Multi-Modal Curriculum Learning for Semi-Supervised Image Classification
Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because t...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Gong, Chen [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2016 |
|---|
| Schlagwörter: |
Object recognition (Computers) |
|---|
| Übergeordnetes Werk: |
Enthalten in: IEEE transactions on image processing - New York, NY : Inst., 1992, 25(2016), 7, Seite 3249-3260 |
|---|---|
| Übergeordnetes Werk: |
volume:25 ; year:2016 ; number:7 ; pages:3249-3260 |
| Links: |
|---|
| DOI / URN: |
10.1109/TIP.2016.2563981 |
|---|
| Katalog-ID: |
OLC1979422788 |
|---|
| LEADER | 01000caa a2200265 4500 | ||
|---|---|---|---|
| 001 | OLC1979422788 | ||
| 003 | DE-627 | ||
| 005 | 20230714203613.0 | ||
| 007 | tu | ||
| 008 | 160720s2016 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TIP.2016.2563981 |2 doi | |
| 028 | 5 | 2 | |a PQ20160815 |
| 035 | |a (DE-627)OLC1979422788 | ||
| 035 | |a (DE-599)GBVOLC1979422788 | ||
| 035 | |a (PRQ)g764-e6c1a81315a8c66fc1b7f1f51651d15bc76fcc6e4c8dbdc8f23bba5b9bf25e1c0 | ||
| 035 | |a (KEY)0213811520160000025000703249multimodalcurriculumlearningforsemisupervisedimage | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 004 |a 620 |q DNB |
| 084 | |a 54.00 |2 bkl | ||
| 100 | 1 | |a Gong, Chen |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Multi-Modal Curriculum Learning for Semi-Supervised Image Classification |
| 264 | 1 | |c 2016 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 520 | |a Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets. | ||
| 650 | 4 | |a Semi-supervised learning | |
| 650 | 4 | |a Pattern recognition | |
| 650 | 4 | |a Multi-modal | |
| 650 | 4 | |a Curriculum learning | |
| 650 | 4 | |a Reliability | |
| 650 | 4 | |a Image classification | |
| 650 | 4 | |a Electronic mail | |
| 650 | 4 | |a Image processing | |
| 650 | 4 | |a Visualization | |
| 650 | 4 | |a Semisupervised learning | |
| 650 | 4 | |a Kernel | |
| 650 | 4 | |a Management | |
| 650 | 4 | |a Electronic mail systems | |
| 650 | 4 | |a Object recognition (Computers) | |
| 650 | 4 | |a Training | |
| 650 | 4 | |a Iterative methods (Mathematics) | |
| 650 | 4 | |a Teacher centers | |
| 650 | 4 | |a Teachers | |
| 650 | 4 | |a Usage | |
| 700 | 1 | |a Tao, Dacheng |4 oth | |
| 700 | 1 | |a Maybank, Stephen J |4 oth | |
| 700 | 1 | |a Liu, Wei |4 oth | |
| 700 | 1 | |a Kang, Guoliang |4 oth | |
| 700 | 1 | |a Yang, Jie |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE transactions on image processing |d New York, NY : Inst., 1992 |g 25(2016), 7, Seite 3249-3260 |w (DE-627)131074458 |w (DE-600)1111265-7 |w (DE-576)029165008 |x 1057-7149 |7 nnns |
| 773 | 1 | 8 | |g volume:25 |g year:2016 |g number:7 |g pages:3249-3260 |
| 856 | 4 | 1 | |u http://dx.doi.org/10.1109/TIP.2016.2563981 |3 Volltext |
| 856 | 4 | 2 | |u http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7465792 |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-TEC | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_2005 | ||
| 936 | b | k | |a 54.00 |q AVZ |
| 951 | |a AR | ||
| 952 | |d 25 |j 2016 |e 7 |h 3249-3260 | ||
| author_variant |
c g cg |
|---|---|
| matchkey_str |
article:10577149:2016----::utmdlurclmerigosmsprieia |
| hierarchy_sort_str |
2016 |
| bklnumber |
54.00 |
| publishDate |
2016 |
| allfields |
10.1109/TIP.2016.2563981 doi PQ20160815 (DE-627)OLC1979422788 (DE-599)GBVOLC1979422788 (PRQ)g764-e6c1a81315a8c66fc1b7f1f51651d15bc76fcc6e4c8dbdc8f23bba5b9bf25e1c0 (KEY)0213811520160000025000703249multimodalcurriculumlearningforsemisupervisedimage DE-627 ger DE-627 rakwb eng 004 620 DNB 54.00 bkl Gong, Chen verfasserin aut Multi-Modal Curriculum Learning for Semi-Supervised Image Classification 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets. Semi-supervised learning Pattern recognition Multi-modal Curriculum learning Reliability Image classification Electronic mail Image processing Visualization Semisupervised learning Kernel Management Electronic mail systems Object recognition (Computers) Training Iterative methods (Mathematics) Teacher centers Teachers Usage Tao, Dacheng oth Maybank, Stephen J oth Liu, Wei oth Kang, Guoliang oth Yang, Jie oth Enthalten in IEEE transactions on image processing New York, NY : Inst., 1992 25(2016), 7, Seite 3249-3260 (DE-627)131074458 (DE-600)1111265-7 (DE-576)029165008 1057-7149 nnns volume:25 year:2016 number:7 pages:3249-3260 http://dx.doi.org/10.1109/TIP.2016.2563981 Volltext http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7465792 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2005 54.00 AVZ AR 25 2016 7 3249-3260 |
| spelling |
10.1109/TIP.2016.2563981 doi PQ20160815 (DE-627)OLC1979422788 (DE-599)GBVOLC1979422788 (PRQ)g764-e6c1a81315a8c66fc1b7f1f51651d15bc76fcc6e4c8dbdc8f23bba5b9bf25e1c0 (KEY)0213811520160000025000703249multimodalcurriculumlearningforsemisupervisedimage DE-627 ger DE-627 rakwb eng 004 620 DNB 54.00 bkl Gong, Chen verfasserin aut Multi-Modal Curriculum Learning for Semi-Supervised Image Classification 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets. Semi-supervised learning Pattern recognition Multi-modal Curriculum learning Reliability Image classification Electronic mail Image processing Visualization Semisupervised learning Kernel Management Electronic mail systems Object recognition (Computers) Training Iterative methods (Mathematics) Teacher centers Teachers Usage Tao, Dacheng oth Maybank, Stephen J oth Liu, Wei oth Kang, Guoliang oth Yang, Jie oth Enthalten in IEEE transactions on image processing New York, NY : Inst., 1992 25(2016), 7, Seite 3249-3260 (DE-627)131074458 (DE-600)1111265-7 (DE-576)029165008 1057-7149 nnns volume:25 year:2016 number:7 pages:3249-3260 http://dx.doi.org/10.1109/TIP.2016.2563981 Volltext http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7465792 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2005 54.00 AVZ AR 25 2016 7 3249-3260 |
| allfields_unstemmed |
10.1109/TIP.2016.2563981 doi PQ20160815 (DE-627)OLC1979422788 (DE-599)GBVOLC1979422788 (PRQ)g764-e6c1a81315a8c66fc1b7f1f51651d15bc76fcc6e4c8dbdc8f23bba5b9bf25e1c0 (KEY)0213811520160000025000703249multimodalcurriculumlearningforsemisupervisedimage DE-627 ger DE-627 rakwb eng 004 620 DNB 54.00 bkl Gong, Chen verfasserin aut Multi-Modal Curriculum Learning for Semi-Supervised Image Classification 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets. Semi-supervised learning Pattern recognition Multi-modal Curriculum learning Reliability Image classification Electronic mail Image processing Visualization Semisupervised learning Kernel Management Electronic mail systems Object recognition (Computers) Training Iterative methods (Mathematics) Teacher centers Teachers Usage Tao, Dacheng oth Maybank, Stephen J oth Liu, Wei oth Kang, Guoliang oth Yang, Jie oth Enthalten in IEEE transactions on image processing New York, NY : Inst., 1992 25(2016), 7, Seite 3249-3260 (DE-627)131074458 (DE-600)1111265-7 (DE-576)029165008 1057-7149 nnns volume:25 year:2016 number:7 pages:3249-3260 http://dx.doi.org/10.1109/TIP.2016.2563981 Volltext http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7465792 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2005 54.00 AVZ AR 25 2016 7 3249-3260 |
| allfieldsGer |
10.1109/TIP.2016.2563981 doi PQ20160815 (DE-627)OLC1979422788 (DE-599)GBVOLC1979422788 (PRQ)g764-e6c1a81315a8c66fc1b7f1f51651d15bc76fcc6e4c8dbdc8f23bba5b9bf25e1c0 (KEY)0213811520160000025000703249multimodalcurriculumlearningforsemisupervisedimage DE-627 ger DE-627 rakwb eng 004 620 DNB 54.00 bkl Gong, Chen verfasserin aut Multi-Modal Curriculum Learning for Semi-Supervised Image Classification 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets. Semi-supervised learning Pattern recognition Multi-modal Curriculum learning Reliability Image classification Electronic mail Image processing Visualization Semisupervised learning Kernel Management Electronic mail systems Object recognition (Computers) Training Iterative methods (Mathematics) Teacher centers Teachers Usage Tao, Dacheng oth Maybank, Stephen J oth Liu, Wei oth Kang, Guoliang oth Yang, Jie oth Enthalten in IEEE transactions on image processing New York, NY : Inst., 1992 25(2016), 7, Seite 3249-3260 (DE-627)131074458 (DE-600)1111265-7 (DE-576)029165008 1057-7149 nnns volume:25 year:2016 number:7 pages:3249-3260 http://dx.doi.org/10.1109/TIP.2016.2563981 Volltext http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7465792 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2005 54.00 AVZ AR 25 2016 7 3249-3260 |
| allfieldsSound |
10.1109/TIP.2016.2563981 doi PQ20160815 (DE-627)OLC1979422788 (DE-599)GBVOLC1979422788 (PRQ)g764-e6c1a81315a8c66fc1b7f1f51651d15bc76fcc6e4c8dbdc8f23bba5b9bf25e1c0 (KEY)0213811520160000025000703249multimodalcurriculumlearningforsemisupervisedimage DE-627 ger DE-627 rakwb eng 004 620 DNB 54.00 bkl Gong, Chen verfasserin aut Multi-Modal Curriculum Learning for Semi-Supervised Image Classification 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets. Semi-supervised learning Pattern recognition Multi-modal Curriculum learning Reliability Image classification Electronic mail Image processing Visualization Semisupervised learning Kernel Management Electronic mail systems Object recognition (Computers) Training Iterative methods (Mathematics) Teacher centers Teachers Usage Tao, Dacheng oth Maybank, Stephen J oth Liu, Wei oth Kang, Guoliang oth Yang, Jie oth Enthalten in IEEE transactions on image processing New York, NY : Inst., 1992 25(2016), 7, Seite 3249-3260 (DE-627)131074458 (DE-600)1111265-7 (DE-576)029165008 1057-7149 nnns volume:25 year:2016 number:7 pages:3249-3260 http://dx.doi.org/10.1109/TIP.2016.2563981 Volltext http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7465792 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2005 54.00 AVZ AR 25 2016 7 3249-3260 |
| language |
English |
| source |
Enthalten in IEEE transactions on image processing 25(2016), 7, Seite 3249-3260 volume:25 year:2016 number:7 pages:3249-3260 |
| sourceStr |
Enthalten in IEEE transactions on image processing 25(2016), 7, Seite 3249-3260 volume:25 year:2016 number:7 pages:3249-3260 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Semi-supervised learning Pattern recognition Multi-modal Curriculum learning Reliability Image classification Electronic mail Image processing Visualization Semisupervised learning Kernel Management Electronic mail systems Object recognition (Computers) Training Iterative methods (Mathematics) Teacher centers Teachers Usage |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
IEEE transactions on image processing |
| authorswithroles_txt_mv |
Gong, Chen @@aut@@ Tao, Dacheng @@oth@@ Maybank, Stephen J @@oth@@ Liu, Wei @@oth@@ Kang, Guoliang @@oth@@ Yang, Jie @@oth@@ |
| publishDateDaySort_date |
2016-01-01T00:00:00Z |
| hierarchy_top_id |
131074458 |
| dewey-sort |
14 |
| id |
OLC1979422788 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a2200265 4500</leader><controlfield tag="001">OLC1979422788</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230714203613.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">160720s2016 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/TIP.2016.2563981</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">PQ20160815</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC1979422788</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)GBVOLC1979422788</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(PRQ)g764-e6c1a81315a8c66fc1b7f1f51651d15bc76fcc6e4c8dbdc8f23bba5b9bf25e1c0</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(KEY)0213811520160000025000703249multimodalcurriculumlearningforsemisupervisedimage</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">620</subfield><subfield code="q">DNB</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Gong, Chen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Multi-Modal Curriculum Learning for Semi-Supervised Image Classification</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Semi-supervised learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pattern recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-modal</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Curriculum learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Reliability</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image classification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Electronic mail</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image processing</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visualization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Semisupervised learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Kernel</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Management</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Electronic mail systems</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Object recognition (Computers)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Training</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Iterative methods (Mathematics)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Teacher centers</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Teachers</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Usage</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Tao, Dacheng</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Maybank, Stephen J</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Wei</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kang, Guoliang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yang, Jie</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">IEEE transactions on image processing</subfield><subfield code="d">New York, NY : Inst., 1992</subfield><subfield code="g">25(2016), 7, Seite 3249-3260</subfield><subfield code="w">(DE-627)131074458</subfield><subfield code="w">(DE-600)1111265-7</subfield><subfield code="w">(DE-576)029165008</subfield><subfield code="x">1057-7149</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:25</subfield><subfield code="g">year:2016</subfield><subfield code="g">number:7</subfield><subfield code="g">pages:3249-3260</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">http://dx.doi.org/10.1109/TIP.2016.2563981</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7465792</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-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.00</subfield><subfield code="q">AVZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">25</subfield><subfield code="j">2016</subfield><subfield code="e">7</subfield><subfield code="h">3249-3260</subfield></datafield></record></collection>
|
| author |
Gong, Chen |
| spellingShingle |
Gong, Chen ddc 004 bkl 54.00 misc Semi-supervised learning misc Pattern recognition misc Multi-modal misc Curriculum learning misc Reliability misc Image classification misc Electronic mail misc Image processing misc Visualization misc Semisupervised learning misc Kernel misc Management misc Electronic mail systems misc Object recognition (Computers) misc Training misc Iterative methods (Mathematics) misc Teacher centers misc Teachers misc Usage Multi-Modal Curriculum Learning for Semi-Supervised Image Classification |
| authorStr |
Gong, Chen |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)131074458 |
| format |
Article |
| dewey-ones |
004 - Data processing & computer science 620 - Engineering & allied operations |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
1057-7149 |
| topic_title |
004 620 DNB 54.00 bkl Multi-Modal Curriculum Learning for Semi-Supervised Image Classification Semi-supervised learning Pattern recognition Multi-modal Curriculum learning Reliability Image classification Electronic mail Image processing Visualization Semisupervised learning Kernel Management Electronic mail systems Object recognition (Computers) Training Iterative methods (Mathematics) Teacher centers Teachers Usage |
| topic |
ddc 004 bkl 54.00 misc Semi-supervised learning misc Pattern recognition misc Multi-modal misc Curriculum learning misc Reliability misc Image classification misc Electronic mail misc Image processing misc Visualization misc Semisupervised learning misc Kernel misc Management misc Electronic mail systems misc Object recognition (Computers) misc Training misc Iterative methods (Mathematics) misc Teacher centers misc Teachers misc Usage |
| topic_unstemmed |
ddc 004 bkl 54.00 misc Semi-supervised learning misc Pattern recognition misc Multi-modal misc Curriculum learning misc Reliability misc Image classification misc Electronic mail misc Image processing misc Visualization misc Semisupervised learning misc Kernel misc Management misc Electronic mail systems misc Object recognition (Computers) misc Training misc Iterative methods (Mathematics) misc Teacher centers misc Teachers misc Usage |
| topic_browse |
ddc 004 bkl 54.00 misc Semi-supervised learning misc Pattern recognition misc Multi-modal misc Curriculum learning misc Reliability misc Image classification misc Electronic mail misc Image processing misc Visualization misc Semisupervised learning misc Kernel misc Management misc Electronic mail systems misc Object recognition (Computers) misc Training misc Iterative methods (Mathematics) misc Teacher centers misc Teachers misc Usage |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| author2_variant |
d t dt s j m sj sjm w l wl g k gk j y jy |
| hierarchy_parent_title |
IEEE transactions on image processing |
| hierarchy_parent_id |
131074458 |
| dewey-tens |
000 - Computer science, knowledge & systems 620 - Engineering |
| hierarchy_top_title |
IEEE transactions on image processing |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)131074458 (DE-600)1111265-7 (DE-576)029165008 |
| title |
Multi-Modal Curriculum Learning for Semi-Supervised Image Classification |
| ctrlnum |
(DE-627)OLC1979422788 (DE-599)GBVOLC1979422788 (PRQ)g764-e6c1a81315a8c66fc1b7f1f51651d15bc76fcc6e4c8dbdc8f23bba5b9bf25e1c0 (KEY)0213811520160000025000703249multimodalcurriculumlearningforsemisupervisedimage |
| title_full |
Multi-Modal Curriculum Learning for Semi-Supervised Image Classification |
| author_sort |
Gong, Chen |
| journal |
IEEE transactions on image processing |
| journalStr |
IEEE transactions on image processing |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works 600 - Technology |
| recordtype |
marc |
| publishDateSort |
2016 |
| contenttype_str_mv |
txt |
| container_start_page |
3249 |
| author_browse |
Gong, Chen |
| container_volume |
25 |
| class |
004 620 DNB 54.00 bkl |
| format_se |
Aufsätze |
| author-letter |
Gong, Chen |
| doi_str_mv |
10.1109/TIP.2016.2563981 |
| dewey-full |
004 620 |
| title_sort |
multi-modal curriculum learning for semi-supervised image classification |
| title_auth |
Multi-Modal Curriculum Learning for Semi-Supervised Image Classification |
| abstract |
Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets. |
| abstractGer |
Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets. |
| abstract_unstemmed |
Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2005 |
| container_issue |
7 |
| title_short |
Multi-Modal Curriculum Learning for Semi-Supervised Image Classification |
| url |
http://dx.doi.org/10.1109/TIP.2016.2563981 http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7465792 |
| remote_bool |
false |
| author2 |
Tao, Dacheng Maybank, Stephen J Liu, Wei Kang, Guoliang Yang, Jie |
| author2Str |
Tao, Dacheng Maybank, Stephen J Liu, Wei Kang, Guoliang Yang, Jie |
| ppnlink |
131074458 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth oth oth oth |
| doi_str |
10.1109/TIP.2016.2563981 |
| up_date |
2024-07-04T00:56:57.247Z |
| _version_ |
1803607990337536000 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a2200265 4500</leader><controlfield tag="001">OLC1979422788</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230714203613.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">160720s2016 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/TIP.2016.2563981</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">PQ20160815</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC1979422788</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)GBVOLC1979422788</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(PRQ)g764-e6c1a81315a8c66fc1b7f1f51651d15bc76fcc6e4c8dbdc8f23bba5b9bf25e1c0</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(KEY)0213811520160000025000703249multimodalcurriculumlearningforsemisupervisedimage</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">620</subfield><subfield code="q">DNB</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Gong, Chen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Multi-Modal Curriculum Learning for Semi-Supervised Image Classification</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Semi-supervised learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pattern recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-modal</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Curriculum learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Reliability</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image classification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Electronic mail</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Image processing</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visualization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Semisupervised learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Kernel</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Management</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Electronic mail systems</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Object recognition (Computers)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Training</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Iterative methods (Mathematics)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Teacher centers</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Teachers</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Usage</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Tao, Dacheng</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Maybank, Stephen J</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Wei</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kang, Guoliang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yang, Jie</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">IEEE transactions on image processing</subfield><subfield code="d">New York, NY : Inst., 1992</subfield><subfield code="g">25(2016), 7, Seite 3249-3260</subfield><subfield code="w">(DE-627)131074458</subfield><subfield code="w">(DE-600)1111265-7</subfield><subfield code="w">(DE-576)029165008</subfield><subfield code="x">1057-7149</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:25</subfield><subfield code="g">year:2016</subfield><subfield code="g">number:7</subfield><subfield code="g">pages:3249-3260</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">http://dx.doi.org/10.1109/TIP.2016.2563981</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7465792</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-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.00</subfield><subfield code="q">AVZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">25</subfield><subfield code="j">2016</subfield><subfield code="e">7</subfield><subfield code="h">3249-3260</subfield></datafield></record></collection>
|
| score |
7.4012613 |