Deep cross-view autoencoder network for multi-view learning
Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneo...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Mi, Jian-Xun [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2022 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Multimedia tools and applications - Springer US, 1995, 81(2022), 17 vom: 21. März, Seite 24645-24664 |
|---|---|
| Übergeordnetes Werk: |
volume:81 ; year:2022 ; number:17 ; day:21 ; month:03 ; pages:24645-24664 |
| Links: |
|---|
| DOI / URN: |
10.1007/s11042-022-12636-2 |
|---|
| Katalog-ID: |
OLC207905225X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC207905225X | ||
| 003 | DE-627 | ||
| 005 | 20230506033936.0 | ||
| 007 | tu | ||
| 008 | 221220s2022 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s11042-022-12636-2 |2 doi | |
| 035 | |a (DE-627)OLC207905225X | ||
| 035 | |a (DE-He213)s11042-022-12636-2-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 070 |a 004 |q VZ |
| 100 | 1 | |a Mi, Jian-Xun |e verfasserin |0 (orcid)0000-0002-7531-4341 |4 aut | |
| 245 | 1 | 0 | |a Deep cross-view autoencoder network for multi-view learning |
| 264 | 1 | |c 2022 | |
| 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 Science+Business Media, LLC, part of Springer Nature 2022 | ||
| 520 | |a Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneous recognition (cross-view recognition) in multi-view learning is still challenging due to the complex correlations among views. Multi-view subspace learning is an effective solution, which attempts to obtain a common representation from downstream computations. Most previous methods are based on the idea of maximal correlation after feature extraction to establish the relationship among different views in a two-step manner, thus leading to performance deterioration. To overcome this drawback, in this paper, we propose a deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner. Specifically, DCVAE contains self-reconstruction, newly designed cross-view reconstruction, and consistency constraint modules. Self-reconstruction ensures the view-specific, cross-view reconstruction transfers the information from one view to another view, and consistency constraint makes the representation of different views more consistent. The proposed model suffices to discover the complex correlation embedded in multi-view data and to integrate heterogeneous views into a latent common representation subspace. Furthermore, the 2D embeddings of the learned common representation subspace demonstrate the consistency constraint is valid and cross-view classification experiments verify the superior performance of DCVAE in the two-view scenario. | ||
| 650 | 4 | |a Multi-view learning | |
| 650 | 4 | |a Cross-view reconstruction | |
| 650 | 4 | |a Common representation | |
| 650 | 4 | |a Cross-view classification | |
| 650 | 4 | |a Encoding consistency | |
| 700 | 1 | |a Fu, Chang-Qing |4 aut | |
| 700 | 1 | |a Chen, Tao |4 aut | |
| 700 | 1 | |a Gou, Tingting |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Multimedia tools and applications |d Springer US, 1995 |g 81(2022), 17 vom: 21. März, Seite 24645-24664 |w (DE-627)189064145 |w (DE-600)1287642-2 |w (DE-576)052842126 |x 1380-7501 |7 nnns |
| 773 | 1 | 8 | |g volume:81 |g year:2022 |g number:17 |g day:21 |g month:03 |g pages:24645-24664 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s11042-022-12636-2 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a SSG-OLC-BUB | ||
| 912 | |a SSG-OLC-MKW | ||
| 951 | |a AR | ||
| 952 | |d 81 |j 2022 |e 17 |b 21 |c 03 |h 24645-24664 | ||
| author_variant |
j x m jxm c q f cqf t c tc t g tg |
|---|---|
| matchkey_str |
article:13807501:2022----::eprsveatecdrewrfru |
| hierarchy_sort_str |
2022 |
| publishDate |
2022 |
| allfields |
10.1007/s11042-022-12636-2 doi (DE-627)OLC207905225X (DE-He213)s11042-022-12636-2-p DE-627 ger DE-627 rakwb eng 070 004 VZ Mi, Jian-Xun verfasserin (orcid)0000-0002-7531-4341 aut Deep cross-view autoencoder network for multi-view learning 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneous recognition (cross-view recognition) in multi-view learning is still challenging due to the complex correlations among views. Multi-view subspace learning is an effective solution, which attempts to obtain a common representation from downstream computations. Most previous methods are based on the idea of maximal correlation after feature extraction to establish the relationship among different views in a two-step manner, thus leading to performance deterioration. To overcome this drawback, in this paper, we propose a deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner. Specifically, DCVAE contains self-reconstruction, newly designed cross-view reconstruction, and consistency constraint modules. Self-reconstruction ensures the view-specific, cross-view reconstruction transfers the information from one view to another view, and consistency constraint makes the representation of different views more consistent. The proposed model suffices to discover the complex correlation embedded in multi-view data and to integrate heterogeneous views into a latent common representation subspace. Furthermore, the 2D embeddings of the learned common representation subspace demonstrate the consistency constraint is valid and cross-view classification experiments verify the superior performance of DCVAE in the two-view scenario. Multi-view learning Cross-view reconstruction Common representation Cross-view classification Encoding consistency Fu, Chang-Qing aut Chen, Tao aut Gou, Tingting aut Enthalten in Multimedia tools and applications Springer US, 1995 81(2022), 17 vom: 21. März, Seite 24645-24664 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:81 year:2022 number:17 day:21 month:03 pages:24645-24664 https://doi.org/10.1007/s11042-022-12636-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW AR 81 2022 17 21 03 24645-24664 |
| spelling |
10.1007/s11042-022-12636-2 doi (DE-627)OLC207905225X (DE-He213)s11042-022-12636-2-p DE-627 ger DE-627 rakwb eng 070 004 VZ Mi, Jian-Xun verfasserin (orcid)0000-0002-7531-4341 aut Deep cross-view autoencoder network for multi-view learning 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneous recognition (cross-view recognition) in multi-view learning is still challenging due to the complex correlations among views. Multi-view subspace learning is an effective solution, which attempts to obtain a common representation from downstream computations. Most previous methods are based on the idea of maximal correlation after feature extraction to establish the relationship among different views in a two-step manner, thus leading to performance deterioration. To overcome this drawback, in this paper, we propose a deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner. Specifically, DCVAE contains self-reconstruction, newly designed cross-view reconstruction, and consistency constraint modules. Self-reconstruction ensures the view-specific, cross-view reconstruction transfers the information from one view to another view, and consistency constraint makes the representation of different views more consistent. The proposed model suffices to discover the complex correlation embedded in multi-view data and to integrate heterogeneous views into a latent common representation subspace. Furthermore, the 2D embeddings of the learned common representation subspace demonstrate the consistency constraint is valid and cross-view classification experiments verify the superior performance of DCVAE in the two-view scenario. Multi-view learning Cross-view reconstruction Common representation Cross-view classification Encoding consistency Fu, Chang-Qing aut Chen, Tao aut Gou, Tingting aut Enthalten in Multimedia tools and applications Springer US, 1995 81(2022), 17 vom: 21. März, Seite 24645-24664 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:81 year:2022 number:17 day:21 month:03 pages:24645-24664 https://doi.org/10.1007/s11042-022-12636-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW AR 81 2022 17 21 03 24645-24664 |
| allfields_unstemmed |
10.1007/s11042-022-12636-2 doi (DE-627)OLC207905225X (DE-He213)s11042-022-12636-2-p DE-627 ger DE-627 rakwb eng 070 004 VZ Mi, Jian-Xun verfasserin (orcid)0000-0002-7531-4341 aut Deep cross-view autoencoder network for multi-view learning 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneous recognition (cross-view recognition) in multi-view learning is still challenging due to the complex correlations among views. Multi-view subspace learning is an effective solution, which attempts to obtain a common representation from downstream computations. Most previous methods are based on the idea of maximal correlation after feature extraction to establish the relationship among different views in a two-step manner, thus leading to performance deterioration. To overcome this drawback, in this paper, we propose a deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner. Specifically, DCVAE contains self-reconstruction, newly designed cross-view reconstruction, and consistency constraint modules. Self-reconstruction ensures the view-specific, cross-view reconstruction transfers the information from one view to another view, and consistency constraint makes the representation of different views more consistent. The proposed model suffices to discover the complex correlation embedded in multi-view data and to integrate heterogeneous views into a latent common representation subspace. Furthermore, the 2D embeddings of the learned common representation subspace demonstrate the consistency constraint is valid and cross-view classification experiments verify the superior performance of DCVAE in the two-view scenario. Multi-view learning Cross-view reconstruction Common representation Cross-view classification Encoding consistency Fu, Chang-Qing aut Chen, Tao aut Gou, Tingting aut Enthalten in Multimedia tools and applications Springer US, 1995 81(2022), 17 vom: 21. März, Seite 24645-24664 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:81 year:2022 number:17 day:21 month:03 pages:24645-24664 https://doi.org/10.1007/s11042-022-12636-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW AR 81 2022 17 21 03 24645-24664 |
| allfieldsGer |
10.1007/s11042-022-12636-2 doi (DE-627)OLC207905225X (DE-He213)s11042-022-12636-2-p DE-627 ger DE-627 rakwb eng 070 004 VZ Mi, Jian-Xun verfasserin (orcid)0000-0002-7531-4341 aut Deep cross-view autoencoder network for multi-view learning 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneous recognition (cross-view recognition) in multi-view learning is still challenging due to the complex correlations among views. Multi-view subspace learning is an effective solution, which attempts to obtain a common representation from downstream computations. Most previous methods are based on the idea of maximal correlation after feature extraction to establish the relationship among different views in a two-step manner, thus leading to performance deterioration. To overcome this drawback, in this paper, we propose a deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner. Specifically, DCVAE contains self-reconstruction, newly designed cross-view reconstruction, and consistency constraint modules. Self-reconstruction ensures the view-specific, cross-view reconstruction transfers the information from one view to another view, and consistency constraint makes the representation of different views more consistent. The proposed model suffices to discover the complex correlation embedded in multi-view data and to integrate heterogeneous views into a latent common representation subspace. Furthermore, the 2D embeddings of the learned common representation subspace demonstrate the consistency constraint is valid and cross-view classification experiments verify the superior performance of DCVAE in the two-view scenario. Multi-view learning Cross-view reconstruction Common representation Cross-view classification Encoding consistency Fu, Chang-Qing aut Chen, Tao aut Gou, Tingting aut Enthalten in Multimedia tools and applications Springer US, 1995 81(2022), 17 vom: 21. März, Seite 24645-24664 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:81 year:2022 number:17 day:21 month:03 pages:24645-24664 https://doi.org/10.1007/s11042-022-12636-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW AR 81 2022 17 21 03 24645-24664 |
| allfieldsSound |
10.1007/s11042-022-12636-2 doi (DE-627)OLC207905225X (DE-He213)s11042-022-12636-2-p DE-627 ger DE-627 rakwb eng 070 004 VZ Mi, Jian-Xun verfasserin (orcid)0000-0002-7531-4341 aut Deep cross-view autoencoder network for multi-view learning 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneous recognition (cross-view recognition) in multi-view learning is still challenging due to the complex correlations among views. Multi-view subspace learning is an effective solution, which attempts to obtain a common representation from downstream computations. Most previous methods are based on the idea of maximal correlation after feature extraction to establish the relationship among different views in a two-step manner, thus leading to performance deterioration. To overcome this drawback, in this paper, we propose a deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner. Specifically, DCVAE contains self-reconstruction, newly designed cross-view reconstruction, and consistency constraint modules. Self-reconstruction ensures the view-specific, cross-view reconstruction transfers the information from one view to another view, and consistency constraint makes the representation of different views more consistent. The proposed model suffices to discover the complex correlation embedded in multi-view data and to integrate heterogeneous views into a latent common representation subspace. Furthermore, the 2D embeddings of the learned common representation subspace demonstrate the consistency constraint is valid and cross-view classification experiments verify the superior performance of DCVAE in the two-view scenario. Multi-view learning Cross-view reconstruction Common representation Cross-view classification Encoding consistency Fu, Chang-Qing aut Chen, Tao aut Gou, Tingting aut Enthalten in Multimedia tools and applications Springer US, 1995 81(2022), 17 vom: 21. März, Seite 24645-24664 (DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 1380-7501 nnns volume:81 year:2022 number:17 day:21 month:03 pages:24645-24664 https://doi.org/10.1007/s11042-022-12636-2 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW AR 81 2022 17 21 03 24645-24664 |
| language |
English |
| source |
Enthalten in Multimedia tools and applications 81(2022), 17 vom: 21. März, Seite 24645-24664 volume:81 year:2022 number:17 day:21 month:03 pages:24645-24664 |
| sourceStr |
Enthalten in Multimedia tools and applications 81(2022), 17 vom: 21. März, Seite 24645-24664 volume:81 year:2022 number:17 day:21 month:03 pages:24645-24664 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Multi-view learning Cross-view reconstruction Common representation Cross-view classification Encoding consistency |
| dewey-raw |
070 |
| isfreeaccess_bool |
false |
| container_title |
Multimedia tools and applications |
| authorswithroles_txt_mv |
Mi, Jian-Xun @@aut@@ Fu, Chang-Qing @@aut@@ Chen, Tao @@aut@@ Gou, Tingting @@aut@@ |
| publishDateDaySort_date |
2022-03-21T00:00:00Z |
| hierarchy_top_id |
189064145 |
| dewey-sort |
270 |
| id |
OLC207905225X |
| 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">OLC207905225X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506033936.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11042-022-12636-2</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC207905225X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11042-022-12636-2-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">070</subfield><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Mi, Jian-Xun</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-7531-4341</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep cross-view autoencoder network for multi-view learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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 Science+Business Media, LLC, part of Springer Nature 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneous recognition (cross-view recognition) in multi-view learning is still challenging due to the complex correlations among views. Multi-view subspace learning is an effective solution, which attempts to obtain a common representation from downstream computations. Most previous methods are based on the idea of maximal correlation after feature extraction to establish the relationship among different views in a two-step manner, thus leading to performance deterioration. To overcome this drawback, in this paper, we propose a deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner. Specifically, DCVAE contains self-reconstruction, newly designed cross-view reconstruction, and consistency constraint modules. Self-reconstruction ensures the view-specific, cross-view reconstruction transfers the information from one view to another view, and consistency constraint makes the representation of different views more consistent. The proposed model suffices to discover the complex correlation embedded in multi-view data and to integrate heterogeneous views into a latent common representation subspace. Furthermore, the 2D embeddings of the learned common representation subspace demonstrate the consistency constraint is valid and cross-view classification experiments verify the superior performance of DCVAE in the two-view scenario.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-view learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-view reconstruction</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Common representation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-view classification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Encoding consistency</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Fu, Chang-Qing</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Tao</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gou, Tingting</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Multimedia tools and applications</subfield><subfield code="d">Springer US, 1995</subfield><subfield code="g">81(2022), 17 vom: 21. März, Seite 24645-24664</subfield><subfield code="w">(DE-627)189064145</subfield><subfield code="w">(DE-600)1287642-2</subfield><subfield code="w">(DE-576)052842126</subfield><subfield code="x">1380-7501</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:81</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:17</subfield><subfield code="g">day:21</subfield><subfield code="g">month:03</subfield><subfield code="g">pages:24645-24664</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11042-022-12636-2</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="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-BUB</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MKW</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">81</subfield><subfield code="j">2022</subfield><subfield code="e">17</subfield><subfield code="b">21</subfield><subfield code="c">03</subfield><subfield code="h">24645-24664</subfield></datafield></record></collection>
|
| author |
Mi, Jian-Xun |
| spellingShingle |
Mi, Jian-Xun ddc 070 misc Multi-view learning misc Cross-view reconstruction misc Common representation misc Cross-view classification misc Encoding consistency Deep cross-view autoencoder network for multi-view learning |
| authorStr |
Mi, Jian-Xun |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)189064145 |
| format |
Article |
| dewey-ones |
070 - News media, journalism & publishing 004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
1380-7501 |
| topic_title |
070 004 VZ Deep cross-view autoencoder network for multi-view learning Multi-view learning Cross-view reconstruction Common representation Cross-view classification Encoding consistency |
| topic |
ddc 070 misc Multi-view learning misc Cross-view reconstruction misc Common representation misc Cross-view classification misc Encoding consistency |
| topic_unstemmed |
ddc 070 misc Multi-view learning misc Cross-view reconstruction misc Common representation misc Cross-view classification misc Encoding consistency |
| topic_browse |
ddc 070 misc Multi-view learning misc Cross-view reconstruction misc Common representation misc Cross-view classification misc Encoding consistency |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Multimedia tools and applications |
| hierarchy_parent_id |
189064145 |
| dewey-tens |
070 - News media, journalism & publishing 000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Multimedia tools and applications |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)189064145 (DE-600)1287642-2 (DE-576)052842126 |
| title |
Deep cross-view autoencoder network for multi-view learning |
| ctrlnum |
(DE-627)OLC207905225X (DE-He213)s11042-022-12636-2-p |
| title_full |
Deep cross-view autoencoder network for multi-view learning |
| author_sort |
Mi, Jian-Xun |
| journal |
Multimedia tools and applications |
| journalStr |
Multimedia tools and applications |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2022 |
| contenttype_str_mv |
txt |
| container_start_page |
24645 |
| author_browse |
Mi, Jian-Xun Fu, Chang-Qing Chen, Tao Gou, Tingting |
| container_volume |
81 |
| class |
070 004 VZ |
| format_se |
Aufsätze |
| author-letter |
Mi, Jian-Xun |
| doi_str_mv |
10.1007/s11042-022-12636-2 |
| normlink |
(ORCID)0000-0002-7531-4341 |
| normlink_prefix_str_mv |
(orcid)0000-0002-7531-4341 |
| dewey-full |
070 004 |
| title_sort |
deep cross-view autoencoder network for multi-view learning |
| title_auth |
Deep cross-view autoencoder network for multi-view learning |
| abstract |
Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneous recognition (cross-view recognition) in multi-view learning is still challenging due to the complex correlations among views. Multi-view subspace learning is an effective solution, which attempts to obtain a common representation from downstream computations. Most previous methods are based on the idea of maximal correlation after feature extraction to establish the relationship among different views in a two-step manner, thus leading to performance deterioration. To overcome this drawback, in this paper, we propose a deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner. Specifically, DCVAE contains self-reconstruction, newly designed cross-view reconstruction, and consistency constraint modules. Self-reconstruction ensures the view-specific, cross-view reconstruction transfers the information from one view to another view, and consistency constraint makes the representation of different views more consistent. The proposed model suffices to discover the complex correlation embedded in multi-view data and to integrate heterogeneous views into a latent common representation subspace. Furthermore, the 2D embeddings of the learned common representation subspace demonstrate the consistency constraint is valid and cross-view classification experiments verify the superior performance of DCVAE in the two-view scenario. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 |
| abstractGer |
Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneous recognition (cross-view recognition) in multi-view learning is still challenging due to the complex correlations among views. Multi-view subspace learning is an effective solution, which attempts to obtain a common representation from downstream computations. Most previous methods are based on the idea of maximal correlation after feature extraction to establish the relationship among different views in a two-step manner, thus leading to performance deterioration. To overcome this drawback, in this paper, we propose a deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner. Specifically, DCVAE contains self-reconstruction, newly designed cross-view reconstruction, and consistency constraint modules. Self-reconstruction ensures the view-specific, cross-view reconstruction transfers the information from one view to another view, and consistency constraint makes the representation of different views more consistent. The proposed model suffices to discover the complex correlation embedded in multi-view data and to integrate heterogeneous views into a latent common representation subspace. Furthermore, the 2D embeddings of the learned common representation subspace demonstrate the consistency constraint is valid and cross-view classification experiments verify the superior performance of DCVAE in the two-view scenario. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 |
| abstract_unstemmed |
Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneous recognition (cross-view recognition) in multi-view learning is still challenging due to the complex correlations among views. Multi-view subspace learning is an effective solution, which attempts to obtain a common representation from downstream computations. Most previous methods are based on the idea of maximal correlation after feature extraction to establish the relationship among different views in a two-step manner, thus leading to performance deterioration. To overcome this drawback, in this paper, we propose a deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner. Specifically, DCVAE contains self-reconstruction, newly designed cross-view reconstruction, and consistency constraint modules. Self-reconstruction ensures the view-specific, cross-view reconstruction transfers the information from one view to another view, and consistency constraint makes the representation of different views more consistent. The proposed model suffices to discover the complex correlation embedded in multi-view data and to integrate heterogeneous views into a latent common representation subspace. Furthermore, the 2D embeddings of the learned common representation subspace demonstrate the consistency constraint is valid and cross-view classification experiments verify the superior performance of DCVAE in the two-view scenario. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-BUB SSG-OLC-MKW |
| container_issue |
17 |
| title_short |
Deep cross-view autoencoder network for multi-view learning |
| url |
https://doi.org/10.1007/s11042-022-12636-2 |
| remote_bool |
false |
| author2 |
Fu, Chang-Qing Chen, Tao Gou, Tingting |
| author2Str |
Fu, Chang-Qing Chen, Tao Gou, Tingting |
| ppnlink |
189064145 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s11042-022-12636-2 |
| up_date |
2024-07-03T23:18:36.645Z |
| _version_ |
1803601803108941824 |
| 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">OLC207905225X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506033936.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11042-022-12636-2</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC207905225X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11042-022-12636-2-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">070</subfield><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Mi, Jian-Xun</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-7531-4341</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep cross-view autoencoder network for multi-view learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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 Science+Business Media, LLC, part of Springer Nature 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In many real-world applications, an increasing number of objects can be collected at varying viewpoints or by different sensors, which brings in the urgent demand for recognizing objects from distinct heterogeneous views. Although significant progress has been achieved recently, heterogeneous recognition (cross-view recognition) in multi-view learning is still challenging due to the complex correlations among views. Multi-view subspace learning is an effective solution, which attempts to obtain a common representation from downstream computations. Most previous methods are based on the idea of maximal correlation after feature extraction to establish the relationship among different views in a two-step manner, thus leading to performance deterioration. To overcome this drawback, in this paper, we propose a deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner. Specifically, DCVAE contains self-reconstruction, newly designed cross-view reconstruction, and consistency constraint modules. Self-reconstruction ensures the view-specific, cross-view reconstruction transfers the information from one view to another view, and consistency constraint makes the representation of different views more consistent. The proposed model suffices to discover the complex correlation embedded in multi-view data and to integrate heterogeneous views into a latent common representation subspace. Furthermore, the 2D embeddings of the learned common representation subspace demonstrate the consistency constraint is valid and cross-view classification experiments verify the superior performance of DCVAE in the two-view scenario.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-view learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-view reconstruction</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Common representation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Cross-view classification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Encoding consistency</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Fu, Chang-Qing</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Tao</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gou, Tingting</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Multimedia tools and applications</subfield><subfield code="d">Springer US, 1995</subfield><subfield code="g">81(2022), 17 vom: 21. März, Seite 24645-24664</subfield><subfield code="w">(DE-627)189064145</subfield><subfield code="w">(DE-600)1287642-2</subfield><subfield code="w">(DE-576)052842126</subfield><subfield code="x">1380-7501</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:81</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:17</subfield><subfield code="g">day:21</subfield><subfield code="g">month:03</subfield><subfield code="g">pages:24645-24664</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11042-022-12636-2</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="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-BUB</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MKW</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">81</subfield><subfield code="j">2022</subfield><subfield code="e">17</subfield><subfield code="b">21</subfield><subfield code="c">03</subfield><subfield code="h">24645-24664</subfield></datafield></record></collection>
|
| score |
7.400985 |