你即將離開本站

並前往https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123470732.pdf

a Dataset for Image Captioning with Reading Comprehension

We find the COCO Captioning dataset [9] not suitable as only an estimated. 2.7% of its captions mention OCR tokens present in the image, and in total.

確定！ 回上一頁

查詢 「ocr dataset」的人也找了：

  1. OCR dataset
    2.
  2. NIST dataset
    3.
  3. Born digital dataset
    4.
  4. MNIST dataset
    5.
  5. IAM dataset
    6.
  6. OCR deep learning
    7.
  7. Alphabet dataset
    8.
  8. Neocr dataset
    9.