Human activity recognition using robust adaptive privileged probabilistic learning
Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for a...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Vrigkas, Michalis [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2021 |
|---|
| Schlagwörter: |
Hidden conditional random fields |
|---|
| Anmerkung: |
© The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Pattern analysis and applications - Springer London, 1998, 24(2021), 3 vom: 04. Jan., Seite 915-932 |
|---|---|
| Übergeordnetes Werk: |
volume:24 ; year:2021 ; number:3 ; day:04 ; month:01 ; pages:915-932 |
| Links: |
|---|
| DOI / URN: |
10.1007/s10044-020-00953-x |
|---|
| Katalog-ID: |
OLC2126970418 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2126970418 | ||
| 003 | DE-627 | ||
| 005 | 20230505123157.0 | ||
| 007 | tu | ||
| 008 | 230505s2021 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s10044-020-00953-x |2 doi | |
| 035 | |a (DE-627)OLC2126970418 | ||
| 035 | |a (DE-He213)s10044-020-00953-x-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 004 |a 600 |q VZ |
| 084 | |a 54.74$jMaschinelles Sehen |2 bkl | ||
| 100 | 1 | |a Vrigkas, Michalis |e verfasserin |0 (orcid)0000-0001-5888-6949 |4 aut | |
| 245 | 1 | 0 | |a Human activity recognition using robust adaptive privileged probabilistic learning |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021 | ||
| 520 | |a Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network. | ||
| 650 | 4 | |a Hidden conditional random fields | |
| 650 | 4 | |a Learning using privileged information | |
| 650 | 4 | |a Human activity recognition | |
| 650 | 4 | |a Student’s | |
| 650 | 4 | |a -distribution | |
| 700 | 1 | |a Kazakos, Evangelos |4 aut | |
| 700 | 1 | |a Nikou, Christophoros |4 aut | |
| 700 | 1 | |a Kakadiaris, Ioannis A. |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Pattern analysis and applications |d Springer London, 1998 |g 24(2021), 3 vom: 04. Jan., Seite 915-932 |w (DE-627)24992921X |w (DE-600)1446989-3 |w (DE-576)27655583X |x 1433-7541 |7 nnns |
| 773 | 1 | 8 | |g volume:24 |g year:2021 |g number:3 |g day:04 |g month:01 |g pages:915-932 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s10044-020-00953-x |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 936 | b | k | |a 54.74$jMaschinelles Sehen |q VZ |0 10641030X |0 (DE-625)10641030X |
| 951 | |a AR | ||
| 952 | |d 24 |j 2021 |e 3 |b 04 |c 01 |h 915-932 | ||
| author_variant |
m v mv e k ek c n cn i a k ia iak |
|---|---|
| matchkey_str |
article:14337541:2021----::uaatvtrcgiinsnrbsaatvpiieep |
| hierarchy_sort_str |
2021 |
| bklnumber |
54.74$jMaschinelles Sehen |
| publishDate |
2021 |
| allfields |
10.1007/s10044-020-00953-x doi (DE-627)OLC2126970418 (DE-He213)s10044-020-00953-x-p DE-627 ger DE-627 rakwb eng 004 600 VZ 54.74$jMaschinelles Sehen bkl Vrigkas, Michalis verfasserin (orcid)0000-0001-5888-6949 aut Human activity recognition using robust adaptive privileged probabilistic learning 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021 Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network. Hidden conditional random fields Learning using privileged information Human activity recognition Student’s -distribution Kazakos, Evangelos aut Nikou, Christophoros aut Kakadiaris, Ioannis A. aut Enthalten in Pattern analysis and applications Springer London, 1998 24(2021), 3 vom: 04. Jan., Seite 915-932 (DE-627)24992921X (DE-600)1446989-3 (DE-576)27655583X 1433-7541 nnns volume:24 year:2021 number:3 day:04 month:01 pages:915-932 https://doi.org/10.1007/s10044-020-00953-x lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT 54.74$jMaschinelles Sehen VZ 10641030X (DE-625)10641030X AR 24 2021 3 04 01 915-932 |
| spelling |
10.1007/s10044-020-00953-x doi (DE-627)OLC2126970418 (DE-He213)s10044-020-00953-x-p DE-627 ger DE-627 rakwb eng 004 600 VZ 54.74$jMaschinelles Sehen bkl Vrigkas, Michalis verfasserin (orcid)0000-0001-5888-6949 aut Human activity recognition using robust adaptive privileged probabilistic learning 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021 Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network. Hidden conditional random fields Learning using privileged information Human activity recognition Student’s -distribution Kazakos, Evangelos aut Nikou, Christophoros aut Kakadiaris, Ioannis A. aut Enthalten in Pattern analysis and applications Springer London, 1998 24(2021), 3 vom: 04. Jan., Seite 915-932 (DE-627)24992921X (DE-600)1446989-3 (DE-576)27655583X 1433-7541 nnns volume:24 year:2021 number:3 day:04 month:01 pages:915-932 https://doi.org/10.1007/s10044-020-00953-x lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT 54.74$jMaschinelles Sehen VZ 10641030X (DE-625)10641030X AR 24 2021 3 04 01 915-932 |
| allfields_unstemmed |
10.1007/s10044-020-00953-x doi (DE-627)OLC2126970418 (DE-He213)s10044-020-00953-x-p DE-627 ger DE-627 rakwb eng 004 600 VZ 54.74$jMaschinelles Sehen bkl Vrigkas, Michalis verfasserin (orcid)0000-0001-5888-6949 aut Human activity recognition using robust adaptive privileged probabilistic learning 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021 Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network. Hidden conditional random fields Learning using privileged information Human activity recognition Student’s -distribution Kazakos, Evangelos aut Nikou, Christophoros aut Kakadiaris, Ioannis A. aut Enthalten in Pattern analysis and applications Springer London, 1998 24(2021), 3 vom: 04. Jan., Seite 915-932 (DE-627)24992921X (DE-600)1446989-3 (DE-576)27655583X 1433-7541 nnns volume:24 year:2021 number:3 day:04 month:01 pages:915-932 https://doi.org/10.1007/s10044-020-00953-x lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT 54.74$jMaschinelles Sehen VZ 10641030X (DE-625)10641030X AR 24 2021 3 04 01 915-932 |
| allfieldsGer |
10.1007/s10044-020-00953-x doi (DE-627)OLC2126970418 (DE-He213)s10044-020-00953-x-p DE-627 ger DE-627 rakwb eng 004 600 VZ 54.74$jMaschinelles Sehen bkl Vrigkas, Michalis verfasserin (orcid)0000-0001-5888-6949 aut Human activity recognition using robust adaptive privileged probabilistic learning 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021 Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network. Hidden conditional random fields Learning using privileged information Human activity recognition Student’s -distribution Kazakos, Evangelos aut Nikou, Christophoros aut Kakadiaris, Ioannis A. aut Enthalten in Pattern analysis and applications Springer London, 1998 24(2021), 3 vom: 04. Jan., Seite 915-932 (DE-627)24992921X (DE-600)1446989-3 (DE-576)27655583X 1433-7541 nnns volume:24 year:2021 number:3 day:04 month:01 pages:915-932 https://doi.org/10.1007/s10044-020-00953-x lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT 54.74$jMaschinelles Sehen VZ 10641030X (DE-625)10641030X AR 24 2021 3 04 01 915-932 |
| allfieldsSound |
10.1007/s10044-020-00953-x doi (DE-627)OLC2126970418 (DE-He213)s10044-020-00953-x-p DE-627 ger DE-627 rakwb eng 004 600 VZ 54.74$jMaschinelles Sehen bkl Vrigkas, Michalis verfasserin (orcid)0000-0001-5888-6949 aut Human activity recognition using robust adaptive privileged probabilistic learning 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021 Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network. Hidden conditional random fields Learning using privileged information Human activity recognition Student’s -distribution Kazakos, Evangelos aut Nikou, Christophoros aut Kakadiaris, Ioannis A. aut Enthalten in Pattern analysis and applications Springer London, 1998 24(2021), 3 vom: 04. Jan., Seite 915-932 (DE-627)24992921X (DE-600)1446989-3 (DE-576)27655583X 1433-7541 nnns volume:24 year:2021 number:3 day:04 month:01 pages:915-932 https://doi.org/10.1007/s10044-020-00953-x lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT 54.74$jMaschinelles Sehen VZ 10641030X (DE-625)10641030X AR 24 2021 3 04 01 915-932 |
| language |
English |
| source |
Enthalten in Pattern analysis and applications 24(2021), 3 vom: 04. Jan., Seite 915-932 volume:24 year:2021 number:3 day:04 month:01 pages:915-932 |
| sourceStr |
Enthalten in Pattern analysis and applications 24(2021), 3 vom: 04. Jan., Seite 915-932 volume:24 year:2021 number:3 day:04 month:01 pages:915-932 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Hidden conditional random fields Learning using privileged information Human activity recognition Student’s -distribution |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
Pattern analysis and applications |
| authorswithroles_txt_mv |
Vrigkas, Michalis @@aut@@ Kazakos, Evangelos @@aut@@ Nikou, Christophoros @@aut@@ Kakadiaris, Ioannis A. @@aut@@ |
| publishDateDaySort_date |
2021-01-04T00:00:00Z |
| hierarchy_top_id |
24992921X |
| dewey-sort |
14 |
| id |
OLC2126970418 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">OLC2126970418</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505123157.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230505s2021 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s10044-020-00953-x</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2126970418</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s10044-020-00953-x-p</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="a">600</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.74$jMaschinelles Sehen</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Vrigkas, Michalis</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-5888-6949</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Human activity recognition using robust adaptive privileged probabilistic learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</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="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hidden conditional random fields</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Learning using privileged information</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Human activity recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Student’s</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">-distribution</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kazakos, Evangelos</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Nikou, Christophoros</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kakadiaris, Ioannis A.</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Pattern analysis and applications</subfield><subfield code="d">Springer London, 1998</subfield><subfield code="g">24(2021), 3 vom: 04. Jan., Seite 915-932</subfield><subfield code="w">(DE-627)24992921X</subfield><subfield code="w">(DE-600)1446989-3</subfield><subfield code="w">(DE-576)27655583X</subfield><subfield code="x">1433-7541</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:24</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:3</subfield><subfield code="g">day:04</subfield><subfield code="g">month:01</subfield><subfield code="g">pages:915-932</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s10044-020-00953-x</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</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="936" ind1="b" ind2="k"><subfield code="a">54.74$jMaschinelles Sehen</subfield><subfield code="q">VZ</subfield><subfield code="0">10641030X</subfield><subfield code="0">(DE-625)10641030X</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">24</subfield><subfield code="j">2021</subfield><subfield code="e">3</subfield><subfield code="b">04</subfield><subfield code="c">01</subfield><subfield code="h">915-932</subfield></datafield></record></collection>
|
| author |
Vrigkas, Michalis |
| spellingShingle |
Vrigkas, Michalis ddc 004 bkl 54.74$jMaschinelles Sehen misc Hidden conditional random fields misc Learning using privileged information misc Human activity recognition misc Student’s misc -distribution Human activity recognition using robust adaptive privileged probabilistic learning |
| authorStr |
Vrigkas, Michalis |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)24992921X |
| format |
Article |
| dewey-ones |
004 - Data processing & computer science 600 - Technology |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
1433-7541 |
| topic_title |
004 600 VZ 54.74$jMaschinelles Sehen bkl Human activity recognition using robust adaptive privileged probabilistic learning Hidden conditional random fields Learning using privileged information Human activity recognition Student’s -distribution |
| topic |
ddc 004 bkl 54.74$jMaschinelles Sehen misc Hidden conditional random fields misc Learning using privileged information misc Human activity recognition misc Student’s misc -distribution |
| topic_unstemmed |
ddc 004 bkl 54.74$jMaschinelles Sehen misc Hidden conditional random fields misc Learning using privileged information misc Human activity recognition misc Student’s misc -distribution |
| topic_browse |
ddc 004 bkl 54.74$jMaschinelles Sehen misc Hidden conditional random fields misc Learning using privileged information misc Human activity recognition misc Student’s misc -distribution |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Pattern analysis and applications |
| hierarchy_parent_id |
24992921X |
| dewey-tens |
000 - Computer science, knowledge & systems 600 - Technology |
| hierarchy_top_title |
Pattern analysis and applications |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)24992921X (DE-600)1446989-3 (DE-576)27655583X |
| title |
Human activity recognition using robust adaptive privileged probabilistic learning |
| ctrlnum |
(DE-627)OLC2126970418 (DE-He213)s10044-020-00953-x-p |
| title_full |
Human activity recognition using robust adaptive privileged probabilistic learning |
| author_sort |
Vrigkas, Michalis |
| journal |
Pattern analysis and applications |
| journalStr |
Pattern analysis and applications |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works 600 - Technology |
| recordtype |
marc |
| publishDateSort |
2021 |
| contenttype_str_mv |
txt |
| container_start_page |
915 |
| author_browse |
Vrigkas, Michalis Kazakos, Evangelos Nikou, Christophoros Kakadiaris, Ioannis A. |
| container_volume |
24 |
| class |
004 600 VZ 54.74$jMaschinelles Sehen bkl |
| format_se |
Aufsätze |
| author-letter |
Vrigkas, Michalis |
| doi_str_mv |
10.1007/s10044-020-00953-x |
| normlink |
(ORCID)0000-0001-5888-6949 10641030X |
| normlink_prefix_str_mv |
(orcid)0000-0001-5888-6949 10641030X (DE-625)10641030X |
| dewey-full |
004 600 |
| title_sort |
human activity recognition using robust adaptive privileged probabilistic learning |
| title_auth |
Human activity recognition using robust adaptive privileged probabilistic learning |
| abstract |
Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network. © The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021 |
| abstractGer |
Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network. © The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021 |
| abstract_unstemmed |
Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network. © The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT |
| container_issue |
3 |
| title_short |
Human activity recognition using robust adaptive privileged probabilistic learning |
| url |
https://doi.org/10.1007/s10044-020-00953-x |
| remote_bool |
false |
| author2 |
Kazakos, Evangelos Nikou, Christophoros Kakadiaris, Ioannis A. |
| author2Str |
Kazakos, Evangelos Nikou, Christophoros Kakadiaris, Ioannis A. |
| ppnlink |
24992921X |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s10044-020-00953-x |
| up_date |
2024-07-04T09:06:47.094Z |
| _version_ |
1803638807829938176 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">OLC2126970418</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505123157.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230505s2021 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s10044-020-00953-x</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2126970418</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s10044-020-00953-x-p</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="a">600</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.74$jMaschinelles Sehen</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Vrigkas, Michalis</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-5888-6949</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Human activity recognition using robust adaptive privileged probabilistic learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</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="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In this work, a supervised probabilistic approach is proposed that integrates the learning using privileged information (LUPI) paradigm into a hidden conditional random field (HCRF) model, called HCRF+, for human action recognition. The proposed model employs a self-training technique for automatic estimation of the regularization parameters of the objective function. Moreover, the method provides robustness to outliers by modeling the conditional distribution of the privileged information by a Student’s t-density function, which is naturally integrated into the HCRF+ framework. The proposed method was evaluated using different forms of privileged information on four publicly available datasets. The experimental results demonstrate its effectiveness concerning the state of the art in the LUPI framework using both hand-crafted and deep learning-based features extracted from a convolutional neural network.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hidden conditional random fields</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Learning using privileged information</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Human activity recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Student’s</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">-distribution</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kazakos, Evangelos</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Nikou, Christophoros</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kakadiaris, Ioannis A.</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Pattern analysis and applications</subfield><subfield code="d">Springer London, 1998</subfield><subfield code="g">24(2021), 3 vom: 04. Jan., Seite 915-932</subfield><subfield code="w">(DE-627)24992921X</subfield><subfield code="w">(DE-600)1446989-3</subfield><subfield code="w">(DE-576)27655583X</subfield><subfield code="x">1433-7541</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:24</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:3</subfield><subfield code="g">day:04</subfield><subfield code="g">month:01</subfield><subfield code="g">pages:915-932</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s10044-020-00953-x</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</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="936" ind1="b" ind2="k"><subfield code="a">54.74$jMaschinelles Sehen</subfield><subfield code="q">VZ</subfield><subfield code="0">10641030X</subfield><subfield code="0">(DE-625)10641030X</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">24</subfield><subfield code="j">2021</subfield><subfield code="e">3</subfield><subfield code="b">04</subfield><subfield code="c">01</subfield><subfield code="h">915-932</subfield></datafield></record></collection>
|
| score |
7.400609 |