Loading [MathJax]/extensions/TeX/ieeemacros.js
sandals Festival Boho sandal Foot Beach Barefoot clothing Soleless wedding Owl sandals jewelry jewelry barefoot sandals Bottomless d646qPw sandals Festival Boho sandal Foot Beach Barefoot clothing Soleless wedding Owl sandals jewelry jewelry barefoot sandals Bottomless d646qPw sandals Festival Boho sandal Foot Beach Barefoot clothing Soleless wedding Owl sandals jewelry jewelry barefoot sandals Bottomless d646qPw
Womens Kids Gift Hockey Trainers Mens White Shoes Running Collector Vegas Sneakers Black Sizes Gift Custom Golden Knights zaqxEPT
Scheduled System Maintenance
On Friday, September 7, IEEE Xplore will undergo scheduled maintenance. Users may experience intermittent access from 2:30–4:30 pm ET (6:30–8:30 UTC).
The site may be unavailable for approximately 60 minutes during this period.
We apologize for any inconvenience.
Advertisement

sandals Festival Boho sandal Foot Beach Barefoot clothing Soleless wedding Owl sandals jewelry jewelry barefoot sandals Bottomless d646qPw

Abstract: Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights:... View more
Abstract:
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.
Date of Conference: 23-28 June 2014
Date Added to IEEE Xplore: 25 September 2014
Electronic ISBN: 978-1-4799-5118-5
ISSN Information:
INSPEC Accession Number: 14632381
Publisher: IEEE
Conference Location: Columbus, OH, USA
Advertisement
Contents
Contents

1. Introduction

Features matter. The last decade of progress on various visual recognition tasks has been based considerably on the use of SIFT [27] and HOG [7]. But if we look at performance on the canonical visual recognition task, PASCAL VOC object detection [13], it is generally acknowledged that progress has been slow during 2010–2012, with small gains obtained by building ensemble systems and employing minor variants of successful methods.

Bottomless jewelry sandals jewelry clothing Beach Owl Festival Barefoot sandal sandals Boho sandals barefoot Soleless Foot wedding
Advertisement
Advertisement