@inproceedings{bb122400,
        AUTHOR = "Satoh, S. and Nakamura, Y. and Kanade, T.",
        TITLE = "Name-It: Naming and Detecting Faces in Video by the Integration 
of Image and Natural Language Processing",
        BOOKTITLE = IJCAI97,
        YEAR = "1997",
        PAGES = "1488-1495",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT118507"}

@inproceedings{bb122401,
        AUTHOR = "Satoh, S. and Kanade, T.",
        TITLE = "Name-It: Association Of Face And Name In Video",
        BOOKTITLE = CVPR97,
        YEAR = "1997",
        PAGES = "368-373",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT118508"}

@inproceedings{bb122402,
        AUTHOR = "Socher, G. and Sagerer, G.F. and Kummert, F. and Fuhr, T.",
        TITLE = "Talking About 3D Scenes: Integration of Image and Speech Understanding
in a Hybrid Distributed System",
        BOOKTITLE = ICIP96,
        YEAR = "1996",
        PAGES = "II: 809-812",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match605.html#TT118509"}

@article{bb122403,
        AUTHOR = "Kuniyoshi, Y. and Inaba, M. and Inoue, H.",
        TITLE = "Learning by Watching: Extracting Reusable Task Knowledge from
Visual Observation of Human Performance",
        JOURNAL = RA,
        VOLUME = "10",
        YEAR = "1994",
        PAGES = "799-822",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118510"}

@inproceedings{bb122404,
        AUTHOR = "Kuniyoshi, Y. and Inoue, H.",
        TITLE = "Indexicality and dynamic attention control in qualitative recognition
of assembly actions",
        BOOKTITLE = ECCV92,
        YEAR = "1992",
        PAGES = "874-878",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118511"}

@article{bb122405,
        AUTHOR = "Porway, J. and Wang, Q.C. and Zhu, S.C.",
        TITLE = "A Hierarchical and Contextual Model for Aerial Image Parsing",
        JOURNAL = IJCV,
        VOLUME = "88",
        YEAR = "2010",
        NUMBER = "2",
        MONTH = "June",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118512"}

@inproceedings{bb122406,
        AUTHOR = "Porway, J. and Wang, K. and Yao, B. and Zhu, S.C.",
        TITLE = "A hierarchical and contextual model for aerial image understanding",
        BOOKTITLE = CVPR08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118513"}

@inproceedings{bb122407,
        AUTHOR = "Si, Z.Z. and Gong, H.F. and Wu, Y.N. and Zhu, S.C.",
        TITLE = "Learning mixed templates for object recognition",
        BOOKTITLE = CVPR09,
        YEAR = "2009",
        PAGES = "272-279",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118514"}

@article{bb122408,
        AUTHOR = "Tu, Z.W. and Bai, X.",
        TITLE = "Auto-Context and Its Application to High-Level Vision Tasks and 3D
Brain Image Segmentation",
        JOURNAL = PAMI,
        VOLUME = "32",
        YEAR = "2010",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "1744-1757",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118515"}

@inproceedings{bb122409,
        AUTHOR = "Tu, Z.W.",
        TITLE = "Auto-context and its application to high-level vision tasks",
        BOOKTITLE = CVPR08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118516"}

@inproceedings{bb122410,
        AUTHOR = "Jones, J. and Hager, G.D. and Khudanpur, S.",
        TITLE = "Toward Computer Vision Systems That Understand Real-World Assembly
Processes",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "426-434",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118517"}

@inproceedings{bb122411,
        AUTHOR = "Lampert, C.H.",
        TITLE = "Partitioning of image datasets using discriminative context information",
        BOOKTITLE = CVPR08,
        YEAR = "2008",
        PAGES = "1-8",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118518"}

@inproceedings{bb122412,
        AUTHOR = "Hansen, C. and Henderson, T.C.",
        TITLE = "Towards the Automatic Generation of Recognition Strategies",
        BOOKTITLE = ICCV88,
        YEAR = "1988",
        PAGES = "275-279",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118519"}

@inproceedings{bb122413,
        AUTHOR = "Cantoni, V. and Cei, U. and Ferretti, M. and Lombardi, L.",
        TITLE = "Towards an Automatic Construction of Object Recognition Strategies",
        BOOKTITLE = ICPR88,
        YEAR = "1988",
        PAGES = "I: 371-374",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118520"}

@inproceedings{bb122414,
        AUTHOR = "Cova, G. and Griffini, A. and Lombardi, L.",
        TITLE = "Object Recognition Strategy in a Multi-Resolution System",
        BOOKTITLE = CIAP89,
        YEAR = "1989",
        PAGES = "729-733",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match606.html#TT118521"}

@article{bb122415,
        AUTHOR = "Feng, Y.S. and Lapata, M.",
        TITLE = "Automatic Caption Generation for News Images",
        JOURNAL = PAMI,
        VOLUME = "35",
        YEAR = "2013",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "797-812",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118522"}

@article{bb122416,
        AUTHOR = "Vinyals, O. and Toshev, A. and Bengio, S. and Erhan, D.",
        TITLE = "Show and Tell: Lessons Learned from the 2015 MSCOCO Image Captioning
Challenge",
        JOURNAL = PAMI,
        VOLUME = "39",
        YEAR = "2017",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "652-663",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118523"}

@inproceedings{bb122417,
        AUTHOR = "Vinyals, O. and Toshev, A. and Bengio, S. and Erhan, D.",
        TITLE = "Show and tell: A neural image caption generator",
        BOOKTITLE = CVPR15,
        YEAR = "2015",
        PAGES = "3156-3164",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118524"}

@article{bb122418,
        AUTHOR = "Wang, J.Y. and Zhu, X.T. and Gong, S.G.",
        TITLE = "Discovering visual concept structure with sparse and incomplete tags",
        JOURNAL = AI,
        VOLUME = "250",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "16-36",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118525"}

@article{bb122419,
        AUTHOR = "Kilickaya, M. and Akkus, B.K. and Cakici, R. and Erdem, A. and Erdem, E. and Ikizler Cinbis, N.",
        TITLE = "Data-driven image captioning via salient region discovery",
        JOURNAL = IET-CV,
        VOLUME = "11",
        YEAR = "2017",
        NUMBER = "6",
        MONTH = "September",
        PAGES = "398-406",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118526"}

@article{bb122420,
        AUTHOR = "He, X.D. and Deng, L.",
        TITLE = "Deep Learning for Image-to-Text Generation: A Technical Overview",
        JOURNAL = SPMag,
        VOLUME = "34",
        YEAR = "2017",
        NUMBER = "6",
        MONTH = "November",
        PAGES = "109-116",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118527"}

@article{bb122421,
        AUTHOR = "Deng, L. and He, X.D.",
        TITLE = "Deep Learning for Image-to-Text Generation: A Technical Overview",
        JOURNAL = SPMag,
        VOLUME = "35",
        YEAR = "2018",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "178",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118527"}

@article{bb122422,
        AUTHOR = "Li, L.H. and Tang, S. and Zhang, Y.D. and Deng, L.X. and Tian, Q.",
        TITLE = "GLA: Global-Local Attention for Image Description",
        JOURNAL = MultMed,
        VOLUME = "20",
        YEAR = "2018",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "726-737",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118528"}

@article{bb122423,
        AUTHOR = "Lu, X. and Wang, B. and Zheng, X. and Li, X.",
        TITLE = "Exploring Models and Data for Remote Sensing Image Caption Generation",
        JOURNAL = GeoRS,
        VOLUME = "56",
        YEAR = "2018",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "2183-2195",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118529"}

@article{bb122424,
        AUTHOR = "Wu, C.L. and Wei, Y.W. and Chu, X.L. and Su, F. and Wang, L.Q.",
        TITLE = "Modeling visual and word-conditional semantic attention for image
captioning",
        JOURNAL = SP:IC,
        VOLUME = "67",
        YEAR = "2018",
        PAGES = "100-107",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118530"}

@article{bb122425,
        AUTHOR = "Zhang, M. and Yang, Y. and Zhang, H. and Ji, Y. and Shen, H.T. and Chua, T.",
        TITLE = "More is Better: Precise and Detailed Image Captioning Using Online
Positive Recall and Missing Concepts Mining",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "32-44",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118531"}

@article{bb122426,
        AUTHOR = "Gella, S. and Keller, F. and Lapata, M.",
        TITLE = "Disambiguating Visual Verbs",
        JOURNAL = PAMI,
        VOLUME = "41",
        YEAR = "2019",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "311-322",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118532"}

@article{bb122427,
        AUTHOR = "Xu, N. and Liu, A.A. and Liu, J. and Nie, W.Z. and Su, Y.T.",
        TITLE = "Scene graph captioner:
Image captioning based on structural visual representation",
        JOURNAL = JVCIR,
        VOLUME = "58",
        YEAR = "2019",
        PAGES = "477-485",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118533"}

@article{bb122428,
        AUTHOR = "He, X.W. and Shi, B.G. and Bai, X. and Xia, G.S. and Zhang, Z.X. and Dong, W.S.",
        TITLE = "Image Caption Generation with Part of Speech Guidance",
        JOURNAL = PRL,
        VOLUME = "119",
        YEAR = "2019",
        PAGES = "229-237",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118534"}

@article{bb122429,
        AUTHOR = "Xiao, X.Y. and Wang, L.F. and Ding, K. and Xiang, S.M. and Pan, C.",
        TITLE = "Dense semantic embedding network for image captioning",
        JOURNAL = PR,
        VOLUME = "90",
        YEAR = "2019",
        PAGES = "285-296",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118535"}

@article{bb122430,
        AUTHOR = "Zhang, X.R. and Wang, X. and Tang, X. and Zhou, H.Y. and Li, C.",
        TITLE = "Description Generation for Remote Sensing Images Using Attribute
Attention Mechanism",
        JOURNAL = RS,
        VOLUME = "11",
        YEAR = "2019",
        NUMBER = "6",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118536"}

@article{bb122431,
        AUTHOR = "Ding, S.T. and Qu, S. and Xi, Y.L. and Sangaiah, A.K. and Wan, S.H.",
        TITLE = "Image caption generation with high-level image features",
        JOURNAL = PRL,
        VOLUME = "123",
        YEAR = "2019",
        PAGES = "89-95",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118537"}

@article{bb122432,
        AUTHOR = "Liu, X.X. and Xu, Q.Y. and Wang, N.",
        TITLE = "A survey on deep neural network-based image captioning",
        JOURNAL = VC,
        VOLUME = "35",
        YEAR = "2019",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "445-470",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118538"}

@article{bb122433,
        AUTHOR = "Hossain, M.Z. and Sohel, F. and Shiratuddin, M.F. and Laga, H.",
        TITLE = "A Comprehensive Survey of Deep Learning for Image Captioning",
        JOURNAL = Surveys,
        VOLUME = "51",
        YEAR = "2019",
        NUMBER = "6",
        MONTH = "February",
        PAGES = "Article No 118",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118539"}

@article{bb122434,
        AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.",
        TITLE = "High-Quality Image Captioning With Fine-Grained and Semantic-Guided
Visual Attention",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1681-1693",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118540"}

@inproceedings{bb122435,
        AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.",
        TITLE = "Fine-Grained and Semantic-Guided Visual Attention for Image
Captioning",
        BOOKTITLE = WACV18,
        YEAR = "2018",
        PAGES = "1709-1717",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118541"}

@article{bb122436,
        AUTHOR = "Li, X. and Jiang, S.",
        TITLE = "Know More Say Less: Image Captioning Based on Scene Graphs",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "2117-2130",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118542"}

@article{bb122437,
        AUTHOR = "Sharif, N. and White, L. and Bennamoun, M. and Liu, W. and Shah, S.A.A.",
        TITLE = "LCEval: Learned Composite Metric for Caption Evaluation",
        JOURNAL = IJCV,
        VOLUME = "127",
        YEAR = "2019",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "1586-1610",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118543"}

@article{bb122438,
        AUTHOR = "Zhang, Z.Y. and Diao, W.H. and Zhang, W.K. and Yan, M.L. and Gao, X. and Sun, X.",
        TITLE = "LAM: Remote Sensing Image Captioning with Label-Attention Mechanism",
        JOURNAL = RS,
        VOLUME = "11",
        YEAR = "2019",
        NUMBER = "20",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118544"}

@article{bb122439,
        AUTHOR = "Fu, K. and Li, Y. and Zhang, W.K. and Yu, H.F. and Sun, X.",
        TITLE = "Boosting Memory with a Persistent Memory Mechanism for Remote Sensing
Image Captioning",
        JOURNAL = RS,
        VOLUME = "12",
        YEAR = "2020",
        NUMBER = "11",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118545"}

@article{bb122440,
        AUTHOR = "Tan, J.H. and Chan, C.S. and Chuah, J.H.",
        TITLE = "COMIC: Toward A Compact Image Captioning Model With Attention",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "2686-2696",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118546"}

@article{bb122441,
        AUTHOR = "Zhou, L. and Zhang, Y. and Jiang, Y. and Zhang, T. and Fan, W.",
        TITLE = "Re-Caption: Saliency-Enhanced Image Captioning Through Two-Phase
Learning",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        NUMBER = "1",
        PAGES = "694-709",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118547"}

@article{bb122442,
        AUTHOR = "Yang, L. and Hu, H.F.",
        TITLE = "Visual Skeleton and Reparative Attention for Part-of-Speech image
captioning system",
        JOURNAL = CVIU,
        VOLUME = "189",
        YEAR = "2019",
        PAGES = "102819",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118548"}

@article{bb122443,
        AUTHOR = "Wang, J.B. and Wang, W. and Wang, L. and Wang, Z.Y. and Feng, D.D. and Tan, T.N.",
        TITLE = "Learning Visual Relationship and Context-Aware Attention for Image
Captioning",
        JOURNAL = PR,
        VOLUME = "98",
        YEAR = "2020",
        PAGES = "107075",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118549"}

@article{bb122444,
        AUTHOR = "Xiao, X. and Wang, L. and Ding, K. and Xiang, S. and Pan, C.",
        TITLE = "Deep Hierarchical Encoder-Decoder Network for Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "2942-2956",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118550"}

@article{bb122445,
        AUTHOR = "Jiang, T. and Zhang, Z. and Yang, Y.",
        TITLE = "Modeling coverage with semantic embedding for image caption generation",
        JOURNAL = VC,
        VOLUME = "35",
        YEAR = "2018",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "1655-1665",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118551"}

@article{bb122446,
        AUTHOR = "Lu, X. and Wang, B. and Zheng, X.",
        TITLE = "Sound Active Attention Framework for Remote Sensing Image Captioning",
        JOURNAL = GeoRS,
        VOLUME = "58",
        YEAR = "2020",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "1985-2000",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118552"}

@article{bb122447,
        AUTHOR = "Li, Y.Y. and Fang, S.K. and Jiao, L.C. and Liu, R.J. and Shang, R.H.",
        TITLE = "A Multi-Level Attention Model for Remote Sensing Image Captions",
        JOURNAL = RS,
        VOLUME = "12",
        YEAR = "2020",
        NUMBER = "6",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118553"}

@article{bb122448,
        AUTHOR = "Chen, X.H. and Zhang, M.X. and Wang, Z. and Zuo, L. and Li, B. and Yang, Y.",
        TITLE = "Leveraging unpaired out-of-domain data for image captioning",
        JOURNAL = PRL,
        VOLUME = "132",
        YEAR = "2020",
        PAGES = "132-140",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118554"}

@article{bb122449,
        AUTHOR = "Xu, N. and Zhang, H. and Liu, A. and Nie, W. and Su, Y. and Nie, J. and Zhang, Y.",
        TITLE = "Multi-Level Policy and Reward-Based Deep Reinforcement Learning
Framework for Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "1372-1383",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118555"}

@article{bb122450,
        AUTHOR = "Guo, L. and Liu, J. and Lu, S. and Lu, H.",
        TITLE = "Show, Tell, and Polish: Ruminant Decoding for Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "2149-2162",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118556"}

@article{bb122451,
        AUTHOR = "Feng, Q. and Wu, Y. and Fan, H. and Yan, C. and Xu, M. and Yang, Y.",
        TITLE = "Cascaded Revision Network for Novel Object Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "30",
        YEAR = "2020",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "3413-3421",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118557"}

@article{bb122452,
        AUTHOR = "Wei, H.Y. and Li, Z.X. and Zhang, C.L. and Ma, H.F.",
        TITLE = "The synergy of double attention: Combine sentence-level and
word-level attention for image captioning",
        JOURNAL = CVIU,
        VOLUME = "201",
        YEAR = "2020",
        PAGES = "103068",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118558"}

@article{bb122453,
        AUTHOR = "Shilpa, M. and He, J. and Zhao, Y.J. and Sun, B. and Yu, L.J.",
        TITLE = "Feedback evaluations to promote image captioning",
        JOURNAL = IET-IPR,
        VOLUME = "14",
        YEAR = "2020",
        NUMBER = "13",
        MONTH = "November",
        PAGES = "3021-3027",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118559"}

@article{bb122454,
        AUTHOR = "Liu, H. and Zhang, S. and Lin, K. and Wen, J. and Li, J. and Hu, X.",
        TITLE = "Vocabulary-Wide Credit Assignment for Training Image Captioning
Models",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "2450-2460",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118560"}

@article{bb122455,
        AUTHOR = "Xu, N. and Tian, H.S. and Wang, Y.H. and Nie, W.Z. and Song, D. and Liu, A.A. and Liu, W.",
        TITLE = "Coupled-dynamic learning for vision and language:
Exploring Interaction between different tasks",
        JOURNAL = PR,
        VOLUME = "113",
        YEAR = "2021",
        PAGES = "107829",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118561"}

@article{bb122456,
        AUTHOR = "Yang, L. and Wang, H. and Tang, P. and Li, Q.",
        TITLE = "CaptionNet: A Tailor-made Recurrent Neural Network for Generating
Image Descriptions",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "835-845",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118562"}

@article{bb122457,
        AUTHOR = "Liu, A.A. and Wang, Y.H. and Xu, N. and Liu, S. and Li, X.",
        TITLE = "Scene-Graph-Guided message passing network for dense captioning",
        JOURNAL = PRL,
        VOLUME = "145",
        YEAR = "2021",
        PAGES = "187-193",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118563"}

@article{bb122458,
        AUTHOR = "Zhang, L. and Zhang, Y.S. and Zhao, X. and Zou, Z.X.",
        TITLE = "Image captioning via proximal policy optimization",
        JOURNAL = IVC,
        VOLUME = "108",
        YEAR = "2021",
        PAGES = "104126",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118564"}

@article{bb122459,
        AUTHOR = "Ji, J.Z. and Du, Z.R. and Zhang, X.D.",
        TITLE = "Divergent-convergent attention for image captioning",
        JOURNAL = PR,
        VOLUME = "115",
        YEAR = "2021",
        PAGES = "107928",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118565"}

@article{bb122460,
        AUTHOR = "Wei, Y.W. and Wu, C.L. and Jia, Z.Y. and Hu, X. and Guo, S. and Shi, H.T.",
        TITLE = "Past is important: Improved image captioning by looking back in time",
        JOURNAL = SP:IC,
        VOLUME = "94",
        YEAR = "2021",
        PAGES = "116183",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118566"}

@article{bb122461,
        AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.",
        TITLE = "Exploring region relationships implicitly:
Image captioning with visual relationship attention",
        JOURNAL = IVC,
        VOLUME = "109",
        YEAR = "2021",
        PAGES = "104146",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118567"}

@article{bb122462,
        AUTHOR = "Zhang, Z.J. and Wu, Q. and Wang, Y. and Chen, F.",
        TITLE = "Exploring Pairwise Relationships Adaptively From Linguistic Context
in Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "24",
        YEAR = "2022",
        PAGES = "3101-3113",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118568"}

@article{bb122463,
        AUTHOR = "Li, X.L. and Zhang, X.T. and Huang, W. and Wang, Q.",
        TITLE = "Truncation Cross Entropy Loss for Remote Sensing Image Captioning",
        JOURNAL = GeoRS,
        VOLUME = "59",
        YEAR = "2021",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "5246-5257",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118569"}

@article{bb122464,
        AUTHOR = "Zhong, X. and Nie, G.Z. and Huang, W.X. and Liu, W.X. and Ma, B. and Lin, C.W.",
        TITLE = "Attention-guided image captioning with adaptive global and local
feature fusion",
        JOURNAL = JVCIR,
        VOLUME = "78",
        YEAR = "2021",
        PAGES = "103138",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118570"}

@article{bb122465,
        AUTHOR = "Sumbul, G. and Nayak, S. and Demir, B.",
        TITLE = "SD-RSIC: Summarization-Driven Deep Remote Sensing Image Captioning",
        JOURNAL = GeoRS,
        VOLUME = "59",
        YEAR = "2021",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "6922-6934",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118571"}

@article{bb122466,
        AUTHOR = "Wu, J. and Chen, T.S. and Wu, H.F. and Yang, Z. and Luo, G.C. and Lin, L.",
        TITLE = "Fine-Grained Image Captioning With Global-Local Discriminative
Objective",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "2413-2427",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118572"}

@article{bb122467,
        AUTHOR = "Wu, L.X. and Xu, M. and Sang, L. and Yao, T. and Mei, T.",
        TITLE = "Noise Augmented Double-Stream Graph Convolutional Networks for Image
Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "31",
        YEAR = "2021",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "3118-3127",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118573"}

@article{bb122468,
        AUTHOR = "Nivedita, M. and Chandrashekar, P. and Mahapatra, S. and Phamila, Y.A.V. and Selvaperumal, S.K.",
        TITLE = "Image Captioning for Video Surveillance System using Neural Networks",
        JOURNAL = IJIG,
        VOLUME = "21",
        YEAR = "2021",
        NUMBER = "4",
        MONTH = "October",
        PAGES = "2150044",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118574"}

@article{bb122469,
        AUTHOR = "Wang, Q. and Huang, W. and Zhang, X.T. and Li, X.L.",
        TITLE = "Word-Sentence Framework for Remote Sensing Image Captioning",
        JOURNAL = GeoRS,
        VOLUME = "59",
        YEAR = "2021",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "10532-10543",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118575"}

@article{bb122470,
        AUTHOR = "Wan, B.Y. and Jiang, W.H. and Fang, Y.M. and Zhu, M.W. and Li, Q. and Liu, Y.",
        TITLE = "Revisiting image captioning via maximum discrepancy competition",
        JOURNAL = PR,
        VOLUME = "122",
        YEAR = "2022",
        PAGES = "108358",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118576"}

@article{bb122471,
        AUTHOR = "Chen, T.Y. and Li, Z.X. and Wu, J.L. and Ma, H.F. and Su, B.P.",
        TITLE = "Improving image captioning with Pyramid Attention and SC-GAN",
        JOURNAL = IVC,
        VOLUME = "117",
        YEAR = "2022",
        PAGES = "104340",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118577"}

@article{bb122472,
        AUTHOR = "Zhou, Y.J. and Long, J.F. and Xu, S.P. and Shang, L.",
        TITLE = "Attribute-driven image captioning via soft-switch pointer",
        JOURNAL = PRL,
        VOLUME = "152",
        YEAR = "2021",
        PAGES = "34-41",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118578"}

@article{bb122473,
        AUTHOR = "Zha, Z.J. and Liu, D. and Zhang, H.W. and Zhang, Y.D. and Wu, F.",
        TITLE = "Context-Aware Visual Policy Network for Fine-Grained Image Captioning",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "710-722",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118579"}

@article{bb122474,
        AUTHOR = "Wang, Q.Z. and Wan, J. and Chan, A.B.",
        TITLE = "On Diversity in Image Captioning: Metrics and Methods",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "1035-1049",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118580"}

@inproceedings{bb122475,
        AUTHOR = "Wang, J. and Xu, W.J. and Wang, Q.Z. and Chan, A.B.",
        TITLE = "Compare and Reweight:
Distinctive Image Captioning Using Similar Images Sets",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "I:370-386",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118581"}

@article{bb122476,
        AUTHOR = "Luo, G.F. and Cheng, L.J. and Jing, C. and Zhao, C. and Song, G.Z.",
        TITLE = "A thorough review of models, evaluation metrics, and datasets on
image captioning",
        JOURNAL = IET-IPR,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "2",
        PAGES = "311-332",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118582"}

@article{bb122477,
        AUTHOR = "Ben, H.X. and Pan, Y.W. and Li, Y. and Yao, T. and Hong, R.C. and Wang, M. and Mei, T.",
        TITLE = "Unpaired Image Captioning With semantic-Constrained Self-Learning",
        JOURNAL = MultMed,
        VOLUME = "24",
        YEAR = "2022",
        PAGES = "904-916",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118583"}

@article{bb122478,
        AUTHOR = "Song, P.P. and Guo, D. and Zhou, J.X. and Xu, M.L. and Wang, M.",
        TITLE = "Memorial GAN With Joint Semantic Optimization for Unpaired Image
Captioning",
        JOURNAL = Cyber,
        VOLUME = "53",
        YEAR = "2023",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "4388-4399",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118584"}

@inproceedings{bb122479,
        AUTHOR = "Li, Y. and Yao, T. and Pan, Y.W. and Chao, H.Y. and Mei, T.",
        TITLE = "Pointing Novel Objects in Image Captioning",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "12489-12498",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118585"}

@article{bb122480,
        AUTHOR = "Liu, M.F. and Hu, H.J. and Li, L.J. and Yu, Y. and Guan, W.L.",
        TITLE = "Chinese Image Caption Generation via Visual Attention and Topic
Modeling",
        JOURNAL = Cyber,
        VOLUME = "52",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "1247-1257",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118586"}

@article{bb122481,
        AUTHOR = "Yang, Q.Q. and Ni, Z.H. and Ren, P.",
        TITLE = "Meta captioning:
A meta learning based remote sensing image captioning framework",
        JOURNAL = PandRS,
        VOLUME = "186",
        YEAR = "2022",
        PAGES = "190-200",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118587"}

@article{bb122482,
        AUTHOR = "Yang, X. and Zhang, H.W. and Cai, J.F.",
        TITLE = "Auto-Encoding and Distilling Scene Graphs for Image Captioning",
        JOURNAL = PAMI,
        VOLUME = "44",
        YEAR = "2022",
        NUMBER = "5",
        MONTH = "May",
        PAGES = "2313-2327",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118588"}

@article{bb122483,
        AUTHOR = "Yang, X. and Zhang, H.W. and Cai, J.F.",
        TITLE = "Deconfounded Image Captioning: A Causal Retrospect",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "12996-13010",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118589"}

@inproceedings{bb122484,
        AUTHOR = "Yang, X. and Tang, K. and Zhang, H.W. and Cai, J.F.",
        TITLE = "Auto-Encoding Scene Graphs for Image Captioning",
        BOOKTITLE = CVPR19,
        YEAR = "2019",
        PAGES = "10677-10686",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118590"}

@article{bb122485,
        AUTHOR = "Yang, Z.P. and Wang, P.B. and Chu, T.S. and Yang, J.",
        TITLE = "Human-Centric Image Captioning",
        JOURNAL = PR,
        VOLUME = "126",
        YEAR = "2022",
        PAGES = "108545",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118591"}

@article{bb122486,
        AUTHOR = "Li, X. and Zhang, W.K. and Sun, X. and Gao, X.",
        TITLE = "Without detection: Two-step clustering features with local-global
attention for image captioning",
        JOURNAL = IET-CV,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "3",
        PAGES = "280-294",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118592"}

@article{bb122487,
        AUTHOR = "Yu, L.T. and Zhang, J. and Wu, Q.",
        TITLE = "Dual Attention on Pyramid Feature Maps for Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "24",
        YEAR = "2022",
        NUMBER = "2022",
        PAGES = "1775-1786",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118593"}

@article{bb122488,
        AUTHOR = "Zhang, M. and Chen, J.X. and Li, P.F. and Jiang, M. and Zhou, Z.",
        TITLE = "Topic scene graphs for image captioning",
        JOURNAL = IET-CV,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "4",
        PAGES = "364-375",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118594"}

@article{bb122489,
        AUTHOR = "Yu, Q. and Zhang, C.X. and Weng, L. and Xiang, S.M. and Pan, C.H.",
        TITLE = "Scene captioning with deep fusion of images and point clouds",
        JOURNAL = PRL,
        VOLUME = "158",
        YEAR = "2022",
        PAGES = "9-15",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118595"}

@article{bb122490,
        AUTHOR = "Chaudhari, C.P. and Devane, S.",
        TITLE = "Improved Framework using Rider Optimization Algorithm for Precise Image
Caption Generation",
        JOURNAL = IJIG,
        VOLUME = "22",
        YEAR = "2022",
        NUMBER = "2",
        MONTH = "April",
        PAGES = "2250021",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118596"}

@article{bb122491,
        AUTHOR = "Shao, X.J. and Xiang, Z.L. and Li, Y.X. and Zhang, M.J.",
        TITLE = "Variational joint self-attention for image captioning",
        JOURNAL = IET-IPR,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "8",
        PAGES = "2075-2086",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118597"}

@article{bb122492,
        AUTHOR = "Li, Y.C. and Wu, C. and Li, L. and Liu, Y.H. and Zhu, J.",
        TITLE = "Caption Generation From Road Images for Traffic Scene Modeling",
        JOURNAL = ITS,
        VOLUME = "23",
        YEAR = "2022",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "7805-7816",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118598"}

@article{bb122493,
        AUTHOR = "Wang, Y.H. and Xu, N. and Liu, A.A. and Li, W.H. and Zhang, Y.D.",
        TITLE = "High-Order Interaction Learning for Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "32",
        YEAR = "2022",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "4417-4430",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118599"}

@article{bb122494,
        AUTHOR = "Guo, D.D. and Lu, R.Y. and Chen, B. and Zeng, Z.Q. and Zhou, M.Y.",
        TITLE = "Matching Visual Features to Hierarchical Semantic Topics for Image
Paragraph Captioning",
        JOURNAL = IJCV,
        VOLUME = "130",
        YEAR = "2022",
        NUMBER = "8",
        MONTH = "August",
        PAGES = "1920-1937",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118600"}

@article{bb122495,
        AUTHOR = "Demirel, B. and Cinbis, R.G.",
        TITLE = "Caption generation on scenes with seen and unseen object categories",
        JOURNAL = IVC,
        VOLUME = "124",
        YEAR = "2022",
        PAGES = "104515",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118601"}

@article{bb122496,
        AUTHOR = "Liu, Z.Y. and Dong, A.M. and Yu, J.G. and Han, Y.B. and Zhou, Y. and Zhao, K.",
        TITLE = "Scene classification for remote sensing images with self-attention
augmented CNN",
        JOURNAL = IET-IPR,
        VOLUME = "16",
        YEAR = "2022",
        NUMBER = "11",
        PAGES = "3085-3096",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118602"}

@article{bb122497,
        AUTHOR = "Wu, X.X. and Zhao, W.T. and Luo, J.B.",
        TITLE = "Learning Cooperative Neural Modules for Stylized Image Captioning",
        JOURNAL = IJCV,
        VOLUME = "130",
        YEAR = "2022",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2305-2320",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118603"}

@article{bb122498,
        AUTHOR = "Zhou, H. and Du, X.P. and Xia, L. and Li, S.",
        TITLE = "Self-Learning for Few-Shot Remote Sensing Image Captioning",
        JOURNAL = RS,
        VOLUME = "14",
        YEAR = "2022",
        NUMBER = "18",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118604"}

@article{bb122499,
        AUTHOR = "Stefanini, M. and Cornia, M. and Baraldi, L. and Cascianelli, S. and Fiameni, G. and Cucchiara, R.",
        TITLE = "From Show to Tell: A Survey on Deep Learning-Based Image Captioning",
        JOURNAL = PAMI,
        VOLUME = "45",
        YEAR = "2023",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "539-559",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT118605"}

Last update:Jun 17, 2024 at 21:38:11