Matches in SemOpenAlex for { <https://semopenalex.org/work/W96692857> ?p ?o ?g. }
- W96692857 endingPage "138" @default.
- W96692857 startingPage "111" @default.
- W96692857 abstract "Body-Mass-Index (BMI) conveys important information about one's life such as health and socio-economic conditions. Large-scale automatic estimation of BMIs can help predict several societal behaviors such as health, job opportunities, friendships, and popularity. The recent works have either employed hand-crafted geometrical face features or face-level deep convolutional neural network features for face to BMI prediction. The hand-crafted geometrical face feature lack generalizability and face-level deep features don't have detailed local information. Although useful, these methods missed the detailed local information which is essential for exact BMI prediction. In this paper, we propose to use deep features that are pooled from different face regions (eye, nose, eyebrow, lips, etc.) and demonstrate that this explicit pooling from face regions can significantly boost the performance of BMI prediction. To address the problem of accurate and pixel-level face regions localization, we propose to use face semantic segmentation in our framework. Extensive experiments are performed using different Convolutional Neural Network (CNN) backbones including FaceNet and VGG-face on three publicly available datasets: VisualBMI, Bollywood and VIP attributes. Experimental results demonstrate that, as compared to the recent works, the proposed Reg-GAP gives a percentage improvement of 22.4% on VIP-attribute, 3.3% on VisualBMI, and 63.09% on the Bollywood dataset." @default.
- W96692857 created "2016-06-24" @default.
- W96692857 creator A5053656900 @default.
- W96692857 creator A5058741063 @default.
- W96692857 creator A5090669166 @default.
- W96692857 date "1989-01-01" @default.
- W96692857 modified "2023-10-15" @default.
- W96692857 title "Health Risks of Obesity" @default.
- W96692857 cites W1511934762 @default.
- W96692857 cites W1861209549 @default.
- W96692857 cites W1936410780 @default.
- W96692857 cites W1938987250 @default.
- W96692857 cites W1943668942 @default.
- W96692857 cites W1969628111 @default.
- W96692857 cites W1970836985 @default.
- W96692857 cites W1975703972 @default.
- W96692857 cites W1977523857 @default.
- W96692857 cites W1979109920 @default.
- W96692857 cites W1980115894 @default.
- W96692857 cites W1983517030 @default.
- W96692857 cites W1988232308 @default.
- W96692857 cites W1989190637 @default.
- W96692857 cites W1989371092 @default.
- W96692857 cites W1991250143 @default.
- W96692857 cites W1997123109 @default.
- W96692857 cites W1997640007 @default.
- W96692857 cites W1998019369 @default.
- W96692857 cites W2000350490 @default.
- W96692857 cites W2004812443 @default.
- W96692857 cites W2006522758 @default.
- W96692857 cites W2007186002 @default.
- W96692857 cites W2007699796 @default.
- W96692857 cites W2009470200 @default.
- W96692857 cites W2012898950 @default.
- W96692857 cites W2012916794 @default.
- W96692857 cites W2015518189 @default.
- W96692857 cites W2015776407 @default.
- W96692857 cites W2018435637 @default.
- W96692857 cites W2020719752 @default.
- W96692857 cites W2021919623 @default.
- W96692857 cites W2022076256 @default.
- W96692857 cites W2022249257 @default.
- W96692857 cites W2022373732 @default.
- W96692857 cites W2023178563 @default.
- W96692857 cites W2024196467 @default.
- W96692857 cites W2025608051 @default.
- W96692857 cites W2029538247 @default.
- W96692857 cites W2031988119 @default.
- W96692857 cites W2032040348 @default.
- W96692857 cites W2034202460 @default.
- W96692857 cites W2034486218 @default.
- W96692857 cites W2034515512 @default.
- W96692857 cites W2037494552 @default.
- W96692857 cites W2040124635 @default.
- W96692857 cites W2040298111 @default.
- W96692857 cites W2041743457 @default.
- W96692857 cites W2043549214 @default.
- W96692857 cites W2048814675 @default.
- W96692857 cites W2049285617 @default.
- W96692857 cites W2051890370 @default.
- W96692857 cites W2052435478 @default.
- W96692857 cites W2053547681 @default.
- W96692857 cites W2054746748 @default.
- W96692857 cites W2055483007 @default.
- W96692857 cites W2055689111 @default.
- W96692857 cites W2057741635 @default.
- W96692857 cites W2061947960 @default.
- W96692857 cites W2066821990 @default.
- W96692857 cites W2067301313 @default.
- W96692857 cites W2075876165 @default.
- W96692857 cites W2075990046 @default.
- W96692857 cites W2077756178 @default.
- W96692857 cites W2079033298 @default.
- W96692857 cites W2080895420 @default.
- W96692857 cites W2085213879 @default.
- W96692857 cites W2088652990 @default.
- W96692857 cites W2089524286 @default.
- W96692857 cites W2090950070 @default.
- W96692857 cites W2091177021 @default.
- W96692857 cites W2092713555 @default.
- W96692857 cites W2092836166 @default.
- W96692857 cites W2094437816 @default.
- W96692857 cites W2095173685 @default.
- W96692857 cites W2096992905 @default.
- W96692857 cites W2101994739 @default.
- W96692857 cites W2106065764 @default.
- W96692857 cites W2107842090 @default.
- W96692857 cites W2110713453 @default.
- W96692857 cites W2111215901 @default.
- W96692857 cites W2113424170 @default.
- W96692857 cites W2114097974 @default.
- W96692857 cites W2114469458 @default.
- W96692857 cites W2117296239 @default.
- W96692857 cites W2117517864 @default.
- W96692857 cites W2125854867 @default.
- W96692857 cites W2126455046 @default.
- W96692857 cites W2130200187 @default.
- W96692857 cites W2132288849 @default.