Zhang W, Shi H, Guo J, Zhang S, Cai Q, Li J, et al. MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-Based Image Captioning. AAAI [Internet]. 2022 Jun. 28 [cited 2026 May 26];36(3):3335-43. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/20243