2021年4月9日
Human-like Controllable Image Captioning with Verb-specific Semantic Roles(具有动词语义角色的类人可控图像字幕生成)
摘要： 前人的缺陷： CIC works mainly focus on (1)subjective control signals,(2)objective control signals or (1) Content-controlled (2) Structure controlled。 almost 阅读全文
posted @ 2021-04-09 00:21 思凡念真 阅读(457) 评论(0) 推荐(0)