{
    "ok": true,
    "doi": "10.46243/jst.2019.v4.i06",
    "references_in_record": 15,
    "not_read": [],
    "own_doi": [],
    "total": 11,
    "page": 1,
    "pages": 1,
    "per_page": 20,
    "items": [
        {
            "position": 2,
            "key": "ref2",
            "doi": "10.1109/iccv.2015.279",
            "doi_url": "https://doi.org/10.1109/iccv.2015.279",
            "unstructured": "Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C. Lawrence Zitnick, and Devi Parikh. VQA: Visual Question Answering. In International Conference on Computer Vision (ICCV), 2015",
            "held": false
        },
        {
            "position": 4,
            "key": "ref4",
            "doi": "10.1109/iccv.2001.937654",
            "doi_url": "https://doi.org/10.1109/iccv.2001.937654",
            "unstructured": "K. Barnard and D. Forsyth. Learning the semantics of words and pictures. In ICCV, volume 2, pages 408–415. IEEE, 2001",
            "held": false
        },
        {
            "position": 5,
            "key": "ref5",
            "doi": "10.1145/1631272.1631292",
            "doi_url": "https://doi.org/10.1145/1631272.1631292",
            "unstructured": "L. Cao, J. Yu, J. Luo, and T. Huang. Enhancing semantic and geographic annotation of web images via logistic canonical co rrelation regression. In ACM International Conference on Multimedia, pages 125–134. ACM, 2009",
            "held": false
        },
        {
            "position": 6,
            "key": "ref6",
            "doi": "10.3115/v1/w14-3102",
            "doi_url": "https://doi.org/10.3115/v1/w14-3102",
            "unstructured": "A. Chang, M. Savva, and C. Manning. Interactive learning of spatial knowledge for text to 3d scene generation. Sponsor: I dibon, page 14, 2014",
            "held": false
        },
        {
            "position": 7,
            "key": "ref7",
            "doi": "10.1109/cvpr.2011.5995610",
            "doi_url": "https://doi.org/10.1109/cvpr.2011.5995610",
            "unstructured": "D. Chen, G. Baatz, K. Köser, S. Tsai, R. Vedantham, T. Pylvä, K. Roimela, X. Chen, J. Bach, M. Pollefeys, et al. City-scale landmark identiﬁcation on mobile devices. In CVPR, pages 737–744. IEEE, 2011",
            "held": false
        },
        {
            "position": 8,
            "key": "ref8",
            "doi": "10.1109/cvpr.2015.7298856",
            "doi_url": "https://doi.org/10.1109/cvpr.2015.7298856",
            "unstructured": "X. Chen and C. Zitnick. Mind’s eye: A recurrent visual representation for image caption generation. In CVPR, 2015",
            "held": false
        },
        {
            "position": 9,
            "key": "ref9",
            "doi": "10.1007/978-3-642-28997-2_28",
            "doi_url": "https://doi.org/10.1007/978-3-642-28997-2_28",
            "unstructured": "F. Coelho and C. Ribeiro. Image abstraction in crossmedia retrieval for text illustration. Lecture Notes in Computer Scie nce, 7224 LNCS:329–339, 2012",
            "held": false
        },
        {
            "position": 11,
            "key": "ref11",
            "doi": "10.1145/383259.383316",
            "doi_url": "https://doi.org/10.1145/383259.383316",
            "unstructured": "B. Coyne and R. Sproat. Wordseye: an automatic text-to-scene conversion system. In Conference on Computer Graphics and Interactive Techniques, pages 487–496. ACM, 2001. [12] D. Crandall, L. Backstrom, D. Huttenlocher, and J. Kleinberg. Mapping the world’s photos. In International Conference on World Wide Web, pages 761–770. ACM, 2009",
            "held": false
        },
        {
            "position": 12,
            "key": "ref12",
            "doi": "10.1109/cvpr.2009.5206848",
            "doi_url": "https://doi.org/10.1109/cvpr.2009.5206848",
            "unstructured": "J. Deng, W. Dong, R. Socher, K. Li, K. Li, and L. Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR, pages 248–255, 2009",
            "held": false
        },
        {
            "position": 13,
            "key": "ref13",
            "doi": "10.1007/s11263-009-0275-4",
            "doi_url": "https://doi.org/10.1007/s11263-009-0275-4",
            "unstructured": "M. Everingham, L. Van Gool, C. Williams, J. Winn, and A. Zisserman. The pascal visual object classes (voc) challenge. In ternational journal of computer vision, 88(2):303–338, 2010. [19] H. Fang, S. Gupta, F. Iandola, R. Srivastava, L. Deng, P. Dollar, J. Gao, X. He, M. Mitchell, J. Platt, C. Zitnick, and G. Zweig. From captions to visual concepts and back. In CVPR, 2015. [20] H. Fang, S. Gupt a, F. Iandola, R. Srivastava, L. Deng, and P. Dollár others. From captions to visual concepts and back.",
            "held": false
        },
        {
            "position": 14,
            "key": "ref14",
            "doi": "10.1007/978-3-642-15561-1_2",
            "doi_url": "https://doi.org/10.1007/978-3-642-15561-1_2",
            "unstructured": "A. Farhadi, M. Hejrati, M. Sadeghi, P. Young, C. Rashtchian, J. Hockenmaier, and D. Forsyth. Every picture tells a story : Generating sentences from images. In ECCV, pages 15–29. Springer, 2010",
            "held": false
        }
    ]
}