An end-to-end network for co-saliency detection in one single image
Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and th...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Yue, Yuanhao [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2023 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© Science China Press 2023 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Science in China - Heidelberg : Springer, 2001, 66(2023), 11 vom: 17. Mai |
|---|---|
| Übergeordnetes Werk: |
volume:66 ; year:2023 ; number:11 ; day:17 ; month:05 |
| Links: |
|---|
| DOI / URN: |
10.1007/s11432-022-3686-1 |
|---|
| Katalog-ID: |
SPR051583836 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | SPR051583836 | ||
| 003 | DE-627 | ||
| 005 | 20230523064717.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230523s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s11432-022-3686-1 |2 doi | |
| 035 | |a (DE-627)SPR051583836 | ||
| 035 | |a (SPR)s11432-022-3686-1-e | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Yue, Yuanhao |e verfasserin |4 aut | |
| 245 | 1 | 3 | |a An end-to-end network for co-saliency detection in one single image |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a © Science China Press 2023 | ||
| 520 | |a Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps. | ||
| 650 | 4 | |a saliency detection |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a convolutional neural network |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a regional feature mapping |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a co-saliency detection |7 (dpeaa)DE-He213 | |
| 650 | 4 | |a deep learning |7 (dpeaa)DE-He213 | |
| 700 | 1 | |a Zou, Qin |4 aut | |
| 700 | 1 | |a Yu, Hongkai |4 aut | |
| 700 | 1 | |a Wang, Qian |4 aut | |
| 700 | 1 | |a Wang, Zhongyuan |4 aut | |
| 700 | 1 | |a Wang, Song |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Science in China |d Heidelberg : Springer, 2001 |g 66(2023), 11 vom: 17. Mai |w (DE-627)385614764 |w (DE-600)2142898-0 |x 1862-2836 |7 nnns |
| 773 | 1 | 8 | |g volume:66 |g year:2023 |g number:11 |g day:17 |g month:05 |
| 856 | 4 | 0 | |u https://dx.doi.org/10.1007/s11432-022-3686-1 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_SPRINGER | ||
| 912 | |a GBV_ILN_20 | ||
| 912 | |a GBV_ILN_22 | ||
| 912 | |a GBV_ILN_23 | ||
| 912 | |a GBV_ILN_24 | ||
| 912 | |a GBV_ILN_31 | ||
| 912 | |a GBV_ILN_32 | ||
| 912 | |a GBV_ILN_39 | ||
| 912 | |a GBV_ILN_40 | ||
| 912 | |a GBV_ILN_60 | ||
| 912 | |a GBV_ILN_62 | ||
| 912 | |a GBV_ILN_65 | ||
| 912 | |a GBV_ILN_69 | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_73 | ||
| 912 | |a GBV_ILN_74 | ||
| 912 | |a GBV_ILN_90 | ||
| 912 | |a GBV_ILN_95 | ||
| 912 | |a GBV_ILN_100 | ||
| 912 | |a GBV_ILN_101 | ||
| 912 | |a GBV_ILN_105 | ||
| 912 | |a GBV_ILN_110 | ||
| 912 | |a GBV_ILN_120 | ||
| 912 | |a GBV_ILN_138 | ||
| 912 | |a GBV_ILN_152 | ||
| 912 | |a GBV_ILN_161 | ||
| 912 | |a GBV_ILN_171 | ||
| 912 | |a GBV_ILN_187 | ||
| 912 | |a GBV_ILN_224 | ||
| 912 | |a GBV_ILN_250 | ||
| 912 | |a GBV_ILN_281 | ||
| 912 | |a GBV_ILN_285 | ||
| 912 | |a GBV_ILN_293 | ||
| 912 | |a GBV_ILN_370 | ||
| 912 | |a GBV_ILN_602 | ||
| 912 | |a GBV_ILN_702 | ||
| 951 | |a AR | ||
| 952 | |d 66 |j 2023 |e 11 |b 17 |c 05 | ||
| author_variant |
y y yy q z qz h y hy q w qw z w zw s w sw |
|---|---|
| matchkey_str |
article:18622836:2023----::nntedewrfroainyeeto |
| hierarchy_sort_str |
2023 |
| publishDate |
2023 |
| allfields |
10.1007/s11432-022-3686-1 doi (DE-627)SPR051583836 (SPR)s11432-022-3686-1-e DE-627 ger DE-627 rakwb eng Yue, Yuanhao verfasserin aut An end-to-end network for co-saliency detection in one single image 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Science China Press 2023 Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps. saliency detection (dpeaa)DE-He213 convolutional neural network (dpeaa)DE-He213 regional feature mapping (dpeaa)DE-He213 co-saliency detection (dpeaa)DE-He213 deep learning (dpeaa)DE-He213 Zou, Qin aut Yu, Hongkai aut Wang, Qian aut Wang, Zhongyuan aut Wang, Song aut Enthalten in Science in China Heidelberg : Springer, 2001 66(2023), 11 vom: 17. Mai (DE-627)385614764 (DE-600)2142898-0 1862-2836 nnns volume:66 year:2023 number:11 day:17 month:05 https://dx.doi.org/10.1007/s11432-022-3686-1 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 AR 66 2023 11 17 05 |
| spelling |
10.1007/s11432-022-3686-1 doi (DE-627)SPR051583836 (SPR)s11432-022-3686-1-e DE-627 ger DE-627 rakwb eng Yue, Yuanhao verfasserin aut An end-to-end network for co-saliency detection in one single image 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Science China Press 2023 Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps. saliency detection (dpeaa)DE-He213 convolutional neural network (dpeaa)DE-He213 regional feature mapping (dpeaa)DE-He213 co-saliency detection (dpeaa)DE-He213 deep learning (dpeaa)DE-He213 Zou, Qin aut Yu, Hongkai aut Wang, Qian aut Wang, Zhongyuan aut Wang, Song aut Enthalten in Science in China Heidelberg : Springer, 2001 66(2023), 11 vom: 17. Mai (DE-627)385614764 (DE-600)2142898-0 1862-2836 nnns volume:66 year:2023 number:11 day:17 month:05 https://dx.doi.org/10.1007/s11432-022-3686-1 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 AR 66 2023 11 17 05 |
| allfields_unstemmed |
10.1007/s11432-022-3686-1 doi (DE-627)SPR051583836 (SPR)s11432-022-3686-1-e DE-627 ger DE-627 rakwb eng Yue, Yuanhao verfasserin aut An end-to-end network for co-saliency detection in one single image 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Science China Press 2023 Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps. saliency detection (dpeaa)DE-He213 convolutional neural network (dpeaa)DE-He213 regional feature mapping (dpeaa)DE-He213 co-saliency detection (dpeaa)DE-He213 deep learning (dpeaa)DE-He213 Zou, Qin aut Yu, Hongkai aut Wang, Qian aut Wang, Zhongyuan aut Wang, Song aut Enthalten in Science in China Heidelberg : Springer, 2001 66(2023), 11 vom: 17. Mai (DE-627)385614764 (DE-600)2142898-0 1862-2836 nnns volume:66 year:2023 number:11 day:17 month:05 https://dx.doi.org/10.1007/s11432-022-3686-1 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 AR 66 2023 11 17 05 |
| allfieldsGer |
10.1007/s11432-022-3686-1 doi (DE-627)SPR051583836 (SPR)s11432-022-3686-1-e DE-627 ger DE-627 rakwb eng Yue, Yuanhao verfasserin aut An end-to-end network for co-saliency detection in one single image 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Science China Press 2023 Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps. saliency detection (dpeaa)DE-He213 convolutional neural network (dpeaa)DE-He213 regional feature mapping (dpeaa)DE-He213 co-saliency detection (dpeaa)DE-He213 deep learning (dpeaa)DE-He213 Zou, Qin aut Yu, Hongkai aut Wang, Qian aut Wang, Zhongyuan aut Wang, Song aut Enthalten in Science in China Heidelberg : Springer, 2001 66(2023), 11 vom: 17. Mai (DE-627)385614764 (DE-600)2142898-0 1862-2836 nnns volume:66 year:2023 number:11 day:17 month:05 https://dx.doi.org/10.1007/s11432-022-3686-1 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 AR 66 2023 11 17 05 |
| allfieldsSound |
10.1007/s11432-022-3686-1 doi (DE-627)SPR051583836 (SPR)s11432-022-3686-1-e DE-627 ger DE-627 rakwb eng Yue, Yuanhao verfasserin aut An end-to-end network for co-saliency detection in one single image 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier © Science China Press 2023 Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps. saliency detection (dpeaa)DE-He213 convolutional neural network (dpeaa)DE-He213 regional feature mapping (dpeaa)DE-He213 co-saliency detection (dpeaa)DE-He213 deep learning (dpeaa)DE-He213 Zou, Qin aut Yu, Hongkai aut Wang, Qian aut Wang, Zhongyuan aut Wang, Song aut Enthalten in Science in China Heidelberg : Springer, 2001 66(2023), 11 vom: 17. Mai (DE-627)385614764 (DE-600)2142898-0 1862-2836 nnns volume:66 year:2023 number:11 day:17 month:05 https://dx.doi.org/10.1007/s11432-022-3686-1 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 AR 66 2023 11 17 05 |
| language |
English |
| source |
Enthalten in Science in China 66(2023), 11 vom: 17. Mai volume:66 year:2023 number:11 day:17 month:05 |
| sourceStr |
Enthalten in Science in China 66(2023), 11 vom: 17. Mai volume:66 year:2023 number:11 day:17 month:05 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
saliency detection convolutional neural network regional feature mapping co-saliency detection deep learning |
| isfreeaccess_bool |
false |
| container_title |
Science in China |
| authorswithroles_txt_mv |
Yue, Yuanhao @@aut@@ Zou, Qin @@aut@@ Yu, Hongkai @@aut@@ Wang, Qian @@aut@@ Wang, Zhongyuan @@aut@@ Wang, Song @@aut@@ |
| publishDateDaySort_date |
2023-05-17T00:00:00Z |
| hierarchy_top_id |
385614764 |
| id |
SPR051583836 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">SPR051583836</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230523064717.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230523s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11432-022-3686-1</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR051583836</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s11432-022-3686-1-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Yue, Yuanhao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="3"><subfield code="a">An end-to-end network for co-saliency detection in one single image</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</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">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Science China Press 2023</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">saliency detection</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">convolutional neural network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">regional feature mapping</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">co-saliency detection</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zou, Qin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yu, Hongkai</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Qian</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Zhongyuan</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Song</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Science in China</subfield><subfield code="d">Heidelberg : Springer, 2001</subfield><subfield code="g">66(2023), 11 vom: 17. Mai</subfield><subfield code="w">(DE-627)385614764</subfield><subfield code="w">(DE-600)2142898-0</subfield><subfield code="x">1862-2836</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:66</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:11</subfield><subfield code="g">day:17</subfield><subfield code="g">month:05</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s11432-022-3686-1</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_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</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_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_120</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_138</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_171</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_187</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_250</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_281</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">66</subfield><subfield code="j">2023</subfield><subfield code="e">11</subfield><subfield code="b">17</subfield><subfield code="c">05</subfield></datafield></record></collection>
|
| author |
Yue, Yuanhao |
| spellingShingle |
Yue, Yuanhao misc saliency detection misc convolutional neural network misc regional feature mapping misc co-saliency detection misc deep learning An end-to-end network for co-saliency detection in one single image |
| authorStr |
Yue, Yuanhao |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)385614764 |
| format |
electronic Article |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut aut aut |
| collection |
springer |
| remote_str |
true |
| illustrated |
Not Illustrated |
| issn |
1862-2836 |
| topic_title |
An end-to-end network for co-saliency detection in one single image saliency detection (dpeaa)DE-He213 convolutional neural network (dpeaa)DE-He213 regional feature mapping (dpeaa)DE-He213 co-saliency detection (dpeaa)DE-He213 deep learning (dpeaa)DE-He213 |
| topic |
misc saliency detection misc convolutional neural network misc regional feature mapping misc co-saliency detection misc deep learning |
| topic_unstemmed |
misc saliency detection misc convolutional neural network misc regional feature mapping misc co-saliency detection misc deep learning |
| topic_browse |
misc saliency detection misc convolutional neural network misc regional feature mapping misc co-saliency detection misc deep learning |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
Science in China |
| hierarchy_parent_id |
385614764 |
| hierarchy_top_title |
Science in China |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)385614764 (DE-600)2142898-0 |
| title |
An end-to-end network for co-saliency detection in one single image |
| ctrlnum |
(DE-627)SPR051583836 (SPR)s11432-022-3686-1-e |
| title_full |
An end-to-end network for co-saliency detection in one single image |
| author_sort |
Yue, Yuanhao |
| journal |
Science in China |
| journalStr |
Science in China |
| lang_code |
eng |
| isOA_bool |
false |
| recordtype |
marc |
| publishDateSort |
2023 |
| contenttype_str_mv |
txt |
| author_browse |
Yue, Yuanhao Zou, Qin Yu, Hongkai Wang, Qian Wang, Zhongyuan Wang, Song |
| container_volume |
66 |
| format_se |
Elektronische Aufsätze |
| author-letter |
Yue, Yuanhao |
| doi_str_mv |
10.1007/s11432-022-3686-1 |
| title_sort |
end-to-end network for co-saliency detection in one single image |
| title_auth |
An end-to-end network for co-saliency detection in one single image |
| abstract |
Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps. © Science China Press 2023 |
| abstractGer |
Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps. © Science China Press 2023 |
| abstract_unstemmed |
Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps. © Science China Press 2023 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_SPRINGER GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_120 GBV_ILN_138 GBV_ILN_152 GBV_ILN_161 GBV_ILN_171 GBV_ILN_187 GBV_ILN_224 GBV_ILN_250 GBV_ILN_281 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 |
| container_issue |
11 |
| title_short |
An end-to-end network for co-saliency detection in one single image |
| url |
https://dx.doi.org/10.1007/s11432-022-3686-1 |
| remote_bool |
true |
| author2 |
Zou, Qin Yu, Hongkai Wang, Qian Wang, Zhongyuan Wang, Song |
| author2Str |
Zou, Qin Yu, Hongkai Wang, Qian Wang, Zhongyuan Wang, Song |
| ppnlink |
385614764 |
| mediatype_str_mv |
c |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s11432-022-3686-1 |
| up_date |
2024-07-03T22:40:02.258Z |
| _version_ |
1803599376300376064 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">SPR051583836</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230523064717.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230523s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11432-022-3686-1</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)SPR051583836</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(SPR)s11432-022-3686-1-e</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Yue, Yuanhao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="3"><subfield code="a">An end-to-end network for co-saliency detection in one single image</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</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">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Science China Press 2023</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">saliency detection</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">convolutional neural network</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">regional feature mapping</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">co-saliency detection</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield><subfield code="7">(dpeaa)DE-He213</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zou, Qin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yu, Hongkai</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Qian</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Zhongyuan</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Song</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Science in China</subfield><subfield code="d">Heidelberg : Springer, 2001</subfield><subfield code="g">66(2023), 11 vom: 17. Mai</subfield><subfield code="w">(DE-627)385614764</subfield><subfield code="w">(DE-600)2142898-0</subfield><subfield code="x">1862-2836</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:66</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:11</subfield><subfield code="g">day:17</subfield><subfield code="g">month:05</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://dx.doi.org/10.1007/s11432-022-3686-1</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_SPRINGER</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</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_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_120</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_138</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_171</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_187</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_250</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_281</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">66</subfield><subfield code="j">2023</subfield><subfield code="e">11</subfield><subfield code="b">17</subfield><subfield code="c">05</subfield></datafield></record></collection>
|
| score |
7.399349 |