Seo PH, Sharma P, Levinboim T, Han B, Soricut R. Reinforcing an Image Caption Generator Using Off-Line Human Feedback. AAAI [Internet]. 2020Apr.3 [cited 2024Sep.22];34(03):2693-700. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/5655