@inproceedings{bb99600,
        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#TT96044"}

@article{bb99601,
        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#TT96045"}

@article{bb99602,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "Dense Sampling Low-Level Statistics of Local Features",
        JOURNAL = IEICE,
        VOLUME = "E93-D",
        YEAR = "2010",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "1727-1736",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96046"}

@inproceedings{bb99603,
        AUTHOR = "Kuniyoshi, Y. and Harada, T. and Nakayama, H.",
        TITLE = "Dense Sampling Low-Level Statistics of Local Features",
        BOOKTITLE = CIVR09,
        YEAR = "2009",
        PAGES = "Article No 17",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96046"}

@inproceedings{bb99604,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "Global Gaussian approach for scene categorization using information
geometry",
        BOOKTITLE = CVPR10,
        YEAR = "2010",
        PAGES = "2336-2343",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96047"}

@inproceedings{bb99605,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "AI Goggles: Real-time Description and Retrieval in the Real World with
Online Learning",
        BOOKTITLE = CRV09,
        YEAR = "2009",
        PAGES = "184-191",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96048"}

@inproceedings{bb99606,
        AUTHOR = "Ushiku, Y. and Yamaguchi, M. and Mukuta, Y. and Harada, T.",
        TITLE = "Common Subspace for Model and Similarity:
Phrase Learning for Caption Generation from Images",
        BOOKTITLE = ICCV15,
        YEAR = "2015",
        PAGES = "2668-2676",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96049"}

@inproceedings{bb99607,
        AUTHOR = "Jin, J. and Nakayama, H.",
        TITLE = "Annotation order matters:
Recurrent Image Annotator for arbitrary length image tagging",
        BOOKTITLE = ICPR16,
        YEAR = "2016",
        PAGES = "2452-2457",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96050"}

@inproceedings{bb99608,
        AUTHOR = "Harada, T. and Nakayama, H. and Kuniyoshi, Y.",
        TITLE = "Improving Local Descriptors by Embedding Global and Local Spatial
Information",
        BOOKTITLE = ECCV10,
        YEAR = "2010",
        PAGES = "IV: 736-749",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96051"}

@inproceedings{bb99609,
        AUTHOR = "Nakayama, H. and Harada, T. and Kuniyoshi, Y.",
        TITLE = "Evaluation of dimensionality reduction methods for image
auto-annotation",
        BOOKTITLE = BMVC10,
        YEAR = "2010",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96052"}

@article{bb99610,
        AUTHOR = "Verma, Y. and Jawahar, C.V.",
        TITLE = "A support vector approach for cross-modal search of images and texts",
        JOURNAL = CVIU,
        VOLUME = "154",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "48-63",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96053"}

@article{bb99611,
        AUTHOR = "Xue, J.F. and Eguchi, K.",
        TITLE = "Video Data Modeling Using Sequential Correspondence Hierarchical
Dirichlet Processes",
        JOURNAL = IEICE,
        VOLUME = "E100-D",
        YEAR = "2017",
        NUMBER = "1",
        MONTH = "January",
        PAGES = "33-41",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96054"}

@article{bb99612,
        AUTHOR = "Tariq, A. and Foroosh, H.",
        TITLE = "A Context-Driven Extractive Framework for Generating Realistic Image
Descriptions",
        JOURNAL = IP,
        VOLUME = "26",
        YEAR = "2017",
        NUMBER = "2",
        MONTH = "February",
        PAGES = "619-632",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96055"}

@article{bb99613,
        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#TT96056"}

@inproceedings{bb99614,
        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#TT96057"}

@article{bb99615,
        AUTHOR = "Gao, L. and Guo, Z. and Zhang, H. and Xu, X. and Shen, H.T.",
        TITLE = "Video Captioning With Attention-Based LSTM and Semantic Consistency",
        JOURNAL = MultMed,
        VOLUME = "19",
        YEAR = "2017",
        NUMBER = "9",
        MONTH = "September",
        PAGES = "2045-2055",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96058"}

@article{bb99616,
        AUTHOR = "Hu, M. and Yang, Y. and Shen, F. and Zhang, L. and Shen, H.T. and Li, X.",
        TITLE = "Robust Web Image Annotation via Exploring Multi-Facet and Structural
Knowledge",
        JOURNAL = IP,
        VOLUME = "26",
        YEAR = "2017",
        NUMBER = "10",
        MONTH = "October",
        PAGES = "4871-4884",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96059"}

@article{bb99617,
        AUTHOR = "Bin, Y. and Yang, Y. and Shen, F. and Xie, N. and Shen, H.T. and Li, X.",
        TITLE = "Describing Video With Attention-Based Bidirectional LSTM",
        JOURNAL = Cyber,
        VOLUME = "49",
        YEAR = "2019",
        NUMBER = "7",
        MONTH = "July",
        PAGES = "2631-2641",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96060"}

@article{bb99618,
        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#TT96061"}

@article{bb99619,
        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#TT96062"}

@article{bb99620,
        AUTHOR = "Fu, K. and Jin, J.Q. and Cui, R.P. and Sha, F. and Zhang, C.S.",
        TITLE = "Aligning Where to See and What to Tell: Image Captioning with
Region-Based Attention and Scene-Specific Contexts",
        JOURNAL = PAMI,
        VOLUME = "39",
        YEAR = "2017",
        NUMBER = "12",
        MONTH = "December",
        PAGES = "2321-2334",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96063"}

@article{bb99621,
        AUTHOR = "Liu, A.A. and Xu, N. and Wong, Y. and Li, J. and Su, Y.T. and Kankanhalli, M.",
        TITLE = "Hierarchical & multimodal video captioning: Discovering and
transferring multimodal knowledge for vision to language",
        JOURNAL = CVIU,
        VOLUME = "163",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "113-125",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96064"}

@article{bb99622,
        AUTHOR = "Nian, F.D. and Li, T. and Wang, Y. and Wu, X.Y. and Ni, B.B. and Xu, C.S.",
        TITLE = "Learning explicit video attributes from mid-level representation for
video captioning",
        JOURNAL = CVIU,
        VOLUME = "163",
        YEAR = "2017",
        NUMBER = "1",
        PAGES = "126-138",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96065"}

@article{bb99623,
        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#TT96066"}

@article{bb99624,
        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#TT96066"}

@article{bb99625,
        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#TT96067"}

@article{bb99626,
        AUTHOR = "Guan, J.N. and Wang, E.",
        TITLE = "Repeated review based image captioning for image evidence review",
        JOURNAL = SP:IC,
        VOLUME = "63",
        YEAR = "2018",
        PAGES = "141-148",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96068"}

@article{bb99627,
        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#TT96069"}

@article{bb99628,
        AUTHOR = "Cheng, Q. and Zhang, Q. and Fu, P. and Tu, C.H. and Li, S.",
        TITLE = "A survey and analysis on automatic image annotation",
        JOURNAL = PR,
        VOLUME = "79",
        YEAR = "2018",
        PAGES = "242-259",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96070"}

@article{bb99629,
        AUTHOR = "Ben Rejeb, I. and Ouni, S. and Barhoumi, W. and Zagrouba, E.",
        TITLE = "Fuzzy VA-Files for multi-label image annotation based on visual content
of regions",
        JOURNAL = SIViP,
        VOLUME = "12",
        YEAR = "2018",
        NUMBER = "5",
        MONTH = "July",
        PAGES = "877-884",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96071"}

@article{bb99630,
        AUTHOR = "Helmy, T.",
        TITLE = "A Generic Framework for Semantic Annotation of Images",
        JOURNAL = IJIG,
        VOLUME = "18",
        YEAR = "2018",
        NUMBER = "3",
        MONTH = "July",
        PAGES = "Article 1850013",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96072"}

@article{bb99631,
        AUTHOR = "Wu, C.L. and Wei, Y. and Chu, X.L. and Su, F. and Wang, L.",
        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#TT96073"}

@article{bb99632,
        AUTHOR = "Ye, S. and Han, J. and Liu, N.",
        TITLE = "Attentive Linear Transformation for Image Captioning",
        JOURNAL = IP,
        VOLUME = "27",
        YEAR = "2018",
        NUMBER = "11",
        MONTH = "November",
        PAGES = "5514-5524",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96074"}

@article{bb99633,
        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#TT96075"}

@article{bb99634,
        AUTHOR = "Hu, J. and Lam, K.M. and Lou, P. and Liu, Q. and Deng, W.P.",
        TITLE = "Can a machine have two systems for recognition, like human beings?",
        JOURNAL = JVCIR,
        VOLUME = "56",
        YEAR = "2018",
        PAGES = "275-286",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96076"}

@article{bb99635,
        AUTHOR = "Bhagat, P.K. and Choudhary, P.",
        TITLE = "Image annotation: Then and now",
        JOURNAL = IVC,
        VOLUME = "80",
        YEAR = "2018",
        PAGES = "1-23",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96077"}

@article{bb99636,
        AUTHOR = "Gil Gonzalez, J. and Alvarez Meza, A. and Orozco Gutierrez, A.",
        TITLE = "Learning from multiple annotators using kernel alignment",
        JOURNAL = PRL,
        VOLUME = "116",
        YEAR = "2018",
        PAGES = "150-156",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96078"}

@article{bb99637,
        AUTHOR = "Bazrafkan, S. and Javidnia, H. and Corcoran, P.",
        TITLE = "Latent space mapping for generation of object elements with
corresponding data annotation",
        JOURNAL = PRL,
        VOLUME = "116",
        YEAR = "2018",
        PAGES = "179-186",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96079"}

@article{bb99638,
        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#TT96080"}

@article{bb99639,
        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#TT96081"}

@article{bb99640,
        AUTHOR = "Niu, Y. and Lu, Z. and Wen, J. and Xiang, T. and Chang, S.",
        TITLE = "Multi-Modal Multi-Scale Deep Learning for Large-Scale Image
Annotation",
        JOURNAL = IP,
        VOLUME = "28",
        YEAR = "2019",
        NUMBER = "4",
        MONTH = "April",
        PAGES = "1720-1731",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96082"}

@article{bb99641,
        AUTHOR = "Jiu, M.Y. and Sahbi, H.",
        TITLE = "Deep representation design from deep kernel networks",
        JOURNAL = PR,
        VOLUME = "88",
        YEAR = "2019",
        PAGES = "447-457",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96083"}

@article{bb99642,
        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#TT96084"}

@article{bb99643,
        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#TT96085"}

@inproceedings{bb99644,
        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#TT96086"}

@article{bb99645,
        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#TT96087"}

@article{bb99646,
        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#TT96088"}

@article{bb99647,
        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#TT96089"}

@article{bb99648,
        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#TT96090"}

@article{bb99649,
        AUTHOR = "Zheng, H. and Wu, J. and Liang, R. and Li, Y. and Li, X.",
        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#TT96091"}

@article{bb99650,
        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#TT96092"}

@article{bb99651,
        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#TT96093"}

@article{bb99652,
        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#TT96094"}

@article{bb99653,
        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#TT96095"}

@article{bb99654,
        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#TT96096"}

@article{bb99655,
        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#TT96097"}

@article{bb99656,
        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#TT96098"}

@article{bb99657,
        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#TT96099"}

@article{bb99658,
        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#TT96100"}

@inproceedings{bb99659,
        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#TT96101"}

@article{bb99660,
        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#TT96102"}

@article{bb99661,
        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#TT96103"}

@article{bb99662,
        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#TT96104"}

@article{bb99663,
        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#TT96105"}

@article{bb99664,
        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#TT96106"}

@article{bb99665,
        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#TT96107"}

@article{bb99666,
        AUTHOR = "Zakharov, N. and Su, H. and Zhu, J. and Glascher, J.",
        TITLE = "Towards controllable image descriptions with semi-supervised VAE",
        JOURNAL = JVCIR,
        VOLUME = "63",
        YEAR = "2019",
        PAGES = "102574",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96108"}

@article{bb99667,
        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#TT96109"}

@article{bb99668,
        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#TT96110"}

@article{bb99669,
        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#TT96111"}

@article{bb99670,
        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#TT96112"}

@article{bb99671,
        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#TT96113"}

@article{bb99672,
        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#TT96114"}

@article{bb99673,
        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#TT96115"}

@article{bb99674,
        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#TT96116"}

@article{bb99675,
        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#TT96117"}

@article{bb99676,
        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#TT96118"}

@article{bb99677,
        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#TT96119"}

@article{bb99678,
        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#TT96120"}

@article{bb99679,
        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#TT96121"}

@article{bb99680,
        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#TT96122"}

@article{bb99681,
        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#TT96123"}

@article{bb99682,
        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#TT96124"}

@article{bb99683,
        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#TT96125"}

@article{bb99684,
        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#TT96126"}

@article{bb99685,
        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#TT96127"}

@article{bb99686,
        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#TT96128"}

@article{bb99687,
        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#TT96129"}

@article{bb99688,
        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#TT96130"}

@article{bb99689,
        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#TT96131"}

@inproceedings{bb99690,
        AUTHOR = "Park, G. and Han, C. and Kim, D. and Yoon, W.",
        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#TT96132"}

@inproceedings{bb99691,
        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#TT96133"}

@inproceedings{bb99692,
        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#TT96134"}

@inproceedings{bb99693,
        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#TT96135"}

@inproceedings{bb99694,
        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#TT96136"}

@inproceedings{bb99695,
        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#TT96137"}

@inproceedings{bb99696,
        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#TT96138"}

@inproceedings{bb99697,
        AUTHOR = "Liu, L. and Tang, J. and Wan, X. and Guo, Z.",
        TITLE = "Generating Diverse and Descriptive Image Captions Using Visual
Paraphrases",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "4239-4248",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96139"}

@inproceedings{bb99698,
        AUTHOR = "Ke, L. and Pei, W. and Li, R. and Shen, X. and Tai, Y.",
        TITLE = "Reflective Decoding Network for Image Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "8887-8896",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96140"}

@inproceedings{bb99699,
        AUTHOR = "Vered, G. and Oren, G. and Atzmon, Y. and Chechik, G.",
        TITLE = "Joint Optimization for Cooperative Image Captioning",
        BOOKTITLE = ICCV19,
        YEAR = "2019",
        PAGES = "8897-8906",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT96141"}

Last update:Jul 28, 2020 at 14:30:08