arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1907.07345cs.CVcs.MMeess.IV
收藏

面向数据驱动的自动视频编辑

Towards Data-Driven Automatic Video Editing

Cinema and Photo Research Institute(电影与摄影研究所)

Sergey Podlesnyy

摘要:

自动视频编辑至少涉及以下步骤:从视觉质量和拍摄动作的重要性的角度选择最有价值的镜头;并将镜头切割成简短而连贯的视觉故事,这将是有趣的观看,以纯粹的数据驱动的方式实现。通过ImageNet训练的卷积神经网络提取视觉语义和美学特征,并通过模仿学习算法训练编辑控制器。结果,在测试时,控制器显示出观察从电影杰作的语料库中学习的基本电影摄影编辑规则的迹象。

英文摘要:

Automatic video editing involving at least the steps of selecting the most valuable footage from points of view of visual quality and the importance of action filmed; and cutting the footage into a brief and coherent visual story that would be interesting to watch is implemented in a purely data-driven manner. Visual semantic and aesthetic features are extracted by the ImageNet-trained convolutional neural network, and the editing controller is trained by an imitation learning algorithm. As a result, at test time the controller shows the signs of observing basic cinematography editing rules learned from the corpus of motion pictures masterpieces.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑