Deep Aging Face Verification With Large Gaps
Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work,...
Ausführliche Beschreibung
Autor*in: |
Wang, Meng [verfasserIn] |
---|
Format: |
Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2016 |
---|
Schlagwörter: |
---|
Systematik: |
|
---|
Übergeordnetes Werk: |
Enthalten in: IEEE transactions on multimedia - New York, NY : Institute of Electrical and Electronics Engineers, 1999, 18(2016), 1, Seite 64-75 |
---|---|
Übergeordnetes Werk: |
volume:18 ; year:2016 ; number:1 ; pages:64-75 |
Links: |
---|
DOI / URN: |
10.1109/TMM.2015.2500730 |
---|
Katalog-ID: |
OLC1971374784 |
---|
LEADER | 01000caa a2200265 4500 | ||
---|---|---|---|
001 | OLC1971374784 | ||
003 | DE-627 | ||
005 | 20220216154754.0 | ||
007 | tu | ||
008 | 160212s2016 xx ||||| 00| ||eng c | ||
024 | 7 | |a 10.1109/TMM.2015.2500730 |2 doi | |
028 | 5 | 2 | |a PQ20160212 |
035 | |a (DE-627)OLC1971374784 | ||
035 | |a (DE-599)GBVOLC1971374784 | ||
035 | |a (PRQ)c1637-7a3926385ff7b3a566f1e7707c497704dcb49856832d7e3139d62b4cd739f6360 | ||
035 | |a (KEY)0381447520160000018000100064deepagingfaceverificationwithlargegaps | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 004 |q DNB |
084 | |a ST 325: |q AVZ |2 rvk | ||
084 | |a 54.87 |2 bkl | ||
100 | 1 | |a Wang, Meng |e verfasserin |4 aut | |
245 | 1 | 0 | |a Deep Aging Face Verification With Large Gaps |
264 | 1 | |c 2016 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
338 | |a Band |b nc |2 rdacarrier | ||
520 | |a Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work, we first collect a so-called cross-age face (CAFE) dataset, ranging from child, to young, to adult, to old groups. Then, we propose a novel framework, called deep aging face verification (DAFV), for this challenging task. DAFV includes two modules: aging pattern synthesis and aging face verification. The aging pattern synthesis module synthesizes the faces of all age groups for the input face of an arbitrary age, and the core structure is a deep aging-aware denoising auto-encoder ( a^2 -DAE) with multiple outputs. The aging face verification module then takes the synthesized aging patterns of a face pair as the input, and each pair of synthesized images of the same age group is fed into a parallel CNN; finally, all parallel CNN outputs are fused to provide similar/dissimilar prediction. For DAFV, the training of the aging face verification module easily suffers from the overfitting results from the aging pattern synthesis module, and we propose to use the cross- validation strategy to produce error-aware outputs for the synthesis module. Extensive experiments on the CAFE dataset well demonstrate the superiority of the proposed DAFV framework over other solutions for aging face verification. | ||
650 | 4 | |a Training | |
650 | 4 | |a Aging | |
650 | 4 | |a Face recognition | |
650 | 4 | |a Cross-age | |
650 | 4 | |a Testing | |
650 | 4 | |a Machine learning | |
650 | 4 | |a deep learning | |
650 | 4 | |a Image reconstruction | |
650 | 4 | |a Face | |
650 | 4 | |a face verification | |
650 | 4 | |a Age | |
650 | 4 | |a Social networks | |
650 | 4 | |a Age differences | |
700 | 1 | |a Zhang, Hanwang |4 oth | |
700 | 1 | |a Yan, Shuicheng |4 oth | |
700 | 1 | |a Niu, Zhiheng |4 oth | |
700 | 1 | |a Xiong, Chao |4 oth | |
700 | 1 | |a Liu, Luoqi |4 oth | |
773 | 0 | 8 | |i Enthalten in |t IEEE transactions on multimedia |d New York, NY : Institute of Electrical and Electronics Engineers, 1999 |g 18(2016), 1, Seite 64-75 |w (DE-627)266019404 |w (DE-600)1467073-2 |w (DE-576)074960644 |x 1520-9210 |7 nnns |
773 | 1 | 8 | |g volume:18 |g year:2016 |g number:1 |g pages:64-75 |
856 | 4 | 1 | |u http://dx.doi.org/10.1109/TMM.2015.2500730 |3 Volltext |
856 | 4 | 2 | |u http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7328752 |
856 | 4 | 2 | |u http://search.proquest.com/docview/1750088953 |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_OLC | ||
912 | |a SSG-OLC-MAT | ||
912 | |a GBV_ILN_70 | ||
936 | r | v | |a ST 325: |
936 | b | k | |a 54.87 |q AVZ |
951 | |a AR | ||
952 | |d 18 |j 2016 |e 1 |h 64-75 |
author_variant |
m w mw |
---|---|
matchkey_str |
article:15209210:2016----::epgnfcvrfctow |
hierarchy_sort_str |
2016 |
bklnumber |
54.87 |
publishDate |
2016 |
allfields |
10.1109/TMM.2015.2500730 doi PQ20160212 (DE-627)OLC1971374784 (DE-599)GBVOLC1971374784 (PRQ)c1637-7a3926385ff7b3a566f1e7707c497704dcb49856832d7e3139d62b4cd739f6360 (KEY)0381447520160000018000100064deepagingfaceverificationwithlargegaps DE-627 ger DE-627 rakwb eng 004 DNB ST 325: AVZ rvk 54.87 bkl Wang, Meng verfasserin aut Deep Aging Face Verification With Large Gaps 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work, we first collect a so-called cross-age face (CAFE) dataset, ranging from child, to young, to adult, to old groups. Then, we propose a novel framework, called deep aging face verification (DAFV), for this challenging task. DAFV includes two modules: aging pattern synthesis and aging face verification. The aging pattern synthesis module synthesizes the faces of all age groups for the input face of an arbitrary age, and the core structure is a deep aging-aware denoising auto-encoder ( a^2 -DAE) with multiple outputs. The aging face verification module then takes the synthesized aging patterns of a face pair as the input, and each pair of synthesized images of the same age group is fed into a parallel CNN; finally, all parallel CNN outputs are fused to provide similar/dissimilar prediction. For DAFV, the training of the aging face verification module easily suffers from the overfitting results from the aging pattern synthesis module, and we propose to use the cross- validation strategy to produce error-aware outputs for the synthesis module. Extensive experiments on the CAFE dataset well demonstrate the superiority of the proposed DAFV framework over other solutions for aging face verification. Training Aging Face recognition Cross-age Testing Machine learning deep learning Image reconstruction Face face verification Age Social networks Age differences Zhang, Hanwang oth Yan, Shuicheng oth Niu, Zhiheng oth Xiong, Chao oth Liu, Luoqi oth Enthalten in IEEE transactions on multimedia New York, NY : Institute of Electrical and Electronics Engineers, 1999 18(2016), 1, Seite 64-75 (DE-627)266019404 (DE-600)1467073-2 (DE-576)074960644 1520-9210 nnns volume:18 year:2016 number:1 pages:64-75 http://dx.doi.org/10.1109/TMM.2015.2500730 Volltext http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7328752 http://search.proquest.com/docview/1750088953 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 ST 325: 54.87 AVZ AR 18 2016 1 64-75 |
spelling |
10.1109/TMM.2015.2500730 doi PQ20160212 (DE-627)OLC1971374784 (DE-599)GBVOLC1971374784 (PRQ)c1637-7a3926385ff7b3a566f1e7707c497704dcb49856832d7e3139d62b4cd739f6360 (KEY)0381447520160000018000100064deepagingfaceverificationwithlargegaps DE-627 ger DE-627 rakwb eng 004 DNB ST 325: AVZ rvk 54.87 bkl Wang, Meng verfasserin aut Deep Aging Face Verification With Large Gaps 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work, we first collect a so-called cross-age face (CAFE) dataset, ranging from child, to young, to adult, to old groups. Then, we propose a novel framework, called deep aging face verification (DAFV), for this challenging task. DAFV includes two modules: aging pattern synthesis and aging face verification. The aging pattern synthesis module synthesizes the faces of all age groups for the input face of an arbitrary age, and the core structure is a deep aging-aware denoising auto-encoder ( a^2 -DAE) with multiple outputs. The aging face verification module then takes the synthesized aging patterns of a face pair as the input, and each pair of synthesized images of the same age group is fed into a parallel CNN; finally, all parallel CNN outputs are fused to provide similar/dissimilar prediction. For DAFV, the training of the aging face verification module easily suffers from the overfitting results from the aging pattern synthesis module, and we propose to use the cross- validation strategy to produce error-aware outputs for the synthesis module. Extensive experiments on the CAFE dataset well demonstrate the superiority of the proposed DAFV framework over other solutions for aging face verification. Training Aging Face recognition Cross-age Testing Machine learning deep learning Image reconstruction Face face verification Age Social networks Age differences Zhang, Hanwang oth Yan, Shuicheng oth Niu, Zhiheng oth Xiong, Chao oth Liu, Luoqi oth Enthalten in IEEE transactions on multimedia New York, NY : Institute of Electrical and Electronics Engineers, 1999 18(2016), 1, Seite 64-75 (DE-627)266019404 (DE-600)1467073-2 (DE-576)074960644 1520-9210 nnns volume:18 year:2016 number:1 pages:64-75 http://dx.doi.org/10.1109/TMM.2015.2500730 Volltext http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7328752 http://search.proquest.com/docview/1750088953 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 ST 325: 54.87 AVZ AR 18 2016 1 64-75 |
allfields_unstemmed |
10.1109/TMM.2015.2500730 doi PQ20160212 (DE-627)OLC1971374784 (DE-599)GBVOLC1971374784 (PRQ)c1637-7a3926385ff7b3a566f1e7707c497704dcb49856832d7e3139d62b4cd739f6360 (KEY)0381447520160000018000100064deepagingfaceverificationwithlargegaps DE-627 ger DE-627 rakwb eng 004 DNB ST 325: AVZ rvk 54.87 bkl Wang, Meng verfasserin aut Deep Aging Face Verification With Large Gaps 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work, we first collect a so-called cross-age face (CAFE) dataset, ranging from child, to young, to adult, to old groups. Then, we propose a novel framework, called deep aging face verification (DAFV), for this challenging task. DAFV includes two modules: aging pattern synthesis and aging face verification. The aging pattern synthesis module synthesizes the faces of all age groups for the input face of an arbitrary age, and the core structure is a deep aging-aware denoising auto-encoder ( a^2 -DAE) with multiple outputs. The aging face verification module then takes the synthesized aging patterns of a face pair as the input, and each pair of synthesized images of the same age group is fed into a parallel CNN; finally, all parallel CNN outputs are fused to provide similar/dissimilar prediction. For DAFV, the training of the aging face verification module easily suffers from the overfitting results from the aging pattern synthesis module, and we propose to use the cross- validation strategy to produce error-aware outputs for the synthesis module. Extensive experiments on the CAFE dataset well demonstrate the superiority of the proposed DAFV framework over other solutions for aging face verification. Training Aging Face recognition Cross-age Testing Machine learning deep learning Image reconstruction Face face verification Age Social networks Age differences Zhang, Hanwang oth Yan, Shuicheng oth Niu, Zhiheng oth Xiong, Chao oth Liu, Luoqi oth Enthalten in IEEE transactions on multimedia New York, NY : Institute of Electrical and Electronics Engineers, 1999 18(2016), 1, Seite 64-75 (DE-627)266019404 (DE-600)1467073-2 (DE-576)074960644 1520-9210 nnns volume:18 year:2016 number:1 pages:64-75 http://dx.doi.org/10.1109/TMM.2015.2500730 Volltext http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7328752 http://search.proquest.com/docview/1750088953 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 ST 325: 54.87 AVZ AR 18 2016 1 64-75 |
allfieldsGer |
10.1109/TMM.2015.2500730 doi PQ20160212 (DE-627)OLC1971374784 (DE-599)GBVOLC1971374784 (PRQ)c1637-7a3926385ff7b3a566f1e7707c497704dcb49856832d7e3139d62b4cd739f6360 (KEY)0381447520160000018000100064deepagingfaceverificationwithlargegaps DE-627 ger DE-627 rakwb eng 004 DNB ST 325: AVZ rvk 54.87 bkl Wang, Meng verfasserin aut Deep Aging Face Verification With Large Gaps 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work, we first collect a so-called cross-age face (CAFE) dataset, ranging from child, to young, to adult, to old groups. Then, we propose a novel framework, called deep aging face verification (DAFV), for this challenging task. DAFV includes two modules: aging pattern synthesis and aging face verification. The aging pattern synthesis module synthesizes the faces of all age groups for the input face of an arbitrary age, and the core structure is a deep aging-aware denoising auto-encoder ( a^2 -DAE) with multiple outputs. The aging face verification module then takes the synthesized aging patterns of a face pair as the input, and each pair of synthesized images of the same age group is fed into a parallel CNN; finally, all parallel CNN outputs are fused to provide similar/dissimilar prediction. For DAFV, the training of the aging face verification module easily suffers from the overfitting results from the aging pattern synthesis module, and we propose to use the cross- validation strategy to produce error-aware outputs for the synthesis module. Extensive experiments on the CAFE dataset well demonstrate the superiority of the proposed DAFV framework over other solutions for aging face verification. Training Aging Face recognition Cross-age Testing Machine learning deep learning Image reconstruction Face face verification Age Social networks Age differences Zhang, Hanwang oth Yan, Shuicheng oth Niu, Zhiheng oth Xiong, Chao oth Liu, Luoqi oth Enthalten in IEEE transactions on multimedia New York, NY : Institute of Electrical and Electronics Engineers, 1999 18(2016), 1, Seite 64-75 (DE-627)266019404 (DE-600)1467073-2 (DE-576)074960644 1520-9210 nnns volume:18 year:2016 number:1 pages:64-75 http://dx.doi.org/10.1109/TMM.2015.2500730 Volltext http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7328752 http://search.proquest.com/docview/1750088953 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 ST 325: 54.87 AVZ AR 18 2016 1 64-75 |
allfieldsSound |
10.1109/TMM.2015.2500730 doi PQ20160212 (DE-627)OLC1971374784 (DE-599)GBVOLC1971374784 (PRQ)c1637-7a3926385ff7b3a566f1e7707c497704dcb49856832d7e3139d62b4cd739f6360 (KEY)0381447520160000018000100064deepagingfaceverificationwithlargegaps DE-627 ger DE-627 rakwb eng 004 DNB ST 325: AVZ rvk 54.87 bkl Wang, Meng verfasserin aut Deep Aging Face Verification With Large Gaps 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work, we first collect a so-called cross-age face (CAFE) dataset, ranging from child, to young, to adult, to old groups. Then, we propose a novel framework, called deep aging face verification (DAFV), for this challenging task. DAFV includes two modules: aging pattern synthesis and aging face verification. The aging pattern synthesis module synthesizes the faces of all age groups for the input face of an arbitrary age, and the core structure is a deep aging-aware denoising auto-encoder ( a^2 -DAE) with multiple outputs. The aging face verification module then takes the synthesized aging patterns of a face pair as the input, and each pair of synthesized images of the same age group is fed into a parallel CNN; finally, all parallel CNN outputs are fused to provide similar/dissimilar prediction. For DAFV, the training of the aging face verification module easily suffers from the overfitting results from the aging pattern synthesis module, and we propose to use the cross- validation strategy to produce error-aware outputs for the synthesis module. Extensive experiments on the CAFE dataset well demonstrate the superiority of the proposed DAFV framework over other solutions for aging face verification. Training Aging Face recognition Cross-age Testing Machine learning deep learning Image reconstruction Face face verification Age Social networks Age differences Zhang, Hanwang oth Yan, Shuicheng oth Niu, Zhiheng oth Xiong, Chao oth Liu, Luoqi oth Enthalten in IEEE transactions on multimedia New York, NY : Institute of Electrical and Electronics Engineers, 1999 18(2016), 1, Seite 64-75 (DE-627)266019404 (DE-600)1467073-2 (DE-576)074960644 1520-9210 nnns volume:18 year:2016 number:1 pages:64-75 http://dx.doi.org/10.1109/TMM.2015.2500730 Volltext http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7328752 http://search.proquest.com/docview/1750088953 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 ST 325: 54.87 AVZ AR 18 2016 1 64-75 |
language |
English |
source |
Enthalten in IEEE transactions on multimedia 18(2016), 1, Seite 64-75 volume:18 year:2016 number:1 pages:64-75 |
sourceStr |
Enthalten in IEEE transactions on multimedia 18(2016), 1, Seite 64-75 volume:18 year:2016 number:1 pages:64-75 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
Training Aging Face recognition Cross-age Testing Machine learning deep learning Image reconstruction Face face verification Age Social networks Age differences |
dewey-raw |
004 |
isfreeaccess_bool |
false |
container_title |
IEEE transactions on multimedia |
authorswithroles_txt_mv |
Wang, Meng @@aut@@ Zhang, Hanwang @@oth@@ Yan, Shuicheng @@oth@@ Niu, Zhiheng @@oth@@ Xiong, Chao @@oth@@ Liu, Luoqi @@oth@@ |
publishDateDaySort_date |
2016-01-01T00:00:00Z |
hierarchy_top_id |
266019404 |
dewey-sort |
14 |
id |
OLC1971374784 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a2200265 4500</leader><controlfield tag="001">OLC1971374784</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20220216154754.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">160212s2016 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/TMM.2015.2500730</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">PQ20160212</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC1971374784</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)GBVOLC1971374784</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(PRQ)c1637-7a3926385ff7b3a566f1e7707c497704dcb49856832d7e3139d62b4cd739f6360</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(KEY)0381447520160000018000100064deepagingfaceverificationwithlargegaps</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">DNB</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 325:</subfield><subfield code="q">AVZ</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.87</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Wang, Meng</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep Aging Face Verification With Large Gaps</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work, we first collect a so-called cross-age face (CAFE) dataset, ranging from child, to young, to adult, to old groups. Then, we propose a novel framework, called deep aging face verification (DAFV), for this challenging task. DAFV includes two modules: aging pattern synthesis and aging face verification. The aging pattern synthesis module synthesizes the faces of all age groups for the input face of an arbitrary age, and the core structure is a deep aging-aware denoising auto-encoder ( a^2 -DAE) with multiple outputs. The aging face verification module then takes the synthesized aging patterns of a face pair as the input, and each pair of synthesized images of the same age group is fed into a parallel CNN; finally, all parallel CNN outputs are fused to provide similar/dissimilar prediction. For DAFV, the training of the aging face verification module easily suffers from the overfitting results from the aging pattern synthesis module, and we propose to use the cross- validation strategy to produce error-aware outputs for the synthesis module. Extensive experiments on the CAFE dataset well demonstrate the superiority of the proposed DAFV framework over other solutions for aging face verification.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Training</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Aging</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Face recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-age</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Testing</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image reconstruction</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Face</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">face verification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Age</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Social networks</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Age differences</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Hanwang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yan, Shuicheng</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Niu, Zhiheng</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Xiong, Chao</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Luoqi</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">IEEE transactions on multimedia</subfield><subfield code="d">New York, NY : Institute of Electrical and Electronics Engineers, 1999</subfield><subfield code="g">18(2016), 1, Seite 64-75</subfield><subfield code="w">(DE-627)266019404</subfield><subfield code="w">(DE-600)1467073-2</subfield><subfield code="w">(DE-576)074960644</subfield><subfield code="x">1520-9210</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:18</subfield><subfield code="g">year:2016</subfield><subfield code="g">number:1</subfield><subfield code="g">pages:64-75</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">http://dx.doi.org/10.1109/TMM.2015.2500730</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7328752</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://search.proquest.com/docview/1750088953</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="936" ind1="r" ind2="v"><subfield code="a">ST 325:</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.87</subfield><subfield code="q">AVZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">18</subfield><subfield code="j">2016</subfield><subfield code="e">1</subfield><subfield code="h">64-75</subfield></datafield></record></collection>
|
author |
Wang, Meng |
spellingShingle |
Wang, Meng ddc 004 rvk ST 325: bkl 54.87 misc Training misc Aging misc Face recognition misc Cross-age misc Testing misc Machine learning misc deep learning misc Image reconstruction misc Face misc face verification misc Age misc Social networks misc Age differences Deep Aging Face Verification With Large Gaps |
authorStr |
Wang, Meng |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)266019404 |
format |
Article |
dewey-ones |
004 - Data processing & computer science |
delete_txt_mv |
keep |
author_role |
aut |
collection |
OLC |
remote_str |
false |
illustrated |
Not Illustrated |
issn |
1520-9210 |
topic_title |
004 DNB ST 325: AVZ rvk 54.87 bkl Deep Aging Face Verification With Large Gaps Training Aging Face recognition Cross-age Testing Machine learning deep learning Image reconstruction Face face verification Age Social networks Age differences |
topic |
ddc 004 rvk ST 325: bkl 54.87 misc Training misc Aging misc Face recognition misc Cross-age misc Testing misc Machine learning misc deep learning misc Image reconstruction misc Face misc face verification misc Age misc Social networks misc Age differences |
topic_unstemmed |
ddc 004 rvk ST 325: bkl 54.87 misc Training misc Aging misc Face recognition misc Cross-age misc Testing misc Machine learning misc deep learning misc Image reconstruction misc Face misc face verification misc Age misc Social networks misc Age differences |
topic_browse |
ddc 004 rvk ST 325: bkl 54.87 misc Training misc Aging misc Face recognition misc Cross-age misc Testing misc Machine learning misc deep learning misc Image reconstruction misc Face misc face verification misc Age misc Social networks misc Age differences |
format_facet |
Aufsätze Gedruckte Aufsätze |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
nc |
author2_variant |
h z hz s y sy z n zn c x cx l l ll |
hierarchy_parent_title |
IEEE transactions on multimedia |
hierarchy_parent_id |
266019404 |
dewey-tens |
000 - Computer science, knowledge & systems |
hierarchy_top_title |
IEEE transactions on multimedia |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)266019404 (DE-600)1467073-2 (DE-576)074960644 |
title |
Deep Aging Face Verification With Large Gaps |
ctrlnum |
(DE-627)OLC1971374784 (DE-599)GBVOLC1971374784 (PRQ)c1637-7a3926385ff7b3a566f1e7707c497704dcb49856832d7e3139d62b4cd739f6360 (KEY)0381447520160000018000100064deepagingfaceverificationwithlargegaps |
title_full |
Deep Aging Face Verification With Large Gaps |
author_sort |
Wang, Meng |
journal |
IEEE transactions on multimedia |
journalStr |
IEEE transactions on multimedia |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
000 - Computer science, information & general works |
recordtype |
marc |
publishDateSort |
2016 |
contenttype_str_mv |
txt |
container_start_page |
64 |
author_browse |
Wang, Meng |
container_volume |
18 |
class |
004 DNB ST 325: AVZ rvk 54.87 bkl |
format_se |
Aufsätze |
author-letter |
Wang, Meng |
doi_str_mv |
10.1109/TMM.2015.2500730 |
dewey-full |
004 |
title_sort |
deep aging face verification with large gaps |
title_auth |
Deep Aging Face Verification With Large Gaps |
abstract |
Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work, we first collect a so-called cross-age face (CAFE) dataset, ranging from child, to young, to adult, to old groups. Then, we propose a novel framework, called deep aging face verification (DAFV), for this challenging task. DAFV includes two modules: aging pattern synthesis and aging face verification. The aging pattern synthesis module synthesizes the faces of all age groups for the input face of an arbitrary age, and the core structure is a deep aging-aware denoising auto-encoder ( a^2 -DAE) with multiple outputs. The aging face verification module then takes the synthesized aging patterns of a face pair as the input, and each pair of synthesized images of the same age group is fed into a parallel CNN; finally, all parallel CNN outputs are fused to provide similar/dissimilar prediction. For DAFV, the training of the aging face verification module easily suffers from the overfitting results from the aging pattern synthesis module, and we propose to use the cross- validation strategy to produce error-aware outputs for the synthesis module. Extensive experiments on the CAFE dataset well demonstrate the superiority of the proposed DAFV framework over other solutions for aging face verification. |
abstractGer |
Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work, we first collect a so-called cross-age face (CAFE) dataset, ranging from child, to young, to adult, to old groups. Then, we propose a novel framework, called deep aging face verification (DAFV), for this challenging task. DAFV includes two modules: aging pattern synthesis and aging face verification. The aging pattern synthesis module synthesizes the faces of all age groups for the input face of an arbitrary age, and the core structure is a deep aging-aware denoising auto-encoder ( a^2 -DAE) with multiple outputs. The aging face verification module then takes the synthesized aging patterns of a face pair as the input, and each pair of synthesized images of the same age group is fed into a parallel CNN; finally, all parallel CNN outputs are fused to provide similar/dissimilar prediction. For DAFV, the training of the aging face verification module easily suffers from the overfitting results from the aging pattern synthesis module, and we propose to use the cross- validation strategy to produce error-aware outputs for the synthesis module. Extensive experiments on the CAFE dataset well demonstrate the superiority of the proposed DAFV framework over other solutions for aging face verification. |
abstract_unstemmed |
Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work, we first collect a so-called cross-age face (CAFE) dataset, ranging from child, to young, to adult, to old groups. Then, we propose a novel framework, called deep aging face verification (DAFV), for this challenging task. DAFV includes two modules: aging pattern synthesis and aging face verification. The aging pattern synthesis module synthesizes the faces of all age groups for the input face of an arbitrary age, and the core structure is a deep aging-aware denoising auto-encoder ( a^2 -DAE) with multiple outputs. The aging face verification module then takes the synthesized aging patterns of a face pair as the input, and each pair of synthesized images of the same age group is fed into a parallel CNN; finally, all parallel CNN outputs are fused to provide similar/dissimilar prediction. For DAFV, the training of the aging face verification module easily suffers from the overfitting results from the aging pattern synthesis module, and we propose to use the cross- validation strategy to produce error-aware outputs for the synthesis module. Extensive experiments on the CAFE dataset well demonstrate the superiority of the proposed DAFV framework over other solutions for aging face verification. |
collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 |
container_issue |
1 |
title_short |
Deep Aging Face Verification With Large Gaps |
url |
http://dx.doi.org/10.1109/TMM.2015.2500730 http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7328752 http://search.proquest.com/docview/1750088953 |
remote_bool |
false |
author2 |
Zhang, Hanwang Yan, Shuicheng Niu, Zhiheng Xiong, Chao Liu, Luoqi |
author2Str |
Zhang, Hanwang Yan, Shuicheng Niu, Zhiheng Xiong, Chao Liu, Luoqi |
ppnlink |
266019404 |
mediatype_str_mv |
n |
isOA_txt |
false |
hochschulschrift_bool |
false |
author2_role |
oth oth oth oth oth |
doi_str |
10.1109/TMM.2015.2500730 |
up_date |
2024-07-03T19:14:47.671Z |
_version_ |
1803586463518949376 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a2200265 4500</leader><controlfield tag="001">OLC1971374784</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20220216154754.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">160212s2016 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/TMM.2015.2500730</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">PQ20160212</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC1971374784</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)GBVOLC1971374784</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(PRQ)c1637-7a3926385ff7b3a566f1e7707c497704dcb49856832d7e3139d62b4cd739f6360</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(KEY)0381447520160000018000100064deepagingfaceverificationwithlargegaps</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">DNB</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 325:</subfield><subfield code="q">AVZ</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.87</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Wang, Meng</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep Aging Face Verification With Large Gaps</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Along with the long-time evolution of popular social networks, e.g. Facebook, social media analysis research inevitably arrived at the era of considering face/user recognition with large age gaps. However, related research with adequate subjects and large age gaps is surprisingly rare. In this work, we first collect a so-called cross-age face (CAFE) dataset, ranging from child, to young, to adult, to old groups. Then, we propose a novel framework, called deep aging face verification (DAFV), for this challenging task. DAFV includes two modules: aging pattern synthesis and aging face verification. The aging pattern synthesis module synthesizes the faces of all age groups for the input face of an arbitrary age, and the core structure is a deep aging-aware denoising auto-encoder ( a^2 -DAE) with multiple outputs. The aging face verification module then takes the synthesized aging patterns of a face pair as the input, and each pair of synthesized images of the same age group is fed into a parallel CNN; finally, all parallel CNN outputs are fused to provide similar/dissimilar prediction. For DAFV, the training of the aging face verification module easily suffers from the overfitting results from the aging pattern synthesis module, and we propose to use the cross- validation strategy to produce error-aware outputs for the synthesis module. Extensive experiments on the CAFE dataset well demonstrate the superiority of the proposed DAFV framework over other solutions for aging face verification.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Training</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Aging</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Face recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-age</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Testing</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image reconstruction</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Face</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">face verification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Age</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Social networks</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Age differences</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Hanwang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yan, Shuicheng</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Niu, Zhiheng</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Xiong, Chao</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Luoqi</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">IEEE transactions on multimedia</subfield><subfield code="d">New York, NY : Institute of Electrical and Electronics Engineers, 1999</subfield><subfield code="g">18(2016), 1, Seite 64-75</subfield><subfield code="w">(DE-627)266019404</subfield><subfield code="w">(DE-600)1467073-2</subfield><subfield code="w">(DE-576)074960644</subfield><subfield code="x">1520-9210</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:18</subfield><subfield code="g">year:2016</subfield><subfield code="g">number:1</subfield><subfield code="g">pages:64-75</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">http://dx.doi.org/10.1109/TMM.2015.2500730</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7328752</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://search.proquest.com/docview/1750088953</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="936" ind1="r" ind2="v"><subfield code="a">ST 325:</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.87</subfield><subfield code="q">AVZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">18</subfield><subfield code="j">2016</subfield><subfield code="e">1</subfield><subfield code="h">64-75</subfield></datafield></record></collection>
|
score |
7.4014435 |