{
    "ok": true,
    "doi": "10.46243/jst.2024.v9.i4.pp1-10",
    "references_in_record": 13,
    "not_read": [],
    "own_doi": [],
    "total": 8,
    "page": 1,
    "pages": 1,
    "per_page": 20,
    "items": [
        {
            "position": 2,
            "key": "ref2",
            "doi": "10.1109/cvpr42600.2020.01213",
            "doi_url": "https://doi.org/10.1109/cvpr42600.2020.01213",
            "unstructured": "Chen, W., Li, H., & Zhang, T, “Towards Accurate Scene Text Recognition with Semantic Reasoning and Dynamic Graph Attention Networks,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Volume 7, pp. 210-225, 2022",
            "held": false
        },
        {
            "position": 3,
            "key": "ref3",
            "doi": "10.1109/cvprw59228.2023.00594",
            "doi_url": "https://doi.org/10.1109/cvprw59228.2023.00594",
            "unstructured": "Luo, L., Wu, Y., & Zhang, C, “Real-time Video Text Detection and Recognition with Maskguided Fusion,” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, volume 4, pp. 180-195, 2023",
            "held": false
        },
        {
            "position": 5,
            "key": "ref5",
            "doi": "10.1109/icme.2015.7177461",
            "doi_url": "https://doi.org/10.1109/icme.2015.7177461",
            "unstructured": "Wang, Z., Jin, L., & Li, W, “Deep Learning-based Real-time Text Recognition in Videos using Tesseract,” In Proceedings of the International Conference on Multimedia and Expo (ICME), volume 3, pp. 80-95, 2023",
            "held": false
        },
        {
            "position": 9,
            "key": "ref9",
            "doi": "10.1109/tpami.2016.2577031",
            "doi_url": "https://doi.org/10.1109/tpami.2016.2577031",
            "unstructured": "Ren, S., He, K., Girshick, R., Sun, J. “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.” In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), volume 28, pp. 91-99, 2015",
            "held": false
        },
        {
            "position": 10,
            "key": "ref10",
            "doi": "10.1109/iccv.2017.322",
            "doi_url": "https://doi.org/10.1109/iccv.2017.322",
            "unstructured": "He, K., Gkioxari, G., Dollar, P., Girshick, R. “Mask R-CNN.” In Proceedings of the IEEE International Conference on Computer Vision (ICCV), volume 2, pp. 2980-2988, 2017",
            "held": false
        },
        {
            "position": 11,
            "key": "ref11",
            "doi": "10.1609/aaai.v31i1.11196",
            "doi_url": "https://doi.org/10.1609/aaai.v31i1.11196",
            "unstructured": "Liao, M., Shi, B., Bai, X., Wang, X., Liu, W. “TextBoxes: A Fast Text Detector with a Single Deep Neural Network.” In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), volume 2, pp. 4165-4172, 2017",
            "held": false
        },
        {
            "position": 12,
            "key": "ref12",
            "doi": "10.1109/cvpr.2017.283",
            "doi_url": "https://doi.org/10.1109/cvpr.2017.283",
            "unstructured": "Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., Liang, J. “EAST: An Efficient and Accurate Scene Text Detector.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), volume 3, pp. 2642- 2651, 2017",
            "held": false
        },
        {
            "position": 13,
            "key": "ref13",
            "doi": "10.1109/tpami.2016.2646371",
            "doi_url": "https://doi.org/10.1109/tpami.2016.2646371",
            "unstructured": "Shi, B., Bai, X., Yao, C. “An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition.” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), volume 39, issue 11, pp. 2298-2304, 2017",
            "held": false
        }
    ]
}