@inproceedings{bb219200,
AUTHOR = "Yan, R. and Naphade, M.R.",
TITLE = "Semi-Supervised Cross Feature Learning for Semantic Concept Detection
in Videos",
BOOKTITLE = CVPR05,
YEAR = "2005",
PAGES = "I: 657-663",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214206"}
@inproceedings{bb219201,
AUTHOR = "Tang, Q. and Lim, J.H. and Jin, J.S. and Sun, H.P. and Tian, Q.",
TITLE = "A generic mid-level representation for semantic video analysis",
BOOKTITLE = ICIP04,
YEAR = "2004",
PAGES = "I: 629-632",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214207"}
@inproceedings{bb219202,
AUTHOR = "Wan, Y.H. and Ji, S.M. and Xie, Y. and Zhang, X. and Xie, P.J.",
TITLE = "Video Program Clustering Indexing Based on Face Recognition Hybrid
Model of Hidden Markov Model and Support Vector Machine",
BOOKTITLE = IWCIA04,
YEAR = "2004",
PAGES = "739-749",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214208"}
@inproceedings{bb219203,
AUTHOR = "de Jong, F.",
TITLE = "Disclosure of Non-scripted Video Content: InDiCo and M4/AMI",
BOOKTITLE = CIVR04,
YEAR = "2004",
PAGES = "647-655",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214209"}
@inproceedings{bb219204,
AUTHOR = "Xie, Y.X. and Luan, X.D. and Lao, S.Y. and Wu, L.D. and Xiao, P. and Wen, J.",
TITLE = "EDU: A Model of Video Summarization",
BOOKTITLE = CIVR04,
YEAR = "2004",
PAGES = "106-114",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214210"}
@inproceedings{bb219205,
AUTHOR = "Cheatle, P.",
TITLE = "Media content and type selection from always-on wearable video",
BOOKTITLE = ICPR04,
YEAR = "2004",
PAGES = "IV: 979-982",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214211"}
@inproceedings{bb219206,
AUTHOR = "Wang, Y.G. and Cheng, Q.A. and Cheng, J. and Huang, T.S.",
TITLE = "MV-MAP: Multiresolution Video Visualization and Summarization on MAPs",
BOOKTITLE = ICPR04,
YEAR = "2004",
PAGES = "III: 886-889",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214212"}
@inproceedings{bb219207,
AUTHOR = "Dorai, C. and Oria, V. and Neelavalli, V.",
TITLE = "Structuralizing educational videos based on presentation content",
BOOKTITLE = ICIP03,
YEAR = "2003",
PAGES = "II: 1029-1032",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214213"}
@inproceedings{bb219208,
AUTHOR = "Lee, S.K. and Hayes, M.H.",
TITLE = "A fast clustering algorithm for video abstraction",
BOOKTITLE = ICIP03,
YEAR = "2003",
PAGES = "II: 563-566",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214214"}
@inproceedings{bb219209,
AUTHOR = "Yasaroglu, Y. and Alatan, A.A.",
TITLE = "Summarizing Video: Content, Features, and HMM Topologies",
BOOKTITLE = VLBV03,
YEAR = "2003",
PAGES = "101-110",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214215"}
@inproceedings{bb219210,
AUTHOR = "Porter, S.V. and Mirmehdi, M. and Thomas, B.T.",
TITLE = "Video Indexing using Motion Estimation",
BOOKTITLE = BMVC03,
YEAR = "2003",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214216"}
@inproceedings{bb219211,
AUTHOR = "Porter, S.V. and Mirmehdi, M. and Thomas, B.T.",
TITLE = "A shortest path representation for video summarisation",
BOOKTITLE = CIAP03,
YEAR = "2003",
PAGES = "460-465",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214217"}
@inproceedings{bb219212,
AUTHOR = "Dimitrova, N. and Agnihotri, L. and Jasinschi, R.S.",
TITLE = "Temporal Video Boundaries",
BOOKTITLE = VideoMining03,
YEAR = "2003",
PAGES = "Chapter 3",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214218"}
@inproceedings{bb219213,
AUTHOR = "Bagga, A. and Hu, J.Y. and Zhong, J.L. and Ramesh, G.",
TITLE = "Multi-source combined-media video tracking for summarization",
BOOKTITLE = ICPR02,
YEAR = "2002",
PAGES = "II: 818-821",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214219"}
@inproceedings{bb219214,
AUTHOR = "Gibson, D.P. and Campbell, N.W. and Thomas, B.T.",
TITLE = "Visual abstraction of wildlife footage using gaussian mixture models
and the minimum description length criterion",
BOOKTITLE = ICPR02,
YEAR = "2002",
PAGES = "II: 814-817",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214220"}
@inproceedings{bb219215,
AUTHOR = "Gibson, D.P. and Campbell, N.W. and Thomas, B.T.",
TITLE = "Visual Abstraction of Wildlife Footage using Gaussian Mixture Models",
BOOKTITLE = VI02,
YEAR = "2002",
PAGES = "23",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214221"}
@inproceedings{bb219216,
AUTHOR = "Sanchez, J.M. and Binefa, X. and Kender, J.R.",
TITLE = "Coupled markov chains for video contents characterization",
BOOKTITLE = ICPR02,
YEAR = "2002",
PAGES = "II: 461-464",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214222"}
@inproceedings{bb219217,
AUTHOR = "Orriols, X. and Binefa, X.",
TITLE = "Online Bayesian Video Summarization and Linking",
BOOKTITLE = CIVR02,
YEAR = "2002",
PAGES = "338-347",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214223"}
@inproceedings{bb219218,
AUTHOR = "Orriols, X. and Binefa, X.",
TITLE = "An EM Algorithm for Video Summarization, Generative Model Approach",
BOOKTITLE = ICCV01,
YEAR = "2001",
PAGES = "II: 335-342",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214224"}
@inproceedings{bb219219,
AUTHOR = "Martin Granel, P. and Roach, M.J. and Mason, J.D.",
TITLE = "Camera Motion Extraction Using Correlation for Motion-Based Video
Classification",
BOOKTITLE = VF01,
YEAR = "2001",
PAGES = "552 ff.",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214225"}
@inproceedings{bb219220,
AUTHOR = "Spierenburg, J.A. and Huijsmans, D.P.",
TITLE = "VOICI: Video Overview for Image Cluster Indexing: A swift browsing
tool for a large digital image database using similarities",
BOOKTITLE = BMVC97,
YEAR = "1997",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214226"}
@inproceedings{bb219221,
AUTHOR = "Vermaak, J. and Perez, P. and Blake, A. and Gangnet, M.",
TITLE = "Rapid Summarisation and Browsing of Video Sequences",
BOOKTITLE = BMVC02,
YEAR = "2002",
PAGES = "3D and Video",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214227"}
@inproceedings{bb219222,
AUTHOR = "Piirainen, T. and Silven, O. and Tuulos, V.",
TITLE = "Layered Self-organizing Maps based Video Content Classification",
BOOKTITLE = SCIA01,
YEAR = "2001",
PAGES = "O-M4A",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214228"}
@inproceedings{bb219223,
AUTHOR = "Ng, J. and Gong, S.",
TITLE = "Learning Intrinsic Video Content Using Levenshtein Distance in Graph
Partitioning",
BOOKTITLE = ECCV02,
YEAR = "2002",
PAGES = "IV: 670 ff.",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214229"}
@inproceedings{bb219224,
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/applicat824.html#TT214230"}
@inproceedings{bb219225,
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/applicat824.html#TT214231"}
@inproceedings{bb219226,
AUTHOR = "Hamada, R. and Satoh, S. and Sakai, S.",
TITLE = "Detection of Important Segments in Cooking Videos",
BOOKTITLE = CBAIVL01,
YEAR = "2001",
PAGES = "118",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214232"}
@inproceedings{bb219227,
AUTHOR = "Aizawa, K. and Ishijima, K.I. and Shiina, M.",
TITLE = "Summarizing Wearable Video",
BOOKTITLE = ICIP01,
YEAR = "2001",
PAGES = "III: 398-401",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214233"}
@inproceedings{bb219228,
AUTHOR = "Gong, Y. and Liu, X.",
TITLE = "Video Summarization with Minimal Visual Content Redundancies",
BOOKTITLE = ICIP01,
YEAR = "2001",
PAGES = "III: 362-365",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214234"}
@inproceedings{bb219229,
AUTHOR = "Martel, L.",
TITLE = "New Rule-based Framework for Post-processing Merging in Video Sequence
Segmentation",
BOOKTITLE = ICIP00,
YEAR = "2000",
PAGES = "Vol I: 327-330",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214235"}
@inproceedings{bb219230,
AUTHOR = "Wang, R.R. and Hong, P.Y. and Huang, T.S.",
TITLE = "Memory-based Moving Object Extraction for Video Indexing",
BOOKTITLE = ICPR00,
YEAR = "2000",
PAGES = "Vol I: 811-814",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214236"}
@inproceedings{bb219231,
AUTHOR = "Oh, J.H. and Hua, K.A.",
TITLE = "An Efficient Technique for Summarizing Videos using Visual Contents",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "TP11",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214237"}
@inproceedings{bb219232,
AUTHOR = "Kurokawa, M. and Echigo, T.",
TITLE = "Video contents access method that uses trajectories of objects
and apparatus therefor",
BOOKTITLE = US_Patent,
YEAR = "2004",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214238"}
@inproceedings{bb219233,
AUTHOR = "Echigo, T. and Kurokawa, M. and Maeda, J. and Tomita, A.",
TITLE = "Method and device for describing video contents",
BOOKTITLE = US_Patent,
YEAR = "2007",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214239"}
@inproceedings{bb219234,
AUTHOR = "Masumitsu, K. and Echigo, T.",
TITLE = "Video Summarization Using Reinforcement Learning in Eigenspace",
BOOKTITLE = ICIP00,
YEAR = "2000",
PAGES = "Vol II: 267-270",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214240"}
@inproceedings{bb219235,
AUTHOR = "Martin, H. and Lozano, R.",
TITLE = "Dynamic Video Abstract Generation using an object DBMS",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "WP5",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214241"}
@inproceedings{bb219236,
AUTHOR = "Toklu, C. and Liou, S.P. and Das, M.",
TITLE = "Video Abstract: A Hybrid Approach to Generate Semantically Meaningful
Video Summaries",
BOOKTITLE = ICME00,
YEAR = "2000",
PAGES = "WA4",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214242"}
@inproceedings{bb219237,
AUTHOR = "Ferman, A.M. and Tekalp, A.M.",
TITLE = "A Unified Framework for Probabilistic Analysis and Extraction of Video
Content",
BOOKTITLE = ICIP99,
YEAR = "1999",
PAGES = "II:91-95",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat824.html#TT214243"}
@article{bb219238,
AUTHOR = "Qiu, Z.F. and Yao, T. and Mei, T.",
TITLE = "Learning Deep Spatio-Temporal Dependence for Semantic Video
Segmentation",
JOURNAL = MultMed,
VOLUME = "20",
YEAR = "2018",
NUMBER = "4",
MONTH = "April",
PAGES = "939-949",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214244"}
@inproceedings{bb219239,
AUTHOR = "Qiu, Z.F. and Yao, T. and Mei, T.",
TITLE = "Learning Spatio-Temporal Representation with Pseudo-3D Residual
Networks",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "5534-5542",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214245"}
@inproceedings{bb219240,
AUTHOR = "Qiu, Z.F. and Yao, T. and Ngo, C.W. and Tian, X.M. and Mei, T.",
TITLE = "Learning Spatio-Temporal Representation With Local and Global Diffusion",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "12048-12057",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214246"}
@inproceedings{bb219241,
AUTHOR = "Yao, T. and Pan, Y. and Li, Y. and Qiu, Z. and Mei, T.",
TITLE = "Boosting Image Captioning with Attributes",
BOOKTITLE = ICCV17,
YEAR = "2017",
PAGES = "4904-4912",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214247"}
@inproceedings{bb219242,
AUTHOR = "Pan, Y. and Yao, T. and Li, Y. and Mei, T.",
TITLE = "Video Captioning with Transferred Semantic Attributes",
BOOKTITLE = CVPR17,
YEAR = "2017",
PAGES = "984-992",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214248"}
@article{bb219243,
AUTHOR = "Zhao, B. and Li, X. and Lu, X.",
TITLE = "CAM-RNN: Co-Attention Model Based RNN for Video Captioning",
JOURNAL = IP,
VOLUME = "28",
YEAR = "2019",
NUMBER = "11",
MONTH = "November",
PAGES = "5552-5565",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214249"}
@article{bb219244,
AUTHOR = "Yan, C. and Tu, Y. and Wang, X. and Zhang, Y. and Hao, X. and Zhang, Y. and Dai, Q.",
TITLE = "STAT: Spatial-Temporal Attention Mechanism for Video Captioning",
JOURNAL = MultMed,
VOLUME = "22",
YEAR = "2020",
NUMBER = "1",
MONTH = "January",
PAGES = "229-241",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214250"}
@article{bb219245,
AUTHOR = "Dai, Q. and Zhang, Y. and Hao, X. and Zhang, Y. and Wang, X. and Tu, Y. and Yan, C.",
TITLE = "STAT: Spatial-Temporal Attention Mechanism for Video Captioning",
JOURNAL = MultMed,
VOLUME = "22",
YEAR = "2020",
NUMBER = "3",
MONTH = "March",
PAGES = "830-830",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214250"}
@article{bb219246,
AUTHOR = "Aafaq, N. and Mian, A. and Liu, W. and Gilani, S.Z. and Shah, M.",
TITLE = "Video Description:
A Survey of Methods, Datasets, and Evaluation Metrics",
JOURNAL = Surveys,
VOLUME = "52",
YEAR = "2019",
NUMBER = "6",
MONTH = "October",
PAGES = "xx-yy",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214251"}
@article{bb219247,
AUTHOR = "Zhang, Z. and Xu, D. and Ouyang, W. and Tan, C.",
TITLE = "Show, Tell and Summarize: Dense Video Captioning Using Visual Cue
Aided Sentence Summarization",
JOURNAL = CirSysVideo,
VOLUME = "30",
YEAR = "2020",
NUMBER = "9",
MONTH = "September",
PAGES = "3130-3139",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214252"}
@article{bb219248,
AUTHOR = "Zhang, W. and Wang, B.R. and Ma, L. and Liu, W.",
TITLE = "Reconstruct and Represent Video Contents for Captioning via
Reinforcement Learning",
JOURNAL = PAMI,
VOLUME = "42",
YEAR = "2020",
NUMBER = "12",
MONTH = "December",
PAGES = "3088-3101",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214253"}
@article{bb219249,
AUTHOR = "Lee, S. and Kim, I.",
TITLE = "DVC-Net: A deep neural network model for dense video captioning",
JOURNAL = IET-CV,
VOLUME = "15",
YEAR = "2021",
NUMBER = "1",
PAGES = "12-23",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214254"}
@article{bb219250,
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#TT214255"}
@article{bb219251,
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#TT214256"}
@article{bb219252,
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#TT214257"}
@article{bb219253,
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#TT214258"}
@article{bb219254,
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#TT214259"}
@article{bb219255,
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#TT214260"}
@article{bb219256,
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#TT214261"}
@article{bb219257,
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#TT214262"}
@article{bb219258,
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#TT214263"}
@article{bb219259,
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#TT214264"}
@article{bb219260,
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#TT214265"}
@article{bb219261,
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#TT214266"}
@article{bb219262,
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#TT214267"}
@article{bb219263,
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#TT214268"}
@article{bb219264,
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#TT214269"}
@article{bb219265,
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#TT214270"}
@article{bb219266,
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#TT214271"}
@inproceedings{bb219267,
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#TT214272"}
@article{bb219268,
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#TT214273"}
@article{bb219269,
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#TT214274"}
@article{bb219270,
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#TT214275"}
@article{bb219271,
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#TT214276"}
@article{bb219272,
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#TT214277"}
@article{bb219273,
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#TT214278"}
@inproceedings{bb219274,
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#TT214279"}
@article{bb219275,
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#TT214280"}
@inproceedings{bb219276,
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#TT214281"}
@article{bb219277,
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#TT214282"}
@article{bb219278,
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#TT214283"}
@article{bb219279,
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#TT214284"}
@article{bb219280,
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#TT214285"}
@article{bb219281,
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#TT214286"}
@article{bb219282,
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#TT214287"}
@article{bb219283,
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#TT214288"}
@inproceedings{bb219284,
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#TT214289"}
@article{bb219285,
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#TT214290"}
@article{bb219286,
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#TT214291"}
@article{bb219287,
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#TT214292"}
@article{bb219288,
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#TT214293"}
@article{bb219289,
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#TT214294"}
@inproceedings{bb219290,
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#TT214295"}
@inproceedings{bb219291,
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#TT214296"}
@inproceedings{bb219292,
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#TT214297"}
@inproceedings{bb219293,
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#TT214298"}
@inproceedings{bb219294,
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#TT214299"}
@inproceedings{bb219295,
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#TT214300"}
@inproceedings{bb219296,
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#TT214301"}
@inproceedings{bb219297,
AUTHOR = "Munusamy, H. and C, C.S.",
TITLE = "Multi-Modal Hierarchical Attention-Based Dense Video Captioning",
BOOKTITLE = ICIP23,
YEAR = "2023",
PAGES = "475-479",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat825vc4.html#TT214302"}
@inproceedings{bb219298,
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#TT214303"}
@inproceedings{bb219299,
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#TT214304"}
Last update:Apr 18, 2024 at 11:38:49