arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1106.4572cs.AIcs.LG
收藏

时间事件的具体到一般学习及其在从视频学习事件定义中的应用

Specific-to-General Learning for Temporal Events with Application to Learning Event Definitions from Video

Purdue University(普渡大学);School of Electrical and Computer Engineering(电气与计算机工程学院)

A. Fern, R. Givan, J. M. Siskind

摘要:

我们开发,分析和评估一种新的,监督,具体到一般的学习者一个简单的时间逻辑,并使用由此产生的算法来学习视频序列的视觉事件定义。首先,我们介绍了一个简单的,命题,时间,事件描述语言AMA是足够的表达,以代表许多事件,但足够的限制,以支持学习。然后,我们给出算法,以及较低和较高的复杂性界限,AMA公式的包容和推广问题。在此基础上,提出了一种基于正例的从具体到一般的学习方法。我们还提出了一个多项式时间可计算的“语法”包容测试,它隐含了语义包容,但不等价于语义包容。一个基于语法包容的泛化算法可以用来代替语义泛化,以提高所得到的学习算法的渐近复杂度。最后,我们将此算法的任务,学习关系事件的定义,从视频和显示,它产生的定义是有竞争力的手编码的。

英文摘要:

We develop, analyze, and evaluate a novel, supervised, specific-to-general learner for a simple temporal logic and use the resulting algorithm to learn visual event definitions from video sequences. First, we introduce a simple, propositional, temporal, event-description language called AMA that is sufficiently expressive to represent many events yet sufficiently restrictive to support learning. We then give algorithms, along with lower and upper complexity bounds, for the subsumption and generalization problems for AMA formulas. We present a positive-examples--only specific-to-general learning method based on these algorithms. We also present a polynomial-time--computable ``syntactic'' subsumption test that implies semantic subsumption without being equivalent to it. A generalization algorithm based on syntactic subsumption can be used in place of semantic generalization to improve the asymptotic complexity of the resulting learning algorithm. Finally, we apply this algorithm to the task of learning relational event definitions from video and show that it yields definitions that are competitive with hand-coded ones.

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。

↑