@article{bb222000,
AUTHOR = "Qi, S.S. and Yang, L.X.",
TITLE = "Video captioning via a symmetric bidirectional decoder",
JOURNAL = IET-CV,
VOLUME = "15",
YEAR = "2021",
NUMBER = "4",
PAGES = "283-296",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT216991"}
@article{bb222001,
AUTHOR = "Li, L. and Zhang, Y.D. and Tang, S. and Xie, L.X. and Li, X.Y. and Tian, Q.",
TITLE = "Adaptive Spatial Location With Balanced Loss for Video Captioning",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "1",
MONTH = "January",
PAGES = "17-30",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT216992"}
@article{bb222002,
AUTHOR = "Zheng, Y. and Zhang, Y. and Feng, R. and Zhang, T. and Fan, W.G.",
TITLE = "Stacked Multimodal Attention Network for Context-Aware Video
Captioning",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "1",
MONTH = "January",
PAGES = "31-42",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT216993"}
@article{bb222003,
AUTHOR = "Li, L. and Gao, X.Y. and Deng, J. and Tu, Y. and Zha, Z.J. and Huang, Q.M.",
TITLE = "Long Short-Term Relation Transformer With Global Gating for Video
Captioning",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "2726-2738",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT216994"}
@article{bb222004,
AUTHOR = "Munusamy, H. and Sekhar, C.C.",
TITLE = "Video captioning using Semantically Contextual Generative Adversarial
Network",
JOURNAL = CVIU,
VOLUME = "221",
YEAR = "2022",
PAGES = "103453",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT216995"}
@article{bb222005,
AUTHOR = "Wang, H. and Lin, G.S. and Hoi, S.C.H. and Miao, C.Y.",
TITLE = "Cross-Modal Graph With Meta Concepts for Video Captioning",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "5150-5162",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT216996"}
@article{bb222006,
AUTHOR = "Xiao, H. and Shi, J.L.",
TITLE = "Diverse video captioning through latent variable expansion",
JOURNAL = PRL,
VOLUME = "160",
YEAR = "2022",
PAGES = "19-25",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT216997"}
@article{bb222007,
AUTHOR = "Prudviraj, J. and Reddy, M.I. and Vishnu, C. and Mohan, C.K.",
TITLE = "AAP-MIT: Attentive Atrous Pyramid Network and Memory Incorporated
Transformer for Multisentence Video Description",
JOURNAL = IP,
VOLUME = "31",
YEAR = "2022",
PAGES = "5559-5569",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT216998"}
@article{bb222008,
AUTHOR = "Xu, W. and Miao, Z.J. and Yu, J. and Tian, Y. and Wan, L. and Ji, Q.",
TITLE = "Bridging Video and Text:
A Two-Step Polishing Transformer for Video Captioning",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "9",
MONTH = "September",
PAGES = "6293-6307",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT216999"}
@article{bb222009,
AUTHOR = "Wu, B.F. and Niu, G.C. and Yu, J. and Xiao, X.Y. and Zhang, J. and Wu, H.",
TITLE = "Towards Knowledge-Aware Video Captioning via Transitive Visual
Relationship Detection",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "10",
MONTH = "October",
PAGES = "6753-6765",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217000"}
@article{bb222010,
AUTHOR = "Yan, L.Q. and Ma, S.Q. and Wang, Q.F. and Chen, Y.J. and Zhang, X.Y. and Savakis, A. and Liu, D.F.",
TITLE = "Video Captioning Using Global-Local Representation",
JOURNAL = CirSysVideo,
VOLUME = "32",
YEAR = "2022",
NUMBER = "10",
MONTH = "October",
PAGES = "6642-6656",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217001"}
@article{bb222011,
AUTHOR = "Subramaniam, A. and Vaidya, J. and Ameen, M.A.M. and Nambiar, A. and Mittal, A.",
TITLE = "Co-segmentation inspired attention module for video-based computer
vision tasks",
JOURNAL = CVIU,
VOLUME = "223",
YEAR = "2022",
PAGES = "103532",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217002"}
@article{bb222012,
AUTHOR = "Liu, F.L. and Wu, X. and You, C.Y. and Ge, S. and Zou, Y.X. and Sun, X.",
TITLE = "Aligning Source Visual and Target Language Domains for Unpaired Video
Captioning",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "12",
MONTH = "December",
PAGES = "9255-9268",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217003"}
@article{bb222013,
AUTHOR = "Yuan, Y.T. and Ma, L. and Zhu, W.W.",
TITLE = "Syntax Customized Video Captioning by Imitating Exemplar Sentences",
JOURNAL = PAMI,
VOLUME = "44",
YEAR = "2022",
NUMBER = "12",
MONTH = "December",
PAGES = "10209-10221",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217004"}
@article{bb222014,
AUTHOR = "Chen, H.R. and Li, J.M. and Frintrop, S. and Hu, X.L.",
TITLE = "The MSR-Video to Text dataset with clean annotations",
JOURNAL = CVIU,
VOLUME = "225",
YEAR = "2022",
PAGES = "103581",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217005"}
@article{bb222015,
AUTHOR = "Moctezuma, D. and Ramirez delReal, T. and Ruiz, G. and Gonzalez Chavez, O.",
TITLE = "Video captioning: A comparative review of where we are and which
could be the route",
JOURNAL = CVIU,
VOLUME = "231",
YEAR = "2023",
PAGES = "103671",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217006"}
@article{bb222016,
AUTHOR = "Aafaq, N. and Mian, A. and Akhtar, N. and Liu, W. and Shah, M.",
TITLE = "Dense Video Captioning With Early Linguistic Information Fusion",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "2309-2322",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217007"}
@inproceedings{bb222017,
AUTHOR = "Wang, J.W. and Jiang, W.H. and Ma, L. and Liu, W. and Xu, Y.",
TITLE = "Bidirectional Attentive Fusion with Context Gating for Dense Video
Captioning",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7190-7198",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217008"}
@article{bb222018,
AUTHOR = "He, M.G. and Du, W.J. and Wen, Z.Q. and Du, Q. and Xie, Y.T. and Wu, Q.",
TITLE = "Multi-Granularity Aggregation Transformer for Joint Video-Audio-Text
Representation Learning",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "6",
MONTH = "June",
PAGES = "2990-3002",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217009"}
@article{bb222019,
AUTHOR = "Qian, Y. and Mao, Y.C. and Chen, Z.H. and Li, C. and Bloh, O.T. and Huang, Q.",
TITLE = "Dense video captioning based on local attention",
JOURNAL = IET-IPR,
VOLUME = "17",
YEAR = "2023",
NUMBER = "9",
PAGES = "2673-2685",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217010"}
@article{bb222020,
AUTHOR = "Tang, M.K. and Wang, Z.Y. and Zeng, Z.Y. and Li, X. and Zhou, L.P.",
TITLE = "Stay in Grid: Improving Video Captioning via Fully Grid-Level
Representation",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "7",
MONTH = "July",
PAGES = "3319-3332",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217011"}
@article{bb222021,
AUTHOR = "Velda, V. and Immanuel, S.A. and Hendria, W.F. and Jeong, C.",
TITLE = "Improving distinctiveness in video captioning with text-video
similarity",
JOURNAL = IVC,
VOLUME = "136",
YEAR = "2023",
PAGES = "104728",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217012"}
@article{bb222022,
AUTHOR = "Zhu, J.K. and Zeng, P.P. and Gao, L.L. and Li, G.F. and Liao, D.L. and Song, J.K.",
TITLE = "Complementarity-Aware Space Learning for Video-Text Retrieval",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "8",
MONTH = "August",
PAGES = "4362-4374",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217013"}
@article{bb222023,
AUTHOR = "Wang, H. and Zhang, L. and Fan, H. and Luo, T.J.",
TITLE = "Collaborative three-stream transformers for video captioning",
JOURNAL = CVIU,
VOLUME = "235",
YEAR = "2023",
PAGES = "103799",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217014"}
@inproceedings{bb222024,
AUTHOR = "Gu, X. and Chen, G. and Wang, Y.F. and Zhang, L. and Luo, T.J. and Wen, L.Y.",
TITLE = "Text with Knowledge Graph Augmented Transformer for Video Captioning",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18941-18951",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217015"}
@article{bb222025,
AUTHOR = "Xu, T. and Cui, Y.Y. and He, X.Y. and Liu, C.H.",
TITLE = "A latent topic-aware network for dense video captioning",
JOURNAL = IET-CV,
VOLUME = "17",
YEAR = "2023",
NUMBER = "7",
PAGES = "795-803",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217016"}
@inproceedings{bb222026,
AUTHOR = "Lu, M. and Li, X.Y. and Liu, C.H.",
TITLE = "Context Visual Information-based Deliberation Network for Video
Captioning",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "9812-9818",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217017"}
@article{bb222027,
AUTHOR = "Wu, B. and Liu, B. and Huang, P. and Bao, J. and Xi, P. and Yu, J.",
TITLE = "Concept Parser With Multimodal Graph Learning for Video Captioning",
JOURNAL = CirSysVideo,
VOLUME = "33",
YEAR = "2023",
NUMBER = "9",
MONTH = "September",
PAGES = "4484-4495",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217018"}
@article{bb222028,
AUTHOR = "Liu, S. and Li, A. and Wang, J.H. and Wang, Y.H.",
TITLE = "Bidirectional Maximum Entropy Training With Word Co-Occurrence for
Video Captioning",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "4494-4507",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217019"}
@article{bb222029,
AUTHOR = "Yang, B. and Cao, M. and Zou, Y.X.",
TITLE = "Concept-Aware Video Captioning:
Describing Videos With Effective Prior Information",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "5366-5378",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217020"}
@article{bb222030,
AUTHOR = "Luo, X.M. and Luo, X.T. and Wang, D. and Liu, J.H. and Wan, B. and Zhao, L.",
TITLE = "Global semantic enhancement network for video captioning",
JOURNAL = PR,
VOLUME = "145",
YEAR = "2024",
PAGES = "109906",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217021"}
@article{bb222031,
AUTHOR = "Liu, Z. and Wang, T. and Zhang, J. and Zheng, F. and Jiang, W.H. and Lu, K.",
TITLE = "Show, Tell and Rephrase: Diverse Video Captioning via Two-Stage
Progressive Training",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "7894-7905",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217022"}
@article{bb222032,
AUTHOR = "Rao, Q. and Yu, X. and Li, G. and Zhu, L.C.",
TITLE = "CMGNet: Collaborative multi-modal graph network for video captioning",
JOURNAL = CVIU,
VOLUME = "238",
YEAR = "2024",
PAGES = "103864",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217023"}
@article{bb222033,
AUTHOR = "Li, G.R. and Ye, H.H. and Qi, Y. and Wang, S.H. and Qing, L.Y. and Huang, Q.M. and Yang, M.H.",
TITLE = "Learning Hierarchical Modular Networks for Video Captioning",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "2",
MONTH = "February",
PAGES = "1049-1064",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217024"}
@inproceedings{bb222034,
AUTHOR = "Ye, H.H. and Li, G.R. and Qi, Y. and Wang, S.H. and Huang, Q.M. and Yang, M.H.",
TITLE = "Hierarchical Modular Network for Video Captioning",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "17918-17927",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217025"}
@article{bb222035,
AUTHOR = "Xie, Y.L. and Niu, J.J. and Zhang, Y. and Ren, F.",
TITLE = "Global-Shared Text Representation Based Multi-Stage Fusion
Transformer Network for Multi-Modal Dense Video Captioning",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "3164-3179",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217026"}
@article{bb222036,
AUTHOR = "Jing, S. and Zhang, H. and Zeng, P.P. and Gao, L.L. and Song, J.K. and Shen, H.T.",
TITLE = "Memory-Based Augmentation Network for Video Captioning",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "2367-2379",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217027"}
@article{bb222037,
AUTHOR = "Liang, Y.Z. and Zhu, L.C. and Wang, X.H. and Yang, Y.",
TITLE = "IcoCap: Improving Video Captioning by Compounding Images",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "4389-4400",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217028"}
@article{bb222038,
AUTHOR = "Wang, Z.H. and Li, L. and Xie, Z. and Liu, C.B.",
TITLE = "Video Frame-wise Explanation Driven Contrastive Learning for
Procedural Text Generation",
JOURNAL = CVIU,
VOLUME = "241",
YEAR = "2024",
PAGES = "103954",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217029"}
@article{bb222039,
AUTHOR = "Chen, Y.X. and Zhang, Z.Q. and Qi, Z.A. and Yuan, C.F. and Wang, J. and Shan, Y. and Li, B. and Hu, W.M. and Qie, X. and Wu, J.P.",
TITLE = "DARTScore: DuAl-Reconstruction Transformer for Video Captioning
Evaluation",
JOURNAL = CirSysVideo,
VOLUME = "34",
YEAR = "2024",
NUMBER = "4",
MONTH = "April",
PAGES = "2041-2055",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217030"}
@article{bb222040,
AUTHOR = "Liu, C.S. and Zhang, X. and Chang, F. and Li, S. and Hao, P.H. and Lu, Y. and Wang, Y.",
TITLE = "Traffic Scenario Understanding and Video Captioning via Guidance
Attention Captioning Network",
JOURNAL = ITS,
VOLUME = "25",
YEAR = "2024",
NUMBER = "5",
MONTH = "May",
PAGES = "3615-3627",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217031"}
@article{bb222041,
AUTHOR = "Zhang, Y.J. and Xu, T.Y. and Song, X.N. and Zhu, X.F. and Feng, Z.H. and Wu, X.J.",
TITLE = "Towards accurate unsupervised video captioning with implicit visual
feature injection and explicit",
JOURNAL = PRL,
VOLUME = "183",
YEAR = "2024",
PAGES = "133-139",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217032"}
@article{bb222042,
AUTHOR = "Im, S.K. and Chan, K.H.",
TITLE = "Local feature-based video captioning with multiple classifier and
CARU-attention",
JOURNAL = IET-IPR,
VOLUME = "18",
YEAR = "2024",
NUMBER = "9",
PAGES = "2304-2317",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217033"}
@article{bb222043,
AUTHOR = "Putra, B.H.H. and Jeong, C.",
TITLE = "Video captioning based on dual learning via multiple reconstruction
blocks",
JOURNAL = IVC,
VOLUME = "148",
YEAR = "2024",
PAGES = "105119",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217034"}
@inproceedings{bb222044,
AUTHOR = "Malakan, Z.M. and Hassan, G.M. and Mian, A.",
TITLE = "Sequential Image Storytelling Model Based on Transformer Attention
Pooling",
BOOKTITLE = IVCNZ23,
YEAR = "2023",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217035"}
@inproceedings{bb222045,
AUTHOR = "Sakaino, H.",
TITLE = "Unseen and Adverse Outdoor Scenes Recognition Through Event-based
Captions",
BOOKTITLE = VCL23,
YEAR = "2023",
PAGES = "3596-3603",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217036"}
@inproceedings{bb222046,
AUTHOR = "Ma, Z.Y. and Zhang, Z.Q. and Chen, Y.X. and Qi, Z.A. and Luo, Y.M. and Li, Z.K. and Yuan, C.F. and Li, B. and Qie, X. and Shan, Y. and Hu, W.M.",
TITLE = "Order-Prompted Tag Sequence Generation for Video Tagging",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15635-15644",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217037"}
@inproceedings{bb222047,
AUTHOR = "Bulat, A. and Sanchez, E. and Martinez, B. and Tzimiropoulos, G.",
TITLE = "ReGen: A good Generative zero-shot video classifier should be
Rewarded",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "13477-13487",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217038"}
@inproceedings{bb222048,
AUTHOR = "Shen, Y.J. and Gu, X. and Xu, K. and Fan, H. and Wen, L. and Zhang, L.",
TITLE = "Accurate and Fast Compressed Video Captioning",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15512-15521",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217039"}
@inproceedings{bb222049,
AUTHOR = "Lin, W. and Jin, T. and Wang, Y. and Pan, W.W. and Li, L.J. and Cheng, X. and Zhao, Z.",
TITLE = "Exploring Group Video Captioning with Efficient Relational
Approximation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15235-15244",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217040"}
@inproceedings{bb222050,
AUTHOR = "Damaceno, R.J.P. and Cesar, R.M.",
TITLE = "An End-to-end Deep Learning Approach for Video Captioning Through
Mobile Devices",
BOOKTITLE = CIARP23,
YEAR = "2023",
PAGES = "I:715-729",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217041"}
@inproceedings{bb222051,
AUTHOR = "Munusamy, H. and Sekhar, C.C.",
TITLE = "Multi-Modal Hierarchical Attention-Based Dense Video Captioning",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "475-479",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217042"}
@inproceedings{bb222052,
AUTHOR = "Chen, K.X. and Di, Q.J. and Lu, Y. and Wang, H.Z.",
TITLE = "Semantic Learning Network for Controllable Video Captioning",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "880-884",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217043"}
@inproceedings{bb222053,
AUTHOR = "Nadeem, A. and Hilton, A. and Dawes, R. and Thomas, G. and Mustafa, A.",
TITLE = "SEM-POS: Grammatically and Semantically Correct Video Captioning",
BOOKTITLE = MULA23,
YEAR = "2023",
PAGES = "2606-2616",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217044"}
@inproceedings{bb222054,
AUTHOR = "Ullah, N. and Mohanta, P.P.",
TITLE = "Thinking Hallucination for Video Captioning",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "IV:623-640",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217045"}
@inproceedings{bb222055,
AUTHOR = "Seo, P.H. and Nagrani, A. and Arnab, A. and Schmid, C.",
TITLE = "End-to-end Generative Pretraining for Multimodal Video Captioning",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "17938-17947",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217046"}
@inproceedings{bb222056,
AUTHOR = "Lin, K. and Li, L.J. and Lin, C.C. and Ahmed, F. and Gan, Z. and Liu, Z.C. and Lu, Y. and Wang, L.J.",
TITLE = "SwinBERT: End-to-End Transformers with Sparse Attention for Video
Captioning",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "17928-17937",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217047"}
@inproceedings{bb222057,
AUTHOR = "Shi, Y. and Yang, X. and Xu, H.Y. and Yuan, C.F. and Li, B. and Hu, W.M. and Zha, Z.J.",
TITLE = "EMScore: Evaluating Video Captioning via Coarse-Grained and
Fine-Grained Embedding Matching",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "17908-17917",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217048"}
@inproceedings{bb222058,
AUTHOR = "Chen, S.X. and Jiang, Y.G.",
TITLE = "Motion Guided Region Message Passing for Video Captioning",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "1523-1532",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217049"}
@inproceedings{bb222059,
AUTHOR = "Joshi, P. and Saharia, C. and Singh, V. and Gautam, D. and Ramakrishnan, G. and Jyothi, P.",
TITLE = "A Tale of Two Modalities for Video Captioning",
BOOKTITLE = MMVAMTC19,
YEAR = "2019",
PAGES = "3708-3712",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217050"}
@inproceedings{bb222060,
AUTHOR = "Wang, T. and Zhang, R.M. and Lu, Z.C. and Zheng, F. and Cheng, R. and Luo, P.",
TITLE = "End-to-End Dense Video Captioning with Parallel Decoding",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "6827-6837",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217051"}
@inproceedings{bb222061,
AUTHOR = "Yang, B. and Zou, Y.X.",
TITLE = "Visual Oriented Encoder: Integrating Multimodal and Multi-Scale
Contexts for Video Captioning",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "188-195",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217052"}
@inproceedings{bb222062,
AUTHOR = "Perez Martin, J. and Bustos, B. and Perez, J.",
TITLE = "Attentive Visual Semantic Specialized Network for Video Captioning",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "5767-5774",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217053"}
@inproceedings{bb222063,
AUTHOR = "Olivastri, S. and Singh, G. and Cuzzolin, F.",
TITLE = "End-to-End Video Captioning",
BOOKTITLE = HVU19,
YEAR = "2019",
PAGES = "1474-1482",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217054"}
@inproceedings{bb222064,
AUTHOR = "Li, L. and Gong, B.",
TITLE = "End-to-End Video Captioning With Multitask Reinforcement Learning",
BOOKTITLE = WACV19,
YEAR = "2019",
PAGES = "339-348",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217055"}
@inproceedings{bb222065,
AUTHOR = "Wang, B. and Ma, L. and Zhang, W. and Liu, W.",
TITLE = "Reconstruction Network for Video Captioning",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7622-7631",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217056"}
@inproceedings{bb222066,
AUTHOR = "Li, Y. and Yao, T. and Pan, Y. and Chao, H. and Mei, T.",
TITLE = "Jointly Localizing and Describing Events for Dense Video Captioning",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "7492-7500",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217057"}
@inproceedings{bb222067,
AUTHOR = "Wu, X. and Li, G. and Cao, Q. and Ji, Q. and Lin, L.",
TITLE = "Interpretable Video Captioning via Trajectory Structured Localization",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "6829-6837",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217058"}
@inproceedings{bb222068,
AUTHOR = "Wang, X. and Chen, W. and Wu, J. and Wang, Y. and Wang, W.Y.",
TITLE = "Video Captioning via Hierarchical Reinforcement Learning",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "4213-4222",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217059"}
@inproceedings{bb222069,
AUTHOR = "Zhou, L. and Zhou, Y. and Corso, J.J. and Socher, R. and Xiong, C.",
TITLE = "End-to-End Dense Video Captioning with Masked Transformer",
BOOKTITLE = CVPR18,
YEAR = "2018",
PAGES = "8739-8748",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217060"}
@inproceedings{bb222070,
AUTHOR = "Yang, D. and Yuan, C.",
TITLE = "Hierarchical Context Encoding for Events Captioning in Videos",
BOOKTITLE = ICIP18,
YEAR = "2018",
PAGES = "1288-1292",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217061"}
@inproceedings{bb222071,
AUTHOR = "Shen, Z.Q. and Li, J.G. and Su, Z. and Li, M.J. and Chen, Y.R. and Jiang, Y.G. and Xue, X.Y.",
TITLE = "Weakly Supervised Dense Video Captioning",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "5159-5167",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217062"}
@inproceedings{bb222072,
AUTHOR = "Baraldi, L. and Grana, C. and Cucchiara, R.",
TITLE = "Hierarchical Boundary-Aware Neural Encoder for Video Captioning",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "3185-3194",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217063"}
@inproceedings{bb222073,
AUTHOR = "Pan, P.B. and Xu, Z.W. and Yang, Y. and Wu, F. and Zhuang, Y.T.",
TITLE = "Hierarchical Recurrent Neural Encoder for Video Representation with
Application to Captioning",
BOOKTITLE = CVPR16,
YEAR = "2016",
PAGES = "1029-1038",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217064"}
@inproceedings{bb222074,
AUTHOR = "Yu, H.N. and Wang, J. and Huang, Z.H. and Yang, Y. and Xu, W.",
TITLE = "Video Paragraph Captioning Using Hierarchical Recurrent Neural
Networks",
BOOKTITLE = CVPR16,
YEAR = "2016",
PAGES = "4584-4593",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217065"}
@inproceedings{bb222075,
AUTHOR = "Shin, A. and Ohnishi, K. and Harada, T.",
TITLE = "Beyond caption to narrative: Video captioning with multiple sentences",
BOOKTITLE = ICIP16,
YEAR = "2016",
PAGES = "3364-3368",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT217066"}
@article{bb222076,
AUTHOR = "Vakali, A. and Hacid, M.S. and Elmagarmid, A.",
TITLE = "MPEG-7 based description schemes for multi-level video content
classification",
JOURNAL = IVC,
VOLUME = "22",
YEAR = "2004",
NUMBER = "5",
MONTH = "May",
PAGES = "367-378",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217067"}
@article{bb222077,
AUTHOR = "Fonseca, P.M. and Pereira, F.",
TITLE = "Automatic video summarization based on MPEG-7 descriptions",
JOURNAL = SP:IC,
VOLUME = "19",
YEAR = "2004",
NUMBER = "8",
MONTH = "September",
PAGES = "685-699",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217068"}
@article{bb222078,
AUTHOR = "Mrak, M. and Calic, J. and Kondoz, A.M.",
TITLE = "Fast analysis of scalable video for adaptive browsing interfaces",
JOURNAL = CVIU,
VOLUME = "113",
YEAR = "2009",
NUMBER = "3",
MONTH = "March",
PAGES = "425-434",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217069"}
@inproceedings{bb222079,
AUTHOR = "Calic, J. and Mrak, M. and Kondoz, A.M.",
TITLE = "Flexible generation of video summaries from layered video bit-streams",
BOOKTITLE = ICIP08,
YEAR = "2008",
PAGES = "2516-2519",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217070"}
@article{bb222080,
AUTHOR = "Herranz, L. and Martinez, J.M.",
TITLE = "An integrated approach to summarization and adaptation using
H.264/MPEG-4 SVC",
JOURNAL = SP:IC,
VOLUME = "24",
YEAR = "2009",
NUMBER = "6",
MONTH = "July",
PAGES = "499-509",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217071"}
@article{bb222081,
AUTHOR = "Herranz, L. and Martinez, J.M.",
TITLE = "On the use of hierarchical prediction structures for efficient summary
generation of H.264/AVC bitstreams",
JOURNAL = SP:IC,
VOLUME = "24",
YEAR = "2009",
NUMBER = "8",
MONTH = "September",
PAGES = "615-629",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217072"}
@article{bb222082,
AUTHOR = "Matos, N. and Pereira, F.",
TITLE = "Automatic creation and evaluation of MPEG-7 compliant summary
descriptions for generic audiovisual content",
JOURNAL = SP:IC,
VOLUME = "23",
YEAR = "2008",
NUMBER = "8",
MONTH = "September",
PAGES = "581-598",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217073"}
@article{bb222083,
AUTHOR = "Ren, J.C. and Jiang, J.M. and Feng, Y.",
TITLE = "Activity-driven content adaptation for effective video summarization",
JOURNAL = JVCIR,
VOLUME = "21",
YEAR = "2010",
NUMBER = "8",
MONTH = "November",
PAGES = "930-938",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217074"}
@article{bb222084,
AUTHOR = "Almeida, J. and Leite, N.J. and da Silva Torres, R.",
TITLE = "VISON: VIdeo Summarization for ONline applications",
JOURNAL = PRL,
VOLUME = "33",
YEAR = "2012",
NUMBER = "4",
MONTH = "March",
PAGES = "397-409",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217075"}
@inproceedings{bb222085,
AUTHOR = "Almeida, J. and Leite, N.J. and da Silva Torres, R.",
TITLE = "Comparison of video sequences with histograms of motion patterns",
BOOKTITLE = ICIP11,
YEAR = "2011",
PAGES = "3673-3676",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217076"}
@inproceedings{bb222086,
AUTHOR = "Almeida, J. and Leite, N.J. and da Silva Torres, R.",
TITLE = "Rapid Cut Detection on Compressed Video",
BOOKTITLE = CIARP11,
YEAR = "2011",
PAGES = "71-78",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217077"}
@article{bb222087,
AUTHOR = "Basavarajaiah, M. and Sharma, P.",
TITLE = "Survey of Compressed Domain Video Summarization Techniques",
JOURNAL = Surveys,
VOLUME = "52",
YEAR = "2019",
NUMBER = "6",
MONTH = "October",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217078"}
@inproceedings{bb222088,
AUTHOR = "Lee, J.H. and Kim, W.Y.",
TITLE = "Video Summarization and Retrieval System Using Face Recognition and
MPEG-7 Descriptors",
BOOKTITLE = CIVR04,
YEAR = "2004",
PAGES = "170-178",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217079"}
@inproceedings{bb222089,
AUTHOR = "Soysal, M. and Alatan, A.A.",
TITLE = "Combining MPEG-7 Based Visual Experts for Reaching Semantics",
BOOKTITLE = VLBV03,
YEAR = "2003",
PAGES = "66-75",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217080"}
@inproceedings{bb222090,
AUTHOR = "Divakaran, A. and Peker, K.A. and Radhakrishnan, R. and Xiong, Z.Y. and Cabasson, R.",
TITLE = "Video Summarization using MPEG-7 Motion Activity and Audio Descriptors",
BOOKTITLE = VideoMining03,
YEAR = "2003",
PAGES = "Chapter 4",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217081"}
@inproceedings{bb222091,
AUTHOR = "Sugano, M. and Nakajima, Y. and Yanagihara, H.",
TITLE = "Automated MPEG audio-video summarization and description",
BOOKTITLE = ICIP02,
YEAR = "2002",
PAGES = "I: 956-959",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217082"}
@inproceedings{bb222092,
AUTHOR = "Jaimes, A. and Echigo, T. and Teraguchi, M. and Satoh, F.",
TITLE = "Learning personalized video highlights from detailed MPEG-7 metadata",
BOOKTITLE = ICIP02,
YEAR = "2002",
PAGES = "I: 133-136",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217083"}
@inproceedings{bb222093,
AUTHOR = "Lin, C.Y. and Tseng, B.L. and Naphade, M.R. and Natsev, A.P. and Smith, J.R.",
TITLE = "VideoAL: A novel end-to-end MPEG-7 video automatic labeling system",
BOOKTITLE = ICIP03,
YEAR = "2003",
PAGES = "III: 53-56",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217084"}
@inproceedings{bb222094,
AUTHOR = "Kim, J.G. and Chang, H.S. and Kim, J.W. and Kim, H.M.",
TITLE = "Efficient Camera Motion Characterization for MPEG Video Indexing",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP11",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217085"}
@inproceedings{bb222095,
AUTHOR = "DeMenthon, D.F. and Megret, R.",
TITLE = "Spatio-temporal Segmentation of Video by
Hierarchical Mean Shift Analysis",
BOOKTITLE = UMD,
YEAR = "2002",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217086"}
@inproceedings{bb222096,
AUTHOR = "Megret, R. and DeMenthon, D.F.",
TITLE = "A Survey of Spatio-temporal Grouping Techniques",
BOOKTITLE = UMD,
YEAR = "2002",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217087"}
@inproceedings{bb222097,
AUTHOR = "DeMenthon, D.F. and Latecki, L.J. and Rosenfeld, A. and Stueckelberg, M.V.",
TITLE = "Relevance Ranking of Video Data using
Hidden Markov Model Distances and Polygon Simplification",
BOOKTITLE = UMD,
YEAR = "2001",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217088"}
@inproceedings{bb222098,
AUTHOR = "DeMenthon, D.F. and Kobla, V. and Doermann, D.",
TITLE = "Video Summarization by Curve Simplification",
BOOKTITLE = UMD,
YEAR = "1998",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217089"}
@inproceedings{bb222099,
AUTHOR = "Yoon, K. and DeMenthon, D.F. and Doermann, D.",
TITLE = "Event Detection from MPEG Video in the Compressed Domain",
BOOKTITLE = ICPR00,
YEAR = "2000",
PAGES = "Vol I: 819-822",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vm3.html#TT217090"}
Last update:Jul 18, 2024 at 20:50:34