PPT-BING: Binarized Normed Gradients for Objectness Estimation at 300fps

MingMing Cheng 1 Ziming Zhang 2 WenYan Li 1 Philip H S Torr 1 1 Torr Vision Group Oxford University 2 Boston University 1 Motivation Generic object detection. We observe that generic objects with well de64257ned closed boundary can be discriminated by looking at the norm of gradients with a suitable resizing of their cor responding image windows in to a small 64257xed size Based on this observation and co ,. . The Bang. ,. . and. . The . Boom. The Five-Paragraph Essay. Did you say . FIVE . paragraphs?. Yes. Yes,. I did say that.. But never. fear! It’s easy with the . bing. , the . bang. , and the . Binarized Normed Gradients for Objectness Estimation at 300fps. Ming-Ming Cheng. 1. Ziming Zhang. 2. Wen-Yan Li. 1. Philip H. S. Torr. 1. 1. Torr . Vision Group, Oxford . University . Scene Analysis and . Applications. 报告人：程明明. 南开大学、计算机与控制工程学. 院. http://mmcheng.net/. Contents. Global . contrast based salient region . detection. ,. PAMI 2014. Altaf Gilani. Senior Program Manager. David Robinson. Principal Program Manager. 3-405. Bing as a platform. Deconstructing the Keynote Demo. Maps (. 2D/3D), . Text to Speech, Speech Recognition, Entity . Binarized. Normed Gradients for . Objectness. Estimation at 300fps. CVPR 2014 Oral. Outline. 1. . Introduction. 2.. . Methodology. 2.1 Normed . gradients (NG) and . objectness. 2.2 Learning . objectness. Cheng. 1. Ziming Zhang. 2. Wen-Yan Lin. 3. . Philip H. S. . Torr. 1. 1. Oxford University, . 2. Boston University . 3. Brookes Vision Group. 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 boundary can be discriminated by looking at the norm of gradients. Based on this observation, we propose to use a binarized normed gradients (BING) for efficient objectness estimation. Experiments on the . By . Zhangliliang. Characteristics. No . bbox. . groundtruth. needed while training. HCP infrastructure is robust to noisy. No explicit hypothesis label (reason: use CNN). Pre-train CNN from . ImageNet. Binarized Normed Gradients for Objectness Estimation at 300fps. Ming-Ming Cheng. 1. Ziming Zhang. 2. Wen-Yan Li. 1. Philip H. S. Torr. 1. 1. Torr . Vision Group, Oxford . University . for . Windows Store Apps. Chris Pendleton. Sr. Program Manager, Lead. 3-133. Bing Maps on Windows 8. Bing Maps for JavaScript. Bing Maps for Managed & Native Code. Application Protocol Handling. Licensing. Ming-Ming Cheng . . Ziming. Zhang . . Wen-Yan Lin . . Philip . Torr. The University of Oxford . . Boston University . . Brookes Vision Group. 2014 IEEE Conference on Computer Vision and Pattern Recognition. Ilya . Razenshteyn. . (Microsoft Research Redmond). joint with. Alexandr. . Andoni. ,. Assaf . Naor. ,. Aleksandar . Nikolov. ,. Erik . Waingarten. How to measure distances?. Metric spaces. Normed spaces. Slide . 1. January 2015. Project: IEEE P802.15 Working Group for Wireless Personal Area Networks (WPANs). Submission Title:. . [. mmWave. Wireless . Backhauling for High Rate Mobile Hotspot Network. Applications. 报告人：程明明. 南开大学、计算机与控制工程学. 院. http://mmcheng.net/. Contents. Global . contrast based salient region . detection. ,. PAMI 2014. BING: Binarized Normed Gradients for Objectness Estimation at .