基于语法模型的目标检测Object Detection with Grammar Models |
|
课程网址: | http://videolectures.net/nips2011_girshick_detection/ |
主讲教师: | Ross B. Girshick |
开课单位: | 脸书公司 |
开课时间: | 2012-09-06 |
课程语种: | 英语 |
中文简介: | 组合模型提供了一种优雅的形式主义,用于表示高度可变对象的视觉外观。虽然从理论角度来看,此类模型具有吸引力,但很难证明它们在具有挑战性的数据集上具有性能优势。在这里,我们开发了一个用于人身检测的语法模型,并表明它在Pascal基准测试中优于以前的高性能系统。我们的模型使用可变形部分的层次结构、可变结构和部分可见对象的显式遮挡模型来表示人。为了训练该模型,我们引入了一种新的识别框架,用于从弱标记数据中学习结构化预测模型。 |
课程简介: | Compositional models provide an elegant formalism for representing the visual appearance of highly variable objects. While such models are appealing from a theoretical point of view, it has been difficult to demonstrate that they lead to performance advantages on challenging datasets. Here we develop a grammar model for person detection and show that it outperforms previous high-performance systems on the PASCAL benchmark. Our model represents people using a hierarchy of deformable parts, variable structure and an explicit model of occlusion for partially visible objects. To train the model, we introduce a new discriminative framework for learning structured prediction models from weakly-labeled data. |
关 键 词: | 图像分析; 计算机科学; 机器学习; 模式识别 |
课程来源: | 视频讲座网 |
最后编审: | 2020-01-13:chenxin |
阅读次数: | 30 |