@article{bb104300,
        AUTHOR = "Park, C.C. and Kim, B. and Kim, G.",
        TITLE = "Towards Personalized Image Captioning via Multimodal Memory Networks",
        JOURNAL = PAMI,
        VOLUME = "41",
        YEAR = "2019",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "999-1012",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100686"}

@inproceedings{bb104301,
        AUTHOR = "Park, C.C. and Kim, B. and Kim, G.",
        TITLE = "Attend to You: Personalized Image Captioning with Context Sequence
Memory Networks",
        BOOKTITLE = CVPR17,
        YEAR = "2017",
        PAGES = "6432-6440",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100687"}

@article{bb104302,
        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#TT100688"}

@article{bb104303,
        AUTHOR = "Yang, M. and Zhao, W. and Xu, W. and Feng, Y. and Zhao, Z. and Chen, X. and Lei, K.",
        TITLE = "Multitask Learning for Cross-Domain Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "1047-1061",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100689"}

@article{bb104304,
        AUTHOR = "Foumani, S.N.M. and Nickabadi, A.",
        TITLE = "A probabilistic topic model using deep visual word representation for
simultaneous image classification and annotation",
        JOURNAL = JVCIR,
        VOLUME = "59",
        YEAR = "2019",
        PAGES = "195-203",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100690"}

@article{bb104305,
        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#TT100691"}

@article{bb104306,
        AUTHOR = "Zheng, H. and Wu, J.H. and Liang, R. and Li, Y. and Li, X.Z.",
        TITLE = "Multi-task learning for captioning images with novel words",
        JOURNAL = IET-CV,
        VOLUME = "13",
        YEAR = "2019",
        NUMBER = "3",
        MONTH = "April",
        PAGES = "294-301",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100692"}

@article{bb104307,
        AUTHOR = "Yu, N. and Hu, X. and Song, B. and Yang, J. and Zhang, J.",
        TITLE = "Topic-Oriented Image Captioning Based on Order-Embedding",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "2743-2754",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100693"}

@article{bb104308,
        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#TT100694"}

@article{bb104309,
        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#TT100695"}

@article{bb104310,
        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#TT100696"}

@article{bb104311,
        AUTHOR = "Peng, Y.Q. and Liu, X. and Wang, W.H. and Zhao, X.S. and Wei, M.",
        TITLE = "Image caption model of double LSTM with scene factors",
        JOURNAL = IVC,
        VOLUME = "86",
        YEAR = "2019",
        PAGES = "38-44",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100697"}

@article{bb104312,
        AUTHOR = "Zhang, J.J. and Wu, Q. and Zhang, J. and Shen, C.H. and Lu, J.F. and Wu, Q.A.",
        TITLE = "Heritage image annotation via collective knowledge",
        JOURNAL = PR,
        VOLUME = "93",
        YEAR = "2019",
        PAGES = "204-214",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100698"}

@article{bb104313,
        AUTHOR = "Verma, Y.",
        TITLE = "Diverse image annotation with missing labels",
        JOURNAL = PR,
        VOLUME = "93",
        YEAR = "2019",
        PAGES = "470-484",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100699"}

@article{bb104314,
        AUTHOR = "Markatopoulou, F. and Mezaris, V. and Patras, I.",
        TITLE = "Implicit and Explicit Concept Relations in Deep Neural Networks for
Multi-Label Video/Image Annotation",
        JOURNAL = CirSysVideo,
        VOLUME = "29",
        YEAR = "2019",
        NUMBER = "6",
        MONTH = "June",
        PAGES = "1631-1644",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100700"}

@article{bb104315,
        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#TT100701"}

@inproceedings{bb104316,
        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#TT100702"}

@article{bb104317,
        AUTHOR = "Laib, L. and Allili, M.S. and Ait Aoudia, S.",
        TITLE = "A probabilistic topic model for event-based image classification and
multi-label annotation",
        JOURNAL = SP:IC,
        VOLUME = "76",
        YEAR = "2019",
        PAGES = "283-294",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100703"}

@article{bb104318,
        AUTHOR = "Olaode, A. and Naghdy, G.",
        TITLE = "Review of the application of machine learning to the automatic semantic
annotation of images",
        JOURNAL = IET-IPR,
        VOLUME = "13",
        YEAR = "2019",
        NUMBER = "8",
        MONTH = "June",
        PAGES = "1232-1245",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100704"}

@article{bb104319,
        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#TT100705"}

@article{bb104320,
        AUTHOR = "Zhang, C.J. and Cheng, J. and Tian, Q.",
        TITLE = "Multiview, Few-Labeled Object Categorization by Predicting Labels
With View Consistency",
        JOURNAL = Cyber,
        VOLUME = "49",
        YEAR = "2019",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "3834-3843",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100706"}

@article{bb104321,
        AUTHOR = "Xian, Y. and Tian, Y.",
        TITLE = "Self-Guiding Multimodal LSTM: When We Do Not Have a Perfect Training
Dataset for Image Captioning",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "5241-5252",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100707"}

@article{bb104322,
        AUTHOR = "Li, X. and Xu, C. and Wang, X. and Lan, W. and Jia, Z. and Yang, G. and Xu, J.",
        TITLE = "COCO-CN for Cross-Lingual Image Tagging, Captioning, and Retrieval",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2347-2360",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100708"}

@article{bb104323,
        AUTHOR = "Tian, C. and Tian, M. and Jiang, M.M. and Liu, H. and Deng, D.H.",
        TITLE = "How much do cross-modal related semantics benefit image captioning by
weighting attributes and re-ranking sentences?",
        JOURNAL = PRL,
        VOLUME = "125",
        YEAR = "2019",
        PAGES = "639-645",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100709"}

@article{bb104324,
        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#TT100710"}

@article{bb104325,
        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#TT100711"}

@article{bb104326,
        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#TT100712"}

@article{bb104327,
        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#TT100713"}

@article{bb104328,
        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#TT100714"}

@article{bb104329,
        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#TT100715"}

@article{bb104330,
        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#TT100716"}

@article{bb104331,
        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#TT100717"}

@article{bb104332,
        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#TT100718"}

@article{bb104333,
        AUTHOR = "Tang, C. and Liu, X. and Wang, P. and Zhang, C. and Li, M. and Wang, L.",
        TITLE = "Adaptive Hypergraph Embedded Semi-Supervised Multi-Label Image
Annotation",
        JOURNAL = MultMed,
        VOLUME = "21",
        YEAR = "2019",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "2837-2849",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100719"}

@article{bb104334,
        AUTHOR = "Mundnich, K. and Booth, B.M. and Girault, B. and Narayanan, S.",
        TITLE = "Generating labels for regression of subjective constructs using
triplet embeddings",
        JOURNAL = PRL,
        VOLUME = "128",
        YEAR = "2019",
        PAGES = "385-392",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100720"}

@article{bb104335,
        AUTHOR = "Huang, Y. and Chen, J. and Ouyang, W. and Wan, W. and Xue, Y.",
        TITLE = "Image Captioning With End-to-End Attribute Detection and Subsequent
Attributes Prediction",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        PAGES = "4013-4026",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100721"}

@article{bb104336,
        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#TT100722"}

@article{bb104337,
        AUTHOR = "Wu, L. and Xu, M. and Wang, J. and Perry, S.",
        TITLE = "Recall What You See Continually Using GridLSTM in Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "3",
        MONTH = "March",
        PAGES = "808-818",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100723"}

@article{bb104338,
        AUTHOR = "Li, Y.Y. and Fang, S.K. and Jiao, L.C. and Liu, R. 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#TT100724"}

@article{bb104339,
        AUTHOR = "Chaudhary, C. and Goyal, P. and Prasad, D.N. and Chen, Y.P.",
        TITLE = "Enhancing the Quality of Image Tagging Using a Visio-Textual
Knowledge Base",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "897-911",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100725"}

@article{bb104340,
        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#TT100726"}

@article{bb104341,
        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#TT100727"}

@article{bb104342,
        AUTHOR = "Deng, Z.R. and Jiang, Z.Q. and Lan, R. and Huang, W.M. and Luo, X.N.",
        TITLE = "Image captioning using DenseNet network and adaptive attention",
        JOURNAL = SP:IC,
        VOLUME = "85",
        YEAR = "2020",
        PAGES = "115836",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100728"}

@article{bb104343,
        AUTHOR = "Ji, J. and Xu, C. and Zhang, X. and Wang, B. and Song, X.",
        TITLE = "Spatio-Temporal Memory Attention for Image Captioning",
        JOURNAL = IP,
        VOLUME = "29",
        YEAR = "2020",
        PAGES = "7615-7628",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100729"}

@article{bb104344,
        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#TT100730"}

@article{bb104345,
        AUTHOR = "Khatchatoorian, A.G. and Jamzad, M.",
        TITLE = "Architecture to improve the accuracy of automatic image annotation
systems",
        JOURNAL = IET-CV,
        VOLUME = "14",
        YEAR = "2020",
        NUMBER = "5",
        MONTH = "August",
        PAGES = "214-223",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100731"}

@article{bb104346,
        AUTHOR = "Theodosiou, Z. and Tsapatsoulis, N.",
        TITLE = "Image annotation: the effects of content, lexicon and annotation method",
        JOURNAL = MultInfoRetr,
        VOLUME = "9",
        YEAR = "2020",
        NUMBER = "3",
        MONTH = "September",
        PAGES = "191-203",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100732"}

@article{bb104347,
        AUTHOR = "Che, W.B. and Fan, X.P. and Xiong, R.Q. and Zhao, D.B.",
        TITLE = "Visual Relationship Embedding Network for Image Paragraph Generation",
        JOURNAL = MultMed,
        VOLUME = "22",
        YEAR = "2020",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2307-2320",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100733"}

@article{bb104348,
        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#TT100734"}

@article{bb104349,
        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#TT100735"}

@article{bb104350,
        AUTHOR = "Shilpa, M. and He, J. and Zhao, Y. 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#TT100736"}

@article{bb104351,
        AUTHOR = "Yu, J. and Li, J. and Yu, Z. and Huang, Q.",
        TITLE = "Multimodal Transformer With Multi-View Visual Representation for
Image Captioning",
        JOURNAL = CirSysVideo,
        VOLUME = "30",
        YEAR = "2020",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "4467-4480",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100737"}

@article{bb104352,
        AUTHOR = "Zhao, W. and Wu, X. and Luo, J.",
        TITLE = "Cross-Domain Image Captioning via Cross-Modal Retrieval and Model
Adaptation",
        JOURNAL = IP,
        VOLUME = "30",
        YEAR = "2021",
        PAGES = "1180-1192",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100738"}

@article{bb104353,
        AUTHOR = "Zhang, J. and Mei, K. and Zheng, Y. and Fan, J.",
        TITLE = "Integrating Part of Speech Guidance for Image Captioning",
        JOURNAL = MultMed,
        VOLUME = "23",
        YEAR = "2021",
        PAGES = "92-104",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100739"}

@inproceedings{bb104354,
        AUTHOR = "Sharif, N. and Jalwana, M.A.A.K. and Bennamoun, M. and Liu, W. and Shah, S.A.A.",
        TITLE = "Leveraging Linguistically-aware Object Relations and NASNet for Image
Captioning",
        BOOKTITLE = IVCNZ20,
        YEAR = "2020",
        PAGES = "1-6",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100740"}

@article{bb104355,
        AUTHOR = "Gouthaman, K.V. and Nambiar, A. and Srinivas, K.S. and Mittal, A.",
        TITLE = "Linguistically-aware attention for reducing the semantic gap in
vision-language tasks",
        JOURNAL = PR,
        VOLUME = "112",
        YEAR = "2021",
        PAGES = "107812",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100741"}

@article{bb104356,
        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#TT100742"}

@article{bb104357,
        AUTHOR = "Zhang, Y. and Shi, X.Y. and Mi, S. and Yang, X.",
        TITLE = "Image captioning with transformer and knowledge graph",
        JOURNAL = PRL,
        VOLUME = "143",
        YEAR = "2021",
        PAGES = "43-49",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100743"}

@article{bb104358,
        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#TT100744"}

@article{bb104359,
        AUTHOR = "Zhang, J. and Li, K. and Wang, Z.",
        TITLE = "Parallel-fusion LSTM with synchronous semantic and visual information
for image captioning",
        JOURNAL = JVCIR,
        VOLUME = "75",
        YEAR = "2021",
        PAGES = "103044",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100745"}

@article{bb104360,
        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#TT100746"}

@article{bb104361,
        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#TT100747"}

@article{bb104362,
        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#TT100748"}

@article{bb104363,
        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#TT100749"}

@article{bb104364,
        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#TT100750"}

@article{bb104365,
        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#TT100751"}

@article{bb104366,
        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#TT100752"}

@inproceedings{bb104367,
        AUTHOR = "Umemura, K. and Kastner, M.A. and Ide, I. and Kawanishi, Y. and Hirayama, T. and Doman, K. and Deguchi, D. and Murase, H.",
        TITLE = "Tell as You Imagine: Sentence Imageability-aware Image Captioning",
        BOOKTITLE = MMMod21,
        YEAR = "2021",
        PAGES = "II:62-73",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100753"}

@inproceedings{bb104368,
        AUTHOR = "Hallonquist, N. and German, D. and Younes, L.",
        TITLE = "Graph Discovery for Visual Test Generation",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "7500-7507",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100754"}

@inproceedings{bb104369,
        AUTHOR = "Li, X.J. and Yang, C. and Chen, S.L. and Zhu, C. and Yin, X.C.",
        TITLE = "Semantic Bilinear Pooling for Fine-Grained Recognition",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "3660-3666",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100755"}

@inproceedings{bb104370,
        AUTHOR = "Chavhan, R. and Banerjee, B. and Zhu, X.X. and Chaudhuri, S.",
        TITLE = "A Novel Actor Dual-Critic Model for Remote Sensing Image Captioning",
        BOOKTITLE = ICPR21,
        YEAR = "2021",
        PAGES = "4918-4925",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100756"}

@inproceedings{bb104371,
        AUTHOR = "Kalimuthu, M. and Mogadala, A. and Mosbach, M. and Klakow, D.",
        TITLE = "Fusion Models for Improved Image Captioning",
        BOOKTITLE = MMDLCA20,
        YEAR = "2020",
        PAGES = "381-395",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100757"}

@inproceedings{bb104372,
        AUTHOR = "Cetinic, E.",
        TITLE = "Iconographic Image Captioning for Artworks",
        BOOKTITLE = FAPER20,
        YEAR = "2020",
        PAGES = "502-516",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100758"}

@inproceedings{bb104373,
        AUTHOR = "Huang, Y.Q. and Chen, J.S.",
        TITLE = "Show, Conceive and Tell: Image Captioning with Prospective Linguistic
Information",
        BOOKTITLE = ACCV20,
        YEAR = "2020",
        PAGES = "VI:478-494",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100759"}

@inproceedings{bb104374,
        AUTHOR = "He, S. and Liao, W. and Tavakoli, H.R. and Yang, M. and Rosenhahn, B. and Pugeault, N.",
        TITLE = "Image Captioning Through Image Transformer",
        BOOKTITLE = ACCV20,
        YEAR = "2020",
        PAGES = "IV:153-169",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100760"}

@inproceedings{bb104375,
        AUTHOR = "Deng, C.R. and Ding, N. and Tan, M.K. and Wu, Q.",
        TITLE = "Length-controllable Image Captioning",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIII:712-729",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100761"}

@inproceedings{bb104376,
        AUTHOR = "Gurari, D. and Zhao, Y.N. and Zhang, M. and Bhattacharya, N.",
        TITLE = "Captioning Images Taken by People Who Are Blind",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XVII:417-434",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100762"}

@inproceedings{bb104377,
        AUTHOR = "Jiu, M. and Sahbi, H.",
        TITLE = "End-to-End Deep Kernel Map Design for Image Annotation",
        BOOKTITLE = ICIP20,
        YEAR = "2020",
        PAGES = "1546-1550",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100763"}

@inproceedings{bb104378,
        AUTHOR = "Zhong, Y.W. and Wang, L.W. and Chen, J.S. and Yu, D. and Li, Y.",
        TITLE = "Comprehensive Image Captioning via Scene Graph Decomposition",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "XIV:211-229",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100764"}

@inproceedings{bb104379,
        AUTHOR = "Wang, Z. and Feng, B. and Narasimhan, K. and Russakovsky, O.",
        TITLE = "Towards Unique and Informative Captioning of Images",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "VII:629-644",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100765"}

@inproceedings{bb104380,
        AUTHOR = "Wang, J. and Xu, W. 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#TT100766"}

@inproceedings{bb104381,
        AUTHOR = "Sidorov, O. and Hu, R. and Rohrbach, M. and Singh, A.",
        TITLE = "Textcaps: A Dataset for Image Captioning with Reading Comprehension",
        BOOKTITLE = ECCV20,
        YEAR = "2020",
        PAGES = "II:742-758",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100767"}

@inproceedings{bb104382,
        AUTHOR = "Durand, T.",
        TITLE = "Learning User Representations for Open Vocabulary Image Hashtag
Prediction",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "9766-9775",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100768"}

@inproceedings{bb104383,
        AUTHOR = "Prabhudesai, M. and Tung, H.Y.F. and Javed, S.A. and Sieb, M. and Harley, A.W. and Fragkiadaki, K.",
        TITLE = "Embodied Language Grounding With 3D Visual Feature Representations",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "2217-2226",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100769"}

@inproceedings{bb104384,
        AUTHOR = "Li, Z. and Tran, Q. and Mai, L. and Lin, Z. and Yuille, A.L.",
        TITLE = "Context-Aware Group Captioning via Self-Attention and Contrastive
Features",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "3437-3447",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100770"}

@inproceedings{bb104385,
        AUTHOR = "Zhou, Y. and Wang, M. and Liu, D. and Hu, Z. and Zhang, H.",
        TITLE = "More Grounded Image Captioning by Distilling Image-Text Matching
Model",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "4776-4785",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100771"}

@inproceedings{bb104386,
        AUTHOR = "Sammani, F. and Melas Kyriazi, L.",
        TITLE = "Show, Edit and Tell: A Framework for Editing Image Captions",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "4807-4815",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100772"}

@inproceedings{bb104387,
        AUTHOR = "Chen, S. and Jin, Q. and Wang, P. and Wu, Q.",
        TITLE = "Say As You Wish: Fine-Grained Control of Image Caption Generation
With Abstract Scene Graphs",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "9959-9968",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100773"}

@inproceedings{bb104388,
        AUTHOR = "Guo, L. and Liu, J. and Zhu, X. and Yao, P. and Lu, S. and Lu, H.",
        TITLE = "Normalized and Geometry-Aware Self-Attention Network for Image
Captioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10324-10333",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100774"}

@inproceedings{bb104389,
        AUTHOR = "Cornia, M. and Stefanini, M. and Baraldi, L. and Cucchiara, R.",
        TITLE = "Meshed-Memory Transformer for Image Captioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10575-10584",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100775"}

@inproceedings{bb104390,
        AUTHOR = "Chen, J. and Jin, Q.",
        TITLE = "Better Captioning With Sequence-Level Exploration",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10887-10896",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100776"}

@inproceedings{bb104391,
        AUTHOR = "Pan, Y. and Yao, T. and Li, Y. and Mei, T.",
        TITLE = "X-Linear Attention Networks for Image Captioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "10968-10977",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100777"}

@inproceedings{bb104392,
        AUTHOR = "Tran, A. and Mathews, A. and Xie, L.",
        TITLE = "Transform and Tell: Entity-Aware News Image Captioning",
        BOOKTITLE = CVPR20,
        YEAR = "2020",
        PAGES = "13032-13042",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100778"}

@inproceedings{bb104393,
        AUTHOR = "Park, G. and Han, C. and Kim, D. and Yoon, W.J.",
        TITLE = "MHSAN: Multi-Head Self-Attention Network for Visual Semantic
Embedding",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "1507-1515",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100779"}

@inproceedings{bb104394,
        AUTHOR = "Chen, C. and Zhang, R. and Koh, E. and Kim, S. and Cohen, S. and Rossi, R.",
        TITLE = "Figure Captioning with Relation Maps for Reasoning",
        BOOKTITLE = WACV20,
        YEAR = "2020",
        PAGES = "1526-1534",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100780"}

@inproceedings{bb104395,
        AUTHOR = "He, S. and Tavakoli, H.R. and Borji, A. and Pugeault, N.",
        TITLE = "Human Attention in Image Captioning: Dataset and Analysis",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "8528-8537",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100781"}

@inproceedings{bb104396,
        AUTHOR = "Laina, I. and Rupprecht, C. and Navab, N.",
        TITLE = "Towards Unsupervised Image Captioning With Shared Multimodal
Embeddings",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "7413-7423",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100782"}

@inproceedings{bb104397,
        AUTHOR = "Huang, L. and Wang, W. and Chen, J. and Wei, X.",
        TITLE = "Attention on Attention for Image Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4633-4642",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100783"}

@inproceedings{bb104398,
        AUTHOR = "Yang, X. and Zhang, H. and Cai, J.",
        TITLE = "Learning to Collocate Neural Modules for Image Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4249-4259",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100784"}

@inproceedings{bb104399,
        AUTHOR = "Yao, T. and Pan, Y. and Li, Y. and Mei, T.",
        TITLE = "Hierarchy Parsing for Image Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "2621-2629",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT100785"}

Last update:Jun 14, 2021 at 09:20:36