搜索结果: 1-10 共查到“计算机科学技术 Metric”相关记录10条 . 查询时间(0.105 秒)
Metric selection in fast dual forward backward splitting
The gradient data optimization index space
2015/8/7
The performance of fast forward-backward splitting, or equivalently fast proximal gradient methods, is susceptible to conditioning of the optimization problem data. This conditioning is related to a m...
Robustness and Generalization for Metric Learning
Metric learning Algorithmic robustness Generalization bounds
2012/11/23
Metric learning has attracted a lot of interest over the last decade, but little work has been done about the generalization ability of such methods. In this paper, we address this issue by proposing ...
A New Metric for Measuring Relatedness of ScientificPapers Based on Non-Textual Features
Relatedness Measure Citation Recommendation Digital Library
2013/1/28
Measuring relatedness of two papers is an issue which arises in many applications, e.g., recommendation, clustering and classification of papers. In this paper, a digital library is modeled as a direc...
Margin Emphasized Metric Learning and Its Application to Gabor Feature Based Face Recognition
face verification metric learning margin Gabor Labeled Faces in Wild
2013/7/24
In addressing side information based face recognition scenario, a new Margin Emphasized Metric Learning (MEML) method is proposed. As an improvement of previous metric learning, MEML defines a new obj...
Efficient lp-Norm Multiple Feature Metric Learning for Image Categorization
Algorithms Performance Experimentation
2013/7/24
Previous metric learning approaches are only able to learn the metric based on single concatenated multivariate feature representation. However, for many real world problems with multiple feature repr...
A metric for method complexity is proposed as an aid to choosing between competing methods, as well as in validating the effects of method integration or the products of method engineering work. It is...
Coupled Metric Learning for Face Recognition with Degraded Images
Coupled Metric Learning Face Recognition Degraded Images
2013/7/16
Real-world face recognition systems are sometimes confronted with degraded face images, e.g., low-resolution, blurred, and noisy ones. Traditional two-step methods have limited performance, due to the...
A NO-REFERENCE PERCEPTUAL BLUR METRIC USING HISTOGRAM OF GRADIENT PROFILE SHARPNESS
image quality assessment blur metric gradient profile just noticeable distortion
2013/7/16
No-reference measurement of blurring artifacts in images is a challenging problem in image quality assessment field. One of the difficulties is that the inherently blurry regions in some natural image...
Coupled metric learning for face recognition with degraded images
Coupled metric learning face recognition
2010/12/20
Real-world face recognition systems are sometimes confronted with degraded face images, e.g., low-resolution, blurred, and noisy ones. Traditional two-step methods have limited performance, due to the...
A No-Reference Blocking Artifacts Metric Using Selective Gradient and Plainness Measures
Blocking artifacts metric gradient measures plainness measures
2013/7/17
This paper presents a novel no-reference blocking artifacts metric using selective gradient and plainness (BAM_SGP) measures for DCT-coded images. A boundary selection criterion is introduced to dist...