Bibliography (10):

1. VinVL: Revisiting Visual Representations in Vision-Language Models

2. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

3. Attention Is All You Need

4. Microsoft COCO: Common Objects in Context

5. nocaps: novel object captioning at scale

6. Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning

7. Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts

8. Wikipedia Bibliography:

   1. Alt attribute

   2. N-gram

   3. Cross-entropy