Learning and transferring movie styles

Karteek ALAHARI,Joseph Redmon,Santosh Divvala,Ross Girshick, Ali Farhadi

semanticscholar(2017)

引用 0|浏览10
暂无评分
摘要
There is currently a lot of interest in analyzing large movie databases to automatically extract film style and aesthetics [1,2]. This analysis has, however, been largely limited to identifying the duration, size, color and motion of movie shots. While these low-level details are pertinent, they do not provide a high-level understanding of cinematography, such as identifying the inherent style in a movie. Ultimately, they are unable to answer challenging questions such as, can we identify the author of a movie clip? Can we generative movie shots in the style of a given director or cinematographer ? can we generate shot sequences on the style of a given director or film editor ?
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要