Non-linear metric learning with multiple features for person re-identification

Author(s):  
Jianguo Jiang ◽  
Hao Liu ◽  
Meibin Qi
2020 ◽  
pp. 114193
Author(s):  
Samuel Rocha Silva ◽  
Thales Vieira ◽  
Dimas Martínez ◽  
Afonso Paiva

2020 ◽  
Vol 411 ◽  
pp. 54-66
Author(s):  
Yonghui Xu ◽  
Chunyan Miao ◽  
Yong Liu ◽  
Hengjie Song ◽  
Yi Hu ◽  
...  
Keyword(s):  

2019 ◽  
Vol 11 (5) ◽  
pp. 536 ◽  
Author(s):  
He Sun ◽  
Jinchang Ren ◽  
Huimin Zhao ◽  
Yijun Yan ◽  
Jaime Zabalza ◽  
...  

To improve the performance of the sparse representation classification (SRC), we propose a superpixel-based feature specific sparse representation framework (SPFS-SRC) for spectral-spatial classification of hyperspectral images (HSI) at superpixel level. First, the HSI is divided into different spatial regions, each region is shape- and size-adapted and considered as a superpixel. For each superpixel, it contains a number of pixels with similar spectral characteristic. Since the utilization of multiple features in HSI classification has been proved to be an effective strategy, we have generated both spatial and spectral features for each superpixel. By assuming that all the pixels in a superpixel belongs to one certain class, a kernel SRC is introduced to the classification of HSI. In the SRC framework, we have employed a metric learning strategy to exploit the commonalities of different features. Experimental results on two popular HSI datasets have demonstrated the efficacy of our proposed methodology.


2021 ◽  
Author(s):  
Kathryn Sarullo ◽  
Deanna Barch ◽  
Christopher Smyser ◽  
Cynthia Rogers ◽  
Barbara Warner ◽  
...  

Race is commonly used as a proxy for multiple features including socioeconomic status. It is critical to dissociate these factors, identify mechanisms that impact infant outcomes, such as birthweight, and direct appropriate interventions and shape public policy. Demographic, socioeconomic, and clinical variables were used to model infant birthweight. Non-linear neural networks better model infant birthweight than linear models (R^2=0.172 vs. R^2=0.145, p-value=0.005). In contrast to linear models, non-linear models ranked income, neighborhood disadvantage, and experiences of discrimination higher in importance while modeling birthweight than race. Consistent with extant social science literature, findings suggest race is a linear proxy for non-linear factors. The ability to disentangle and identify the source of effects for socioeconomic status and other social factors that often correlate with race is critical for the ability to appropriately target interventions and public policies designed to improve infant outcomes as well as point out the disparities in these outcomes.


1967 ◽  
Vol 28 ◽  
pp. 105-176
Author(s):  
Robert F. Christy

(Ed. note: The custom in these Symposia has been to have a summary-introductory presentation which lasts about 1 to 1.5 hours, during which discussion from the floor is minor and usually directed at technical clarification. The remainder of the session is then devoted to discussion of the whole subject, oriented around the summary-introduction. The preceding session, I-A, at Nice, followed this pattern. Christy suggested that we might experiment in his presentation with a much more informal approach, allowing considerable discussion of the points raised in the summary-introduction during its presentation, with perhaps the entire morning spent in this way, reserving the afternoon session for discussion only. At Varenna, in the Fourth Symposium, several of the summaryintroductory papers presented from the astronomical viewpoint had been so full of concepts unfamiliar to a number of the aerodynamicists-physicists present, that a major part of the following discussion session had been devoted to simply clarifying concepts and then repeating a considerable amount of what had been summarized. So, always looking for alternatives which help to increase the understanding between the different disciplines by introducing clarification of concept as expeditiously as possible, we tried Christy's suggestion. Thus you will find the pattern of the following different from that in session I-A. I am much indebted to Christy for extensive collaboration in editing the resulting combined presentation and discussion. As always, however, I have taken upon myself the responsibility for the final editing, and so all shortcomings are on my head.)


Sign in / Sign up

Export Citation Format

Share Document