@article{bb94800,
        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#TT91336"}

@inproceedings{bb94801,
        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#TT91337"}

@article{bb94802,
        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#TT91338"}

@article{bb94803,
        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#TT91339"}

@article{bb94804,
        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#TT91340"}

@article{bb94805,
        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#TT91341"}

@article{bb94806,
        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#TT91342"}

@article{bb94807,
        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#TT91343"}

@article{bb94808,
        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#TT91344"}

@article{bb94809,
        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#TT91345"}

@article{bb94810,
        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#TT91346"}

@article{bb94811,
        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#TT91346"}

@article{bb94812,
        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#TT91347"}

@article{bb94813,
        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#TT91348"}

@article{bb94814,
        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#TT91349"}

@article{bb94815,
        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#TT91350"}

@article{bb94816,
        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#TT91351"}

@article{bb94817,
        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#TT91352"}

@article{bb94818,
        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#TT91353"}

@article{bb94819,
        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#TT91354"}

@article{bb94820,
        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#TT91355"}

@article{bb94821,
        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#TT91356"}

@article{bb94822,
        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#TT91357"}

@article{bb94823,
        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#TT91358"}

@article{bb94824,
        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#TT91359"}

@article{bb94825,
        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#TT91360"}

@article{bb94826,
        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#TT91361"}

@article{bb94827,
        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#TT91362"}

@article{bb94828,
        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#TT91363"}

@article{bb94829,
        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#TT91364"}

@article{bb94830,
        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#TT91365"}

@inproceedings{bb94831,
        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#TT91366"}

@article{bb94832,
        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#TT91367"}

@article{bb94833,
        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#TT91368"}

@article{bb94834,
        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#TT91369"}

@article{bb94835,
        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#TT91370"}

@article{bb94836,
        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#TT91371"}

@article{bb94837,
        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#TT91372"}

@article{bb94838,
        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#TT91373"}

@article{bb94839,
        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#TT91374"}

@article{bb94840,
        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#TT91375"}

@article{bb94841,
        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#TT91376"}

@article{bb94842,
        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#TT91377"}

@article{bb94843,
        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#TT91378"}

@article{bb94844,
        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#TT91379"}

@article{bb94845,
        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#TT91380"}

@inproceedings{bb94846,
        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#TT91381"}

@article{bb94847,
        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#TT91382"}

@article{bb94848,
        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#TT91383"}

@inproceedings{bb94849,
        AUTHOR = "Wang, Q.Z. and Chan, A.B.",
        TITLE = "Gated Hierarchical Attention for Image Captioning",
        BOOKTITLE = ACCV18,
        YEAR = "2018",
        PAGES = "IV:21-37",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91384"}

@inproceedings{bb94850,
        AUTHOR = "Wang, W. and Chen, Z.H. and Hu, H.F.",
        TITLE = "Multivariate Attention Network for Image Captioning",
        BOOKTITLE = ACCV18,
        YEAR = "2018",
        PAGES = "VI:587-602",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91385"}

@inproceedings{bb94851,
        AUTHOR = "Ghanimifard, M. and Dobnik, S.",
        TITLE = "Knowing When to Look for What and Where: Evaluating Generation of
Spatial Descriptions with Adaptive Attention",
        BOOKTITLE = VL18,
        YEAR = "2018",
        PAGES = "IV:153-161",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91386"}

@inproceedings{bb94852,
        AUTHOR = "Kim, B. and Lee, Y.H. and Jung, H. and Cho, C.",
        TITLE = "Distinctive-Attribute Extraction for Image Captioning",
        BOOKTITLE = VL18,
        YEAR = "2018",
        PAGES = "IV:133-144",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91387"}

@inproceedings{bb94853,
        AUTHOR = "Tanti, M. and Gatt, A. and Muscat, A.",
        TITLE = "Pre-gen Metrics: Predicting Caption Quality Metrics Without Generating
Captions",
        BOOKTITLE = VL18,
        YEAR = "2018",
        PAGES = "IV:114-123",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91388"}

@inproceedings{bb94854,
        AUTHOR = "Tanti, M. and Gatt, A. and Camilleri, K.P.",
        TITLE = "Quantifying the Amount of Visual Information Used by Neural Caption
Generators",
        BOOKTITLE = VL18,
        YEAR = "2018",
        PAGES = "IV:124-132",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91389"}

@inproceedings{bb94855,
        AUTHOR = "Ren, L. and Qi, G. and Hua, K.",
        TITLE = "Improving Diversity of Image Captioning Through Variational
Autoencoders and Adversarial Learning",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "263-272",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91390"}

@inproceedings{bb94856,
        AUTHOR = "Zhou, Y. and Sun, Y. and Honavar, V.",
        TITLE = "Improving Image Captioning by Leveraging Knowledge Graphs",
        BOOKTITLE = WACV19,
        YEAR = "2019",
        PAGES = "283-293",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91391"}

@inproceedings{bb94857,
        AUTHOR = "Rapson, C.J. and Seet, B. and Naeem, M.A. and Lee, J.E. and Al Sarayreh, M. and Klette, R.",
        TITLE = "Reducing the Pain: A Novel Tool for Efficient Ground-Truth Labelling
in Images",
        BOOKTITLE = IVCNZ18,
        YEAR = "2018",
        PAGES = "1-9",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91392"}

@inproceedings{bb94858,
        AUTHOR = "Lu, J.S. and Yang, J.W. and Batra, D. and Parikh, D.",
        TITLE = "Neural Baby Talk",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "7219-7228",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91393"}

@inproceedings{bb94859,
        AUTHOR = "Wu, B.Y. and Chen, W.D. and Sun, P. and Liu, W. and Ghanem, B. and Lyu, S.W.",
        TITLE = "Tagging Like Humans: Diverse and Distinct Image Annotation",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "7967-7975",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91394"}

@inproceedings{bb94860,
        AUTHOR = "Wu, X.J. and Zhang, L. and Li, F.Z. and Wang, B.J.",
        TITLE = "A Novel Model for Multi-label Image Annotation",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "1953-1958",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91395"}

@inproceedings{bb94861,
        AUTHOR = "Jiu, M. and Sahbi, H. and Qi, L.",
        TITLE = "Deep Context Networks for Image Annotation",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "2422-2427",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91396"}

@inproceedings{bb94862,
        AUTHOR = "Khademi, M. and Schulte, O.",
        TITLE = "Image Caption Generation with Hierarchical Contextual Visual Spatial
Attention",
        BOOKTITLE = Cognitive18,
        YEAR = "2018",
        PAGES = "2024-20248",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91397"}

@inproceedings{bb94863,
        AUTHOR = "Yan, S. and Wu, F. and Smith, J.S. and Lu, W. and Zhang, B.",
        TITLE = "Image Captioning using Adversarial Networks and Reinforcement
Learning",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "248-253",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91398"}

@inproceedings{bb94864,
        AUTHOR = "Wang, F. and Gong, X. and Huang, L.",
        TITLE = "Time-Dependent Pre-attention Model for Image Captioning",
        BOOKTITLE = ICPR18,
        YEAR = "2018",
        PAGES = "3297-3302",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91399"}

@inproceedings{bb94865,
        AUTHOR = "Luo, R. and Shakhnarovich, G. and Cohen, S. and Price, B.",
        TITLE = "Discriminability Objective for Training Descriptive Captions",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "6964-6974",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91400"}

@inproceedings{bb94866,
        AUTHOR = "Cui, Y. and Yang, G. and Veit, A. and Huang, X. and Belongie, S.",
        TITLE = "Learning to Evaluate Image Captioning",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "5804-5812",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91401"}

@inproceedings{bb94867,
        AUTHOR = "Aneja, J. and Deshpande, A. and Schwing, A.G.",
        TITLE = "Convolutional Image Captioning",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "5561-5570",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91402"}

@inproceedings{bb94868,
        AUTHOR = "Chen, F. and Ji, R. and Sun, X. and Wu, Y. and Su, J.",
        TITLE = "GroupCap: Group-Based Image Captioning with Structured Relevance and
Diversity Constraints",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "1345-1353",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91403"}

@inproceedings{bb94869,
        AUTHOR = "Chen, X. and Ma, L. and Jiang, W. and Yao, J. and Liu, W.",
        TITLE = "Regularizing RNNs for Caption Generation by Reconstructing the Past
with the Present",
        BOOKTITLE = CVPR18,
        YEAR = "2018",
        PAGES = "7995-8003",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91404"}

@inproceedings{bb94870,
        AUTHOR = "Yao, T. and Pan, Y.W. and Li, Y. and Mei, T.",
        TITLE = "Exploring Visual Relationship for Image Captioning",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XIV: 711-727",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91405"}

@inproceedings{bb94871,
        AUTHOR = "Shah, S.A.A.",
        TITLE = "NNEval: Neural Network Based Evaluation Metric for Image Captioning",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VIII: 39-55",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91406"}

@inproceedings{bb94872,
        AUTHOR = "Jiang, W.H. and Ma, L. and Jiang, Y.G. and Liu, W. and Zhang, T.",
        TITLE = "Recurrent Fusion Network for Image Captioning",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "II: 510-526",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91407"}

@inproceedings{bb94873,
        AUTHOR = "Chatterjee, M. and Schwing, A.G.",
        TITLE = "Diverse and Coherent Paragraph Generation from Images",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "II: 747-763",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91408"}

@inproceedings{bb94874,
        AUTHOR = "Chen, S. and Zhao, Q.",
        TITLE = "Boosted Attention: Leveraging Human Attention for Image Captioning",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XI: 72-88",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91409"}

@inproceedings{bb94875,
        AUTHOR = "Dai, B. and Ye, D. and Lin, D.",
        TITLE = "Rethinking the Form of Latent States in Image Captioning",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "VI: 294-310",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91410"}

@inproceedings{bb94876,
        AUTHOR = "Liu, X. and Li, H.S. and Shao, J. and Chen, D.P. and Wang, X.G.",
        TITLE = "Show, Tell and Discriminate:
Image Captioning by Self-retrieval with Partially Labeled Data",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XV: 353-369",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91411"}

@inproceedings{bb94877,
        AUTHOR = "Fang, F. and Wang, H. and Tang, P.",
        TITLE = "Image Captioning with Word Level Attention",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "1278-1282",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91412"}

@inproceedings{bb94878,
        AUTHOR = "Zhu, Z. and Xue, Z. and Yuan, Z.",
        TITLE = "Topic-Guided Attention for Image Captioning",
        BOOKTITLE = ICIP18,
        YEAR = "2018",
        PAGES = "2615-2619",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91413"}

@inproceedings{bb94879,
        AUTHOR = "Gomez Garay, A. and Raducanu, B. and Salas, J.",
        TITLE = "Dense Captioning of Natural Scenes in Spanish",
        BOOKTITLE = MCPR18,
        YEAR = "2018",
        PAGES = "145-154",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91414"}

@inproceedings{bb94880,
        AUTHOR = "Yao, L. and Ballas, N. and Cho, K. and Smith, J. and Bengio, Y.",
        TITLE = "Oracle Performance for Visual Captioning",
        BOOKTITLE = BMVC16,
        YEAR = "2016",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91415"}

@inproceedings{bb94881,
        AUTHOR = "Khatchatoorian, A.G. and Jamzad, M.",
        TITLE = "Post Rectifying Methods to Improve the Accuracy of Image Annotation",
        BOOKTITLE = DICTA17,
        YEAR = "2017",
        PAGES = "1-7",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91416"}

@inproceedings{bb94882,
        AUTHOR = "Dong, H. and Zhang, J.Q. and McIlwraith, D. and Guo, Y.",
        TITLE = "I2T2I: Learning text to image synthesis with textual data
augmentation",
        BOOKTITLE = ICIP17,
        YEAR = "2017",
        PAGES = "2015-2019",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91417"}

@inproceedings{bb94883,
        AUTHOR = "Pellegrin, L. and Escalante, H.J. and Montes y Gomez, M. and Villegas, M. and Gonzalez, F.A.",
        TITLE = "A Flexible Framework for the Evaluation of Unsupervised Image
Annotation",
        BOOKTITLE = CIARP17,
        YEAR = "2017",
        PAGES = "508-516",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91418"}

@inproceedings{bb94884,
        AUTHOR = "Jia, Y.H. and Bai, L. and Wang, P. and Guo, J.L. and Xie, Y.X.",
        TITLE = "Deep Convolutional Neural Network for Correlating Images and Sentences",
        BOOKTITLE = MMMod18,
        YEAR = "2018",
        PAGES = "I:154-165",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91419"}

@inproceedings{bb94885,
        AUTHOR = "Liu, J.Y. and Wang, L. and Yang, M.H.",
        TITLE = "Referring Expression Generation and Comprehension via Attributes",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "4866-4874",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91420"}

@inproceedings{bb94886,
        AUTHOR = "Dai, B. and Fidler, S. and Urtasun, R. and Lin, D.",
        TITLE = "Towards Diverse and Natural Image Descriptions via a Conditional GAN",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "2989-2998",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91421"}

@inproceedings{bb94887,
        AUTHOR = "Niu, Z.X. and Zhou, M. and Wang, L. and Gao, X. and Hua, G.",
        TITLE = "Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1899-1907",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91422"}

@inproceedings{bb94888,
        AUTHOR = "Liang, X. and Hu, Z. and Zhang, H. and Gan, C. and Xing, E.P.",
        TITLE = "Recurrent Topic-Transition GAN for Visual Paragraph Generation",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "3382-3391",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91423"}

@inproceedings{bb94889,
        AUTHOR = "Shetty, R. and Rohrbach, M. and Hendricks, L.A. and Fritz, M. and Schiele, B.",
        TITLE = "Speaking the Same Language:
Matching Machine to Human Captions by Adversarial Training",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "4155-4164",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91424"}

@inproceedings{bb94890,
        AUTHOR = "Liu, S. and Zhu, Z. and Ye, N. and Guadarrama, S. and Murphy, K.",
        TITLE = "Improved Image Captioning via Policy Gradient optimization of SPIDEr",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "873-881",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91425"}

@inproceedings{bb94891,
        AUTHOR = "Gu, J.X. and Joty, S. and Cai, J.F. and Wang, G.",
        TITLE = "Unpaired Image Captioning by Language Pivoting",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "I: 519-535",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91426"}

@inproceedings{bb94892,
        AUTHOR = "Gu, J.X. and Wang, G. and Cai, J.F. and Chen, T.",
        TITLE = "An Empirical Study of Language CNN for Image Captioning",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1231-1240",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91427"}

@inproceedings{bb94893,
        AUTHOR = "Pedersoli, M. and Lucas, T. and Schmid, C. and Verbeek, J.",
        TITLE = "Areas of Attention for Image Captioning",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1251-1259",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91428"}

@inproceedings{bb94894,
        AUTHOR = "Li, Y. and Ouyang, W. and Zhou, B. and Wang, K. and Wang, X.",
        TITLE = "Scene Graph Generation from Objects, Phrases and Region Captions",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1270-1279",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91429"}

@inproceedings{bb94895,
        AUTHOR = "Zhang, Z. and Wu, J.J. and Li, Q. and Huang, Z. and Traer, J. and McDermott, J.H. and Tenenbaum, J.B. and Freeman, W.T.",
        TITLE = "Generative Modeling of Audible Shapes for Object Perception",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "1260-1269",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91430"}

@inproceedings{bb94896,
        AUTHOR = "Liu, Z.J. and Freeman, W.T. and Tenenbaum, J.B. and Wu, J.J.",
        TITLE = "Physical Primitive Decomposition",
        BOOKTITLE = ECCV18,
        YEAR = "2018",
        PAGES = "XII: 3-20",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91431"}

@inproceedings{bb94897,
        AUTHOR = "Wu, J.J. and Lim, J. and Zhang, H.Y. and Tenenbaum, J.B. and Freeman, W.T.",
        TITLE = "Physics 101: Learning Physical Object Properties from Unlabeled Videos",
        BOOKTITLE = BMVC16,
        YEAR = "2016",
        PAGES = "xx-yy",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91432"}

@inproceedings{bb94898,
        AUTHOR = "Tavakoliy, H.R. and Shetty, R. and Borji, A. and Laaksonen, J.",
        TITLE = "Paying Attention to Descriptions Generated by Image Captioning Models",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "2506-2515",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91433"}

@inproceedings{bb94899,
        AUTHOR = "Chen, T.H. and Liao, Y.H. and Chuang, C.Y. and Hsu, W.T. and Fu, J. and Sun, M.",
        TITLE = "Show, Adapt and Tell:
Adversarial Training of Cross-Domain Image Captioner",
        BOOKTITLE = ICCV17,
        YEAR = "2017",
        PAGES = "521-530",
        BIBSOURCE = "http://www.visionbib.com/bibliography/match607ic1.html#TT91434"}

Last update:Jul 14, 2019 at 21:53:00