Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network
• To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GC...
Ausführliche Beschreibung
Autor*in: |
Sheng, Weijie [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2021transfer abstract |
---|
Übergeordnetes Werk: |
Enthalten in: Association between dopa decarboxylase gene variants and borderline personality disorder - Mobascher, Arian ELSEVIER, 2014, the journal of the Pattern Recognition Society, Amsterdam |
---|---|
Übergeordnetes Werk: |
volume:114 ; year:2021 ; pages:0 |
Links: |
---|
DOI / URN: |
10.1016/j.patcog.2021.107868 |
---|
Katalog-ID: |
ELV053260880 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | ELV053260880 | ||
003 | DE-627 | ||
005 | 20230626034522.0 | ||
007 | cr uuu---uuuuu | ||
008 | 210910s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.patcog.2021.107868 |2 doi | |
028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001314.pica |
035 | |a (DE-627)ELV053260880 | ||
035 | |a (ELSEVIER)S0031-3203(21)00055-8 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Sheng, Weijie |e verfasserin |4 aut | |
245 | 1 | 0 | |a Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network |
264 | 1 | |c 2021transfer abstract | |
336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
337 | |a nicht spezifiziert |b z |2 rdamedia | ||
338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
520 | |a • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. | ||
520 | |a • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. | ||
700 | 1 | |a Li, Xinde |4 oth | |
773 | 0 | 8 | |i Enthalten in |n Elsevier |a Mobascher, Arian ELSEVIER |t Association between dopa decarboxylase gene variants and borderline personality disorder |d 2014 |d the journal of the Pattern Recognition Society |g Amsterdam |w (DE-627)ELV017326583 |
773 | 1 | 8 | |g volume:114 |g year:2021 |g pages:0 |
856 | 4 | 0 | |u https://doi.org/10.1016/j.patcog.2021.107868 |3 Volltext |
912 | |a GBV_USEFLAG_U | ||
912 | |a GBV_ELV | ||
912 | |a SYSFLAG_U | ||
951 | |a AR | ||
952 | |d 114 |j 2021 |h 0 |
author_variant |
w s ws |
---|---|
matchkey_str |
shengweijielixinde:2021----:uttslannfrataeiettrcgiinneoineontouigtetoehnet |
hierarchy_sort_str |
2021transfer abstract |
publishDate |
2021 |
allfields |
10.1016/j.patcog.2021.107868 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001314.pica (DE-627)ELV053260880 (ELSEVIER)S0031-3203(21)00055-8 DE-627 ger DE-627 rakwb eng Sheng, Weijie verfasserin aut Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. Li, Xinde oth Enthalten in Elsevier Mobascher, Arian ELSEVIER Association between dopa decarboxylase gene variants and borderline personality disorder 2014 the journal of the Pattern Recognition Society Amsterdam (DE-627)ELV017326583 volume:114 year:2021 pages:0 https://doi.org/10.1016/j.patcog.2021.107868 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 114 2021 0 |
spelling |
10.1016/j.patcog.2021.107868 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001314.pica (DE-627)ELV053260880 (ELSEVIER)S0031-3203(21)00055-8 DE-627 ger DE-627 rakwb eng Sheng, Weijie verfasserin aut Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. Li, Xinde oth Enthalten in Elsevier Mobascher, Arian ELSEVIER Association between dopa decarboxylase gene variants and borderline personality disorder 2014 the journal of the Pattern Recognition Society Amsterdam (DE-627)ELV017326583 volume:114 year:2021 pages:0 https://doi.org/10.1016/j.patcog.2021.107868 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 114 2021 0 |
allfields_unstemmed |
10.1016/j.patcog.2021.107868 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001314.pica (DE-627)ELV053260880 (ELSEVIER)S0031-3203(21)00055-8 DE-627 ger DE-627 rakwb eng Sheng, Weijie verfasserin aut Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. Li, Xinde oth Enthalten in Elsevier Mobascher, Arian ELSEVIER Association between dopa decarboxylase gene variants and borderline personality disorder 2014 the journal of the Pattern Recognition Society Amsterdam (DE-627)ELV017326583 volume:114 year:2021 pages:0 https://doi.org/10.1016/j.patcog.2021.107868 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 114 2021 0 |
allfieldsGer |
10.1016/j.patcog.2021.107868 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001314.pica (DE-627)ELV053260880 (ELSEVIER)S0031-3203(21)00055-8 DE-627 ger DE-627 rakwb eng Sheng, Weijie verfasserin aut Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. Li, Xinde oth Enthalten in Elsevier Mobascher, Arian ELSEVIER Association between dopa decarboxylase gene variants and borderline personality disorder 2014 the journal of the Pattern Recognition Society Amsterdam (DE-627)ELV017326583 volume:114 year:2021 pages:0 https://doi.org/10.1016/j.patcog.2021.107868 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 114 2021 0 |
allfieldsSound |
10.1016/j.patcog.2021.107868 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001314.pica (DE-627)ELV053260880 (ELSEVIER)S0031-3203(21)00055-8 DE-627 ger DE-627 rakwb eng Sheng, Weijie verfasserin aut Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network 2021transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. • To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. Li, Xinde oth Enthalten in Elsevier Mobascher, Arian ELSEVIER Association between dopa decarboxylase gene variants and borderline personality disorder 2014 the journal of the Pattern Recognition Society Amsterdam (DE-627)ELV017326583 volume:114 year:2021 pages:0 https://doi.org/10.1016/j.patcog.2021.107868 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U AR 114 2021 0 |
language |
English |
source |
Enthalten in Association between dopa decarboxylase gene variants and borderline personality disorder Amsterdam volume:114 year:2021 pages:0 |
sourceStr |
Enthalten in Association between dopa decarboxylase gene variants and borderline personality disorder Amsterdam volume:114 year:2021 pages:0 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
isfreeaccess_bool |
false |
container_title |
Association between dopa decarboxylase gene variants and borderline personality disorder |
authorswithroles_txt_mv |
Sheng, Weijie @@aut@@ Li, Xinde @@oth@@ |
publishDateDaySort_date |
2021-01-01T00:00:00Z |
hierarchy_top_id |
ELV017326583 |
id |
ELV053260880 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV053260880</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626034522.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.patcog.2021.107868</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001314.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV053260880</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0031-3203(21)00055-8</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="100" ind1="1" ind2=" "><subfield code="a">Sheng, Weijie</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">• To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">• To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Xinde</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="a">Mobascher, Arian ELSEVIER</subfield><subfield code="t">Association between dopa decarboxylase gene variants and borderline personality disorder</subfield><subfield code="d">2014</subfield><subfield code="d">the journal of the Pattern Recognition Society</subfield><subfield code="g">Amsterdam</subfield><subfield code="w">(DE-627)ELV017326583</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:114</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.patcog.2021.107868</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">114</subfield><subfield code="j">2021</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
author |
Sheng, Weijie |
spellingShingle |
Sheng, Weijie Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network |
authorStr |
Sheng, Weijie |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV017326583 |
format |
electronic Article |
delete_txt_mv |
keep |
author_role |
aut |
collection |
elsevier |
remote_str |
true |
illustrated |
Not Illustrated |
topic_title |
Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
zu |
author2_variant |
x l xl |
hierarchy_parent_title |
Association between dopa decarboxylase gene variants and borderline personality disorder |
hierarchy_parent_id |
ELV017326583 |
hierarchy_top_title |
Association between dopa decarboxylase gene variants and borderline personality disorder |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)ELV017326583 |
title |
Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network |
ctrlnum |
(DE-627)ELV053260880 (ELSEVIER)S0031-3203(21)00055-8 |
title_full |
Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network |
author_sort |
Sheng, Weijie |
journal |
Association between dopa decarboxylase gene variants and borderline personality disorder |
journalStr |
Association between dopa decarboxylase gene variants and borderline personality disorder |
lang_code |
eng |
isOA_bool |
false |
recordtype |
marc |
publishDateSort |
2021 |
contenttype_str_mv |
zzz |
container_start_page |
0 |
author_browse |
Sheng, Weijie |
container_volume |
114 |
format_se |
Elektronische Aufsätze |
author-letter |
Sheng, Weijie |
doi_str_mv |
10.1016/j.patcog.2021.107868 |
title_sort |
multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network |
title_auth |
Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network |
abstract |
• To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. |
abstractGer |
• To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. |
abstract_unstemmed |
• To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset. |
collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U |
title_short |
Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network |
url |
https://doi.org/10.1016/j.patcog.2021.107868 |
remote_bool |
true |
author2 |
Li, Xinde |
author2Str |
Li, Xinde |
ppnlink |
ELV017326583 |
mediatype_str_mv |
z |
isOA_txt |
false |
hochschulschrift_bool |
false |
author2_role |
oth |
doi_str |
10.1016/j.patcog.2021.107868 |
up_date |
2024-07-06T18:27:29.628Z |
_version_ |
1803855278510178304 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV053260880</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626034522.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.patcog.2021.107868</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001314.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV053260880</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0031-3203(21)00055-8</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="100" ind1="1" ind2=" "><subfield code="a">Sheng, Weijie</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Multi-task learning for gait-based identity recognition and emotion recognition using attention enhanced temporal graph convolutional network</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">• To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">• To our knowledge, this is the first work to treat identity recognition and emotion recognition as related tasks for jointly learning. We propose a multi-task learning architecture for gait-related recognition problems and achieve better performances by sharing knowledge. • We propose a novel AT-GCN network for gait skeleton sequences, which can effectively capture discriminative spatiotemporal gait features. The attention mechanism is employed to enhance the expressive capability for achieving higher performance. • We present a new dataset of human gaits (EMOGAIT), which consists of 1, 440 real-world gait videos annotated with identity labels and emotion labels. The proposed model achieves state-of-the-art results on both EMOGAIT dataset and TUMGAID dataset.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Xinde</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="a">Mobascher, Arian ELSEVIER</subfield><subfield code="t">Association between dopa decarboxylase gene variants and borderline personality disorder</subfield><subfield code="d">2014</subfield><subfield code="d">the journal of the Pattern Recognition Society</subfield><subfield code="g">Amsterdam</subfield><subfield code="w">(DE-627)ELV017326583</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:114</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.patcog.2021.107868</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">114</subfield><subfield code="j">2021</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
score |
7.396736 |