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 1408.6418cs.CVcs.CLcs.IR
收藏

视频输入句子输出

Video In Sentences Out

Purdue University(普渡大学);University of Toronto(多伦多大学);University of South Carolina(南卡罗来纳大学)
Andrei Barbu, Alexander Bridge, Zachary Burchill, Dan Coroian, Sven Dickinson, Sanja Fidler, Aaron Michaux, Sam Mussman, Siddharth Narayanaswamy, Dhaval Salvi, … 展开作者

Andrei Barbu, Alexander Bridge, Zachary Burchill, Dan Coroian, Sven Dickinson, Sanja Fidler, Aaron Michaux, Sam Mussman, Siddharth Narayanaswamy, Dhaval Salvi, Lara Schmidt, Jiangnan Shangguan, Jeffrey Mark Siskind, Jarrell Waggoner, Song Wang, Jinlian Wei, Yifan Yin, Zhiqi Zhang

摘要:

我们提出了一个系统,产生视频的基本描述:谁对谁做了什么,他们在哪里和如何做到这一点。动作类被渲染为动词,参与者对象作为名词短语,这些对象的属性作为形容词修饰语在这些名词短语,这些参与者之间的空间关系作为介词短语,和事件的特点作为介词短语修饰语和状语修饰语。提取渲染这些语言实体所需的信息需要一种事件识别方法,该方法可以恢复对象轨迹、轨迹到角色的分配以及改变身体姿势。

英文摘要:

We present a system that produces sentential descriptions of video: who did what to whom, and where and how they did it. Action class is rendered as a verb, participant objects as noun phrases, properties of those objects as adjectival modifiers in those noun phrases, spatial relations between those participants as prepositional phrases, and characteristics of the event as prepositional-phrase adjuncts and adverbial modifiers. Extracting the information needed to render these linguistic entities requires an approach to event recognition that recovers object tracks, the trackto-role assignments, and changing body posture.

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。

↑