Ming-Ming Cheng1 Ziming Zhang2 Wen-Yan Lin3 Philip Torr1 1The University of Oxford 2Boston University 3Brookes Vision Group Abstract Training a generic objectness measure to produce a small set of candidate object windows, has been shown to speed up the classical sliding window object detection paradigm. We observe that generic objects with well-defined closed b
![BING: Binarized Normed Gradients for Objectness Estimation at 300fps](https://cdn-ak-scissors.b.st-hatena.com/image/square/d391402ff952b3de28cf2cdd8224dc233ae66ca9/height=288;version=1;width=512/https%3A%2F%2Fi0.wp.com%2Fmmcheng.net%2Fwp-content%2Fuploads%2F2015%2F05%2FBING1.png%3Ffit%3D1000%252C500%26ssl%3D1)