arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1605.03324cs.CVcs.ROstat.ML
收藏

基于视频集的无监督语义动作发现

Unsupervised Semantic Action Discovery from Video Collections

Cornell University(康奈尔大学);Stanford University(斯坦福大学);Brain of Things Inc(Brain of Things公司)

Ozan Sener, Amir Roshan Zamir, Chenxia Wu, Silvio Savarese, Ashutosh Saxena

摘要:

人类交流有多种形式,包括语音,文本和教学视频。它通常有一个基本结构,有一个起点,终点,以及它们之间的某些客观步骤。在本文中,我们考虑的教学视频,其中有数以千万计的互联网上。我们提出了一种方法,用于解析视频到这样的语义步骤,在一个无监督的方式。我们的方法是能够提供一个语义的“故事情节”的视频组成的客观步骤。我们在一个联合生成模型中使用视觉和语言线索来实现这一点。我们的方法还可以为每个识别的语义步骤和视频片段提供文本描述。我们评估我们的方法在大量复杂的YouTube视频,并表明我们的方法发现语义正确的指令,各种任务。

英文摘要:

Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet. We propose a method for parsing a video into such semantic steps in an unsupervised way. Our method is capable of providing a semantic "storyline" of the video composed of its objective steps. We accomplish this using both visual and language cues in a joint generative model. Our method can also provide a textual description for each of the identified semantic steps and video segments. We evaluate our method on a large number of complex YouTube videos and show that our method discovers semantically correct instructions for a variety of tasks.

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。

↑