOLUME = "27",
YEAR = "2017",
NUMBER = "6",
MONTH = "June",
PAGES = "1340-1352",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238872"}
@article{bb243981,
AUTHOR = "Xu, X. and Hospedales, T.M. and Gong, S.G.",
TITLE = "Discovery of Shared Semantic Spaces for Multiscene Video Query and
Summarization",
JOURNAL = CirSysVideo,
VOLUME = "27",
YEAR = "2017",
NUMBER = "6",
MONTH = "June",
PAGES = "1353-1367",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238873"}
@article{bb243982,
AUTHOR = "Wang, M. and Liang, J.B. and Zhang, S.H. and Lu, S.P. and Shamir, A. and Hu, S.M.",
TITLE = "Hyper-Lapse From Multiple Spatially-Overlapping Videos",
JOURNAL = IP,
VOLUME = "27",
YEAR = "2018",
NUMBER = "4",
MONTH = "April",
PAGES = "1735-1747",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238874"}
@article{bb243983,
AUTHOR = "Gao, Z. and Lu, G.L. and Lyu, C. and Yan, P.",
TITLE = "Key-frame selection for automatic summarization of surveillance videos:
a method of multiple change-point detection",
JOURNAL = MVA,
VOLUME = "29",
YEAR = "2018",
NUMBER = "7",
MONTH = "October",
PAGES = "1101-1117",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238875"}
@article{bb243984,
AUTHOR = "Thomas, S.S. and Gupta, S. and Subramanian, V.K.",
TITLE = "Event Detection on Roads Using Perceptual Video Summarization",
JOURNAL = ITS,
VOLUME = "19",
YEAR = "2018",
NUMBER = "9",
MONTH = "September",
PAGES = "2944-2954",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238876"}
@article{bb243985,
AUTHOR = "Baskurt, K.B. and Samet, R.",
TITLE = "Video synopsis: A survey",
JOURNAL = CVIU,
VOLUME = "181",
YEAR = "2019",
PAGES = "26-38",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238877"}
@article{bb243986,
AUTHOR = "Zhang, Z. and Nie, Y. and Sun, H. and Zhang, Q. and Lai, Q. and Li, G. and Xiao, M.",
TITLE = "Multi-View Video Synopsis via Simultaneous Object-Shifting and
View-Switching Optimization",
JOURNAL = IP,
VOLUME = "29",
YEAR = "2020",
NUMBER = "1",
PAGES = "971-985",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238878"}
@article{bb243987,
AUTHOR = "Nie, Y. and Li, Z. and Zhang, Z. and Zhang, Q. and Ma, T. and Sun, H.",
TITLE = "Collision-Free Video Synopsis Incorporating Object Speed and Size
Changes",
JOURNAL = IP,
VOLUME = "29",
YEAR = "2020",
PAGES = "1465-1478",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238879"}
@article{bb243988,
AUTHOR = "Chen, Y. and Hu, R.M. and Xiao, J. and Wang, Z.Y.",
TITLE = "Multisource surveillance video coding with synthetic reference frame",
JOURNAL = JVCIR,
VOLUME = "65",
YEAR = "2019",
PAGES = "102685",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238880"}
@article{bb243989,
AUTHOR = "Muhammad, K. and Hussain, T. and Baik, S.W.",
TITLE = "Efficient CNN based summarization of surveillance videos for
resource-constrained devices",
JOURNAL = PRL,
VOLUME = "130",
YEAR = "2020",
PAGES = "370-375",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238881"}
@article{bb243990,
AUTHOR = "Sreeja, M.U. and Kovoor, B.C.",
TITLE = "An aggregated deep convolutional recurrent model for event based
surveillance video summarisation: A supervised approach",
JOURNAL = IET-CV,
VOLUME = "15",
YEAR = "2021",
NUMBER = "4",
PAGES = "297-311",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238882"}
@article{bb243991,
AUTHOR = "Wu, L.R. and Huang, K.J. and Shen, H.B. and Gao, L.L.",
TITLE = "Foreground-Background Parallel Compression With Residual Encoding for
Surveillance Video",
JOURNAL = CirSysVideo,
VOLUME = "31",
YEAR = "2021",
NUMBER = "7",
MONTH = "July",
PAGES = "2711-2724",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238883"}
@article{bb243992,
AUTHOR = "Yang, Y. and Kim, H. and Choi, H. and Chae, S. and Kim, I.J.",
TITLE = "Scene Adaptive Online Surveillance Video Synopsis via Dynamic Tube
Rearrangement Using Octree",
JOURNAL = IP,
VOLUME = "30",
YEAR = "2021",
PAGES = "8318-8331",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238884"}
@article{bb243993,
AUTHOR = "Nie, Y.W. and Ge, W. and Zeng, S.M. and Zhang, Q. and Li, G.Q. and Li, P. and Cai, H.M.",
TITLE = "Occlusion-Preserved Surveillance Video Synopsis with Flexible Object
Graph",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "5",
MONTH = "May",
PAGES = "2653-2669",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238885"}
@article{bb243994,
AUTHOR = "Beigh, T.M. and Venkatesan, D.V.P. and Arumugam, J.",
TITLE = "Predictive summarization framework for resource-constrained device
surveillance videos",
JOURNAL = PR,
VOLUME = "171",
YEAR = "2026",
PAGES = "112274",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238886"}
@inproceedings{bb243995,
AUTHOR = "Patel, T. and Yao, A.Y.H. and Qiang, Y. and Ooi, W.T. and Zimmermann, R.",
TITLE = "Multi-Camera Video Scene Graphs for Surveillance Videos Indexing and
Retrieval",
BOOKTITLE = ICIP21,
YEAR = "2021",
PAGES = "2383-2387",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238887"}
@inproceedings{bb243996,
AUTHOR = "Pappalardo, G. and Allegra, D. and Stanco, F. and Battiato, S.",
TITLE = "A New Framework for Studying Tubes Rearrangement Strategies in
Surveillance Video Synopsis",
BOOKTITLE = ICIP19,
YEAR = "2019",
PAGES = "664-668",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238888"}
@inproceedings{bb243997,
AUTHOR = "Durand, T. and He, X. and Pop, I. and Robinault, L.",
TITLE = "Utilizing Deep Object Detector for Video Surveillance Indexing and
Retrieval",
BOOKTITLE = "MMMod19",
YEAR = "2019",
PAGES = "II:506-518",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238889"}
@inproceedings{bb243998,
AUTHOR = "Fang, K. and Wu, T.L. and Yang, D. and Savarese, S. and Lim, J.J.",
TITLE = "Demo2Vec: Reasoning Object Affordances from Online Videos",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "2139-2147",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238890"}
@inproceedings{bb243999,
AUTHOR = "Ravi, H. and Wang, L. and Muniz, C.M. and Sigal, L. and Metaxas, D.N. and Kapadia, M.",
TITLE = "Show Me a Story: Towards Coherent Neural Story Illustration",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7613-7621",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825survi1.html#TT238891"}
Last update:Nov 26, 2025 at 20:24:09