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 1605.09757cs.IRcs.AIcs.CV
收藏

本体驱动的视觉概念检测器学习

Towards ontology driven learning of visual concept detectors

Dextro Robotics, Inc.(德克斯特罗机器人公司)

Sanchit Arora, Chuck Cho, Paul Fitzpatrick, Francois Scharffe

摘要:

近年来,深度学习技术的成熟使得视觉媒体中的对象识别取得了突破。虽然对于一些特定的基准,神经技术似乎匹配,如果不是优于人类的判断,挑战仍然是开放的检测任意视频中的任意概念。在本文中,我们提出了一个系统,结合了神经技术,一个大规模的视觉概念本体,和一个主动学习循环,提供在飞行模型学习的任意概念。我们给出了一个概述的系统作为一个整体,并专注于本体论的核心作用,指导和引导新概念的学习,提高召回的概念检测,并在用户端,提供语义搜索上的注释视频库。

英文摘要:

The maturity of deep learning techniques has led in recent years to a breakthrough in object recognition in visual media. While for some specific benchmarks, neural techniques seem to match if not outperform human judgement, challenges are still open for detecting arbitrary concepts in arbitrary videos. In this paper, we propose a system that combines neural techniques, a large scale visual concepts ontology, and an active learning loop, to provide on the fly model learning of arbitrary concepts. We give an overview of the system as a whole, and focus on the central role of the ontology for guiding and bootstrapping the learning of new concepts, improving the recall of concept detection, and, on the user end, providing semantic search on a library of annotated videos.

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。

↑