Learning a referenceless stereopair quality engine with deep nonnegativity constrained sparse autoencoder
•A three-column deep non-negativity constrained sparse autoencoder is proposed for BSIQA.•Both feature evolution and feature mapping are addressed in a unified framework for BSIQA.•A Bayesian inference-based quality combination framework is used to derive 3D quality score. This paper proposes a no-r...
Uloženo v:
| Vydáno v: | Pattern recognition Ročník 76; s. 242 - 255 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.04.2018
|
| Témata: | |
| ISSN: | 0031-3203, 1873-5142 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | •A three-column deep non-negativity constrained sparse autoencoder is proposed for BSIQA.•Both feature evolution and feature mapping are addressed in a unified framework for BSIQA.•A Bayesian inference-based quality combination framework is used to derive 3D quality score.
This paper proposes a no-reference (NR)/referenceless quality evaluation method for stereoscopic three-dimensional (S3D) images based on deep nonnegativity constrained sparse autoencoder (DNCSAE). To address the quality issue of stereopairs whose perceived quality is not only determined by the individual left and right image qualities but also their interactions, a three-column DNCSAE framework is customized with individual DNCSAE module coping with the left image, the right image, and the cyclopean image, respectively. In the proposed framework, each individual DNCSAE module shares the same network architecture consisting of multiple stacked NCSAE layers and one Softmax regression layer at the end. The contribution of our model is that hierarchical feature evolution and nonlinear feature mapping are jointly optimized in a unified and perceptual-aware deep network (DNCSAE), which well resembles several important visual properties, i.e., hierarchy, sparsity, and non-negativity. To be more specific, for each DNCSAE, by taking a set of handcrafted natural scene statistic (NSS) features as inputs in the visible layer, the features in hidden layers are successively evolved to deeper levels producing increasingly discriminative quality-aware features (QAFs). Then, QAFs in the last NCSAE layer are summarized to their corresponding quality score by Softmax regression. Finally, three individual yet complementary quality scores estimated by each DNCSAE model are combined based on a Bayesian framework to obtain an overall 3D quality score. Experiments on three benchmark databases demonstrate the superiority of our method in terms of both prediction accuracy and generalization capability. |
|---|---|
| AbstractList | •A three-column deep non-negativity constrained sparse autoencoder is proposed for BSIQA.•Both feature evolution and feature mapping are addressed in a unified framework for BSIQA.•A Bayesian inference-based quality combination framework is used to derive 3D quality score.
This paper proposes a no-reference (NR)/referenceless quality evaluation method for stereoscopic three-dimensional (S3D) images based on deep nonnegativity constrained sparse autoencoder (DNCSAE). To address the quality issue of stereopairs whose perceived quality is not only determined by the individual left and right image qualities but also their interactions, a three-column DNCSAE framework is customized with individual DNCSAE module coping with the left image, the right image, and the cyclopean image, respectively. In the proposed framework, each individual DNCSAE module shares the same network architecture consisting of multiple stacked NCSAE layers and one Softmax regression layer at the end. The contribution of our model is that hierarchical feature evolution and nonlinear feature mapping are jointly optimized in a unified and perceptual-aware deep network (DNCSAE), which well resembles several important visual properties, i.e., hierarchy, sparsity, and non-negativity. To be more specific, for each DNCSAE, by taking a set of handcrafted natural scene statistic (NSS) features as inputs in the visible layer, the features in hidden layers are successively evolved to deeper levels producing increasingly discriminative quality-aware features (QAFs). Then, QAFs in the last NCSAE layer are summarized to their corresponding quality score by Softmax regression. Finally, three individual yet complementary quality scores estimated by each DNCSAE model are combined based on a Bayesian framework to obtain an overall 3D quality score. Experiments on three benchmark databases demonstrate the superiority of our method in terms of both prediction accuracy and generalization capability. |
| Author | Lin, Weisi Jiang, Gangyi Shao, Feng Jiang, Qiuping |
| Author_xml | – sequence: 1 givenname: Qiuping surname: Jiang fullname: Jiang, Qiuping organization: Faculty of Information Science and Engineering, Ningbo University, Ningbo 315211, China – sequence: 2 givenname: Feng surname: Shao fullname: Shao, Feng email: shaofeng@nbu.edu.cn organization: Faculty of Information Science and Engineering, Ningbo University, Ningbo 315211, China – sequence: 3 givenname: Weisi surname: Lin fullname: Lin, Weisi organization: School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, Singapore – sequence: 4 givenname: Gangyi surname: Jiang fullname: Jiang, Gangyi organization: Faculty of Information Science and Engineering, Ningbo University, Ningbo 315211, China |
| BookMark | eNqFkM1OwzAQhC0EEm3hDTj4BRLsuIkTDkio4k-qxAXOln82wVWxg-0W9e1xVE4c4LRa7c5o5pujU-cdIHRFSUkJba435SiT9kNZEcpLSktC6Ama0ZazoqbL6hTNCGG0YBVh52ge4yY_8HyYIbsGGZx1A5Y4QA8BnIYtxIhjyosfpQ34cye3Nh0wuME6wF82vWMDMOKcw8Egk91PZ-1dTEHmF4PjKEMELHfJZ0dvIFygs15uI1z-zAV6e7h_XT0V65fH59XdutCMNKkA3krVG86VIj3TCmrWVapjy75t2raiTIFulFHLuma8J23Luo4TUxkCyjBu2ALdHH118DHmTkLblCN6N2XbCkrEBE1sxBGamKAJSkVmksXLX-Ix2A8ZDv_Jbo8yyMX2FoKI2k4kjQ2gkzDe_m3wDUhwjoM |
| CitedBy_id | crossref_primary_10_1007_s11554_021_01137_4 crossref_primary_10_1109_TIP_2018_2881828 crossref_primary_10_1109_ACCESS_2020_2992746 crossref_primary_10_1016_j_jvcir_2020_102848 crossref_primary_10_1109_TASE_2019_2935314 crossref_primary_10_1016_j_patcog_2019_107168 crossref_primary_10_1016_j_jvcir_2020_102868 crossref_primary_10_1016_j_compmedimag_2018_08_006 crossref_primary_10_1109_ACCESS_2018_2866081 crossref_primary_10_1109_TMM_2018_2867742 crossref_primary_10_1109_TIP_2020_3036766 crossref_primary_10_1109_LSP_2019_2940105 crossref_primary_10_1109_ACCESS_2019_2930707 crossref_primary_10_3390_app9183906 crossref_primary_10_1016_j_image_2019_06_014 crossref_primary_10_1016_j_image_2024_117138 crossref_primary_10_1109_TMM_2020_2965461 crossref_primary_10_1002_jsid_653 crossref_primary_10_1109_ACCESS_2020_2974006 crossref_primary_10_1109_ACCESS_2018_2885818 crossref_primary_10_1016_j_jvcir_2022_103643 crossref_primary_10_1016_j_image_2021_116175 crossref_primary_10_1016_j_jvcir_2022_103586 crossref_primary_10_1016_j_neucom_2020_04_049 crossref_primary_10_1109_TIM_2020_3005111 crossref_primary_10_1016_j_sigpro_2018_04_019 |
| Cites_doi | 10.1016/j.patcog.2016.01.034 10.1109/TNNLS.2015.2479223 10.3758/BF03202845 10.1109/TIP.2013.2267393 10.1016/j.neucom.2015.06.116 10.1137/0916069 10.1016/j.patcog.2010.09.005 10.1016/j.neucom.2014.05.090 10.1109/TIP.2013.2240003 10.1109/TMM.2016.2594142 10.1109/TIP.2017.2702383 10.1007/s11045-012-0178-3 10.1109/TIP.2015.2446942 10.1109/TIP.2016.2642791 10.1016/j.patcog.2006.11.022 10.1109/TIP.2015.2500021 10.1016/j.patcog.2011.06.023 10.1109/TMM.2016.2601028 10.1109/TIP.2012.2191563 10.1093/cercor/4.5.509 10.1016/S0031-3203(96)00051-9 10.1109/LSP.2016.2516521 10.1364/OE.24.011640 10.1073/pnas.0509629103 10.1016/0896-6273(94)90455-3 10.1109/TMM.2016.2542580 10.1038/44565 10.1016/j.jvcir.2015.09.009 10.1109/TIP.2003.819861 10.1109/TCSVT.2015.2430711 10.1007/BF00055146 10.1109/TNNLS.2014.2310059 10.1561/2200000006 10.1109/TMM.2011.2109701 10.1109/TIP.2014.2355716 10.1109/TMM.2015.2493781 10.1109/TIP.2015.2413298 10.1109/TIP.2014.2302686 10.1109/TIP.2015.2436332 10.1109/TIP.2015.2456414 10.1109/TIP.2016.2538462 10.1109/TIP.2012.2214050 10.1109/TIP.2011.2147325 |
| ContentType | Journal Article |
| Copyright | 2017 Elsevier Ltd |
| Copyright_xml | – notice: 2017 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.patcog.2017.11.001 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1873-5142 |
| EndPage | 255 |
| ExternalDocumentID | 10_1016_j_patcog_2017_11_001 S0031320317304582 |
| GroupedDBID | --K --M -D8 -DT -~X .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 29O 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABFRF ABHFT ABJNI ABMAC ABTAH ABXDB ABYKQ ACBEA ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADMXK ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FD6 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM KZ1 LG9 LMP LY1 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UNMZH VOH WUQ XJE XPP ZMT ZY4 ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c306t-e78abfd77bb0f3cbe5392b934f8688213bec6bdb45537f08839970d2d0ebd37d3 |
| ISICitedReferencesCount | 31 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000424853800019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0031-3203 |
| IngestDate | Sat Nov 29 03:52:22 EST 2025 Tue Nov 18 22:23:06 EST 2025 Fri Feb 23 02:25:23 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Stereoscopic 3D image Deep learning Image quality assessment No-reference/referenceless Sparse autoencoder Nonnegativity constrained |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c306t-e78abfd77bb0f3cbe5392b934f8688213bec6bdb45537f08839970d2d0ebd37d3 |
| PageCount | 14 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_patcog_2017_11_001 crossref_primary_10_1016_j_patcog_2017_11_001 elsevier_sciencedirect_doi_10_1016_j_patcog_2017_11_001 |
| PublicationCentury | 2000 |
| PublicationDate | April 2018 2018-04-00 |
| PublicationDateYYYYMMDD | 2018-04-01 |
| PublicationDate_xml | – month: 04 year: 2018 text: April 2018 |
| PublicationDecade | 2010 |
| PublicationTitle | Pattern recognition |
| PublicationYear | 2018 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Oh, Kim, Kim, Kim, Lee, Bovik (bib0005) 2017; 26 Moghaddam, Jamzad (bib0011) 2007; 40 Snyman (bib0047) 2005 Blake, Boothroyd (bib0052) 1985; 37 Mittal, Moorthy, Bovik (bib0015) 2012; 21 Zhao, Nandhakumar (bib0002) 1996; 29 Narwaria, Lin, Cetin (bib0008) 2012; 45 Ryu, Sohn (bib0030) 2014; 24 Li, Po, Cheung, Xu, Feng, Yuan, Cheung (bib0041) 2016; 26 Hinton, Zemel (bib0045) 1994 Agostinelli, Anderson, Lee (bib0044) 2013 Shao, Li, Lin, Jiang, Yu, Dai (bib0024) 2015; 24 Chen, Cormack, Bovik (bib0031) 2013; 22 Rumelhart, Hinton, Williams (bib0048) 1988 Ghadiyaram, Bovik (bib0058) 2016; 25 Wang, Bovik, Sheikh, Simoncelli (bib0007) 2004; 13 Saad, Bovik, Charrier (bib0016) 2012; 21 Xu, Liu, Quan, Callet (bib0010) 2015; 24 Li, Lin, Xu, Fang (bib0019) 2016; 18 Ranzato, Boureau, LeCun (bib0046) 2007 Zhang, Qu, Ma, Guan, Huang (bib0034) 2016 Benoit, Le Callet, Campisi, Cousseau (bib0020) January 2009; 2008 Zhou, Yu (bib0032) 2016; 18 Shao, Li, Lin, Jiang, Dai (bib0054) 2016; 18 Lin, Wu (bib0023) 2014; 23 Belhumeur (bib0053) 1996; 19 Smolic (bib0001) 2011; 44 Jiang, Shao, Lin, Jiang (bib0003) 2016; 23 Hosseini-Asl, Zurada, Nasraoui (bib0043) 2016; 27 Chen, Su, Kwon, Cormack, Bovik (bib0022) October 2013; 28 Moorthy, Bovik (bib0014) 2011; 20 Wang, Rehman, Zeng, Wang, Wang (bib0026) 2015; 24 Bengio (bib0037) 2009; 2 Levelt (bib0049) 1965 Shao, Lin, Gu, Jiang, Srikanthan (bib0055) 2013; 22 Shao, Jiang, Fu, Yu, Jiang (bib0006) May 2016; 24 Van Essen, Gallant (bib0038) 1994; 13 Lee, Seung (bib0040) 1999; 401 Liu, Hua, Zhao, Huang, Bovik (bib0013) 2016; 40 Wachsmuth, Oram, Perrett (bib0039) 1994; 4 Wang, Wang S, Ma, Wang (bib0004) 2017; 26 Jiang, Shao, Jiang, Yu, Peng (bib0012) November. 2015; 33 Moorthy, Su, Mittal, Bovik (bib0056) 2013; 28 Final Report from the Video Quality Experts Group on the Validation of Objective Models of Video Quality Assessment, Phase II, Video Quality Experts Group (VQEG), Tech. Rep., 2003. Appina, Khan, Channappayya (bib0033) 2016; 43 Bensalma, Larabi (bib0021) 2013; 24 Ma, Wang, Liu, Ngan (bib0028) November 2016; 215 Chorowski, Zurada (bib0042) 2015; 26 Ding, Sperling (bib0050) 2006; 103 Xue, Mou, Zhang, Bovik, Feng (bib0017) 2014; 23 Wang, Liu, Wang, Chen (bib0029) 2015; 151 Gu, Zhai, Yang, Zhang (bib0018) 2014; 17 Byrd, Lu, Nocedal, Zhu (bib0051) 1995; 16 Zhang, Chandler (bib0025) 2015; 24 Shao, Tian, Lin, Jiang, Dai (bib0035) 2016; 25 Lv, Yu, Jiang, Shao, Peng, Chen (bib0036) 2016; 47 Qi, Zhao, Gao (bib0027) 2015; 17 Ma, Li, Zhang, Ngan (bib0009) 2011; 13 Gu (10.1016/j.patcog.2017.11.001_bib0018) 2014; 17 Bensalma (10.1016/j.patcog.2017.11.001_bib0021) 2013; 24 Rumelhart (10.1016/j.patcog.2017.11.001_bib0048) 1988 Ghadiyaram (10.1016/j.patcog.2017.11.001_bib0058) 2016; 25 Xu (10.1016/j.patcog.2017.11.001_bib0010) 2015; 24 Zhao (10.1016/j.patcog.2017.11.001_bib0002) 1996; 29 Wang (10.1016/j.patcog.2017.11.001_bib0007) 2004; 13 Wang (10.1016/j.patcog.2017.11.001_bib0026) 2015; 24 Belhumeur (10.1016/j.patcog.2017.11.001_bib0053) 1996; 19 Li (10.1016/j.patcog.2017.11.001_bib0019) 2016; 18 Zhou (10.1016/j.patcog.2017.11.001_bib0032) 2016; 18 Liu (10.1016/j.patcog.2017.11.001_bib0013) 2016; 40 Shao (10.1016/j.patcog.2017.11.001_bib0024) 2015; 24 Van Essen (10.1016/j.patcog.2017.11.001_bib0038) 1994; 13 Saad (10.1016/j.patcog.2017.11.001_bib0016) 2012; 21 Moorthy (10.1016/j.patcog.2017.11.001_bib0056) 2013; 28 Blake (10.1016/j.patcog.2017.11.001_bib0052) 1985; 37 Hosseini-Asl (10.1016/j.patcog.2017.11.001_bib0043) 2016; 27 Shao (10.1016/j.patcog.2017.11.001_bib0055) 2013; 22 Lv (10.1016/j.patcog.2017.11.001_bib0036) 2016; 47 Mittal (10.1016/j.patcog.2017.11.001_bib0015) 2012; 21 Lin (10.1016/j.patcog.2017.11.001_bib0023) 2014; 23 Wang (10.1016/j.patcog.2017.11.001_bib0004) 2017; 26 Narwaria (10.1016/j.patcog.2017.11.001_bib0008) 2012; 45 Chen (10.1016/j.patcog.2017.11.001_bib0031) 2013; 22 Byrd (10.1016/j.patcog.2017.11.001_bib0051) 1995; 16 Ma (10.1016/j.patcog.2017.11.001_bib0009) 2011; 13 Benoit (10.1016/j.patcog.2017.11.001_bib0020) 2009; 2008 Moorthy (10.1016/j.patcog.2017.11.001_bib0014) 2011; 20 Shao (10.1016/j.patcog.2017.11.001_bib0054) 2016; 18 Jiang (10.1016/j.patcog.2017.11.001_bib0003) 2016; 23 Qi (10.1016/j.patcog.2017.11.001_bib0027) 2015; 17 Chen (10.1016/j.patcog.2017.11.001_bib0022) 2013; 28 Zhang (10.1016/j.patcog.2017.11.001_bib0025) 2015; 24 Ryu (10.1016/j.patcog.2017.11.001_bib0030) 2014; 24 Li (10.1016/j.patcog.2017.11.001_bib0041) 2016; 26 Ma (10.1016/j.patcog.2017.11.001_bib0028) 2016; 215 Levelt (10.1016/j.patcog.2017.11.001_bib0049) 1965 Zhang (10.1016/j.patcog.2017.11.001_bib0034) 2016 Jiang (10.1016/j.patcog.2017.11.001_bib0012) 2015; 33 Oh (10.1016/j.patcog.2017.11.001_bib0005) 2017; 26 Agostinelli (10.1016/j.patcog.2017.11.001_bib0044) 2013 10.1016/j.patcog.2017.11.001_bib0057 Moghaddam (10.1016/j.patcog.2017.11.001_bib0011) 2007; 40 Shao (10.1016/j.patcog.2017.11.001_bib0006) 2016; 24 Wachsmuth (10.1016/j.patcog.2017.11.001_bib0039) 1994; 4 Lee (10.1016/j.patcog.2017.11.001_bib0040) 1999; 401 Wang (10.1016/j.patcog.2017.11.001_bib0029) 2015; 151 Shao (10.1016/j.patcog.2017.11.001_bib0035) 2016; 25 Xue (10.1016/j.patcog.2017.11.001_bib0017) 2014; 23 Bengio (10.1016/j.patcog.2017.11.001_bib0037) 2009; 2 Snyman (10.1016/j.patcog.2017.11.001_bib0047) 2005 Smolic (10.1016/j.patcog.2017.11.001_bib0001) 2011; 44 Ding (10.1016/j.patcog.2017.11.001_bib0050) 2006; 103 Appina (10.1016/j.patcog.2017.11.001_bib0033) 2016; 43 Ranzato (10.1016/j.patcog.2017.11.001_bib0046) 2007 Chorowski (10.1016/j.patcog.2017.11.001_bib0042) 2015; 26 Hinton (10.1016/j.patcog.2017.11.001_bib0045) 1994 |
| References_xml | – year: 2016 ident: bib0034 article-title: Learning structure of stereoscopic image for no-reference quality assessment with convolutional neural network publication-title: Pattern Recognit. – volume: 37 start-page: 114 year: 1985 end-page: 124 ident: bib0052 article-title: The precedence of binocular fusion over binocular rivalry publication-title: Attent. Percept. Psychophys. – volume: 13 start-page: 1 year: 1994 end-page: 10 ident: bib0038 article-title: Neural mechanisms of form and motion processing in the primate visual system publication-title: Neuron – volume: 47 start-page: 346 year: 2016 end-page: 357 ident: bib0036 article-title: No-reference stereoscopic image quality assessment using binocular self-similarity and deep neural network publication-title: Signal Process. – volume: 40 start-page: 1946 year: 2007 end-page: 1957 ident: bib0011 article-title: Motion blur identification in noisy images using mathematical models and statistical measures publication-title: Pattern Recognit – volume: 17 start-page: 50 year: 2014 end-page: 63 ident: bib0018 article-title: Using free energy principle for blind image quality assessment publication-title: IEEE Trans. Multimedia – year: 2005 ident: bib0047 article-title: Practical Mathematical Optimization: An Introduction to Basic Optimization Theory and Classical and New Gradient-Based Algorithms – volume: 22 start-page: 3379 year: 2013 end-page: 3391 ident: bib0031 article-title: No-reference quality assessment of natural stereopairs publication-title: IEEE Trans. Image Process. – volume: 13 start-page: 600 year: 2004 end-page: 612 ident: bib0007 article-title: Image quality assessment: from error visibility to structural similarity publication-title: IEEE Trans. Image Process. – volume: 103 start-page: 1141 year: 2006 end-page: 1146 ident: bib0050 article-title: A gain-control theory of binocular combination publication-title: Proc. Nation. Acad. Sci. USA – volume: 24 start-page: 11640 year: May 2016 end-page: 11653 ident: bib0006 article-title: Optimizing visual comfort for stereoscopic 3D display based on color-plus-depth signals publication-title: Opt. Express – year: 1965 ident: bib0049 article-title: On binocular rivalry publication-title: Van Gorcum Assen – volume: 17 start-page: 2338 year: 2015 end-page: 2344 ident: bib0027 article-title: Reduced reference stereoscopic image quality assessment based on binocular perceptual information publication-title: IEEE Trans. Multimedia – volume: 26 start-page: 1044 year: 2016 end-page: 1057 ident: bib0041 article-title: No-reference video quality assessment with 3D shearlet transform and convolutional neural networks publication-title: IEEE Trans. Circuits Syst. Video Technol. – volume: 45 start-page: 299 year: 2012 end-page: 313 ident: bib0008 article-title: Scalable image quality assessment with 2D mel-cepstrum and machine learning approach publication-title: Pattern Recognit. – volume: 25 start-page: 2059 year: 2016 end-page: 2074 ident: bib0035 article-title: Toward a blind deep quality evaluator for stereoscopic images based on monocular and binocular interactions publication-title: IEEE Trans. Image Process. – volume: 40 start-page: 1 year: 2016 end-page: 15 ident: bib0013 article-title: Blind image quality assessment by relative gradient statistics and adaboosting neural network publication-title: Signal Process. – volume: 29 start-page: 2115 year: 1996 end-page: 2126 ident: bib0002 article-title: Effects of camera alignment errors on stereoscopic depth estimates publication-title: Pattern Recognit. – volume: 18 start-page: 1077 year: 2016 end-page: 1084 ident: bib0032 article-title: Binocular responses for no-reference 3D image quality assessment publication-title: IEEE Trans. Multimedia – year: 1988 ident: bib0048 article-title: Learning Representations by Back-Propagating Errors – volume: 151 start-page: 683 year: 2015 end-page: 691 ident: bib0029 article-title: Natural image statistics based 3D reduced reference image quality assessment in contourlet domain publication-title: Neurocomputing – volume: 24 start-page: 3400 year: 2015 end-page: 3414 ident: bib0026 article-title: Quality prediction of asymmetrically distorted stereoscopic 3D images publication-title: IEEE Trans. Image Process. – volume: 44 start-page: 1958 year: 2011 end-page: 1968 ident: bib0001 article-title: 3D video and free viewpoint video—from capture to display publication-title: Pattern Recognit. – volume: 2008 year: January 2009 ident: bib0020 article-title: Quality assessment of stereoscopic images publication-title: EURASIP J. Image Video Process. – volume: 4 start-page: 509 year: 1994 end-page: 522 ident: bib0039 article-title: Recognition of objects and their component parts: responses of single units in the temporal cortex of the macaque publication-title: Cerebral Cortex – start-page: 1185 year: 2007 end-page: 1192 ident: bib0046 article-title: Sparse feature learning for deep belief networks publication-title: Proc. Conf. Adv. Neural Inform. Process. Syst. – volume: 215 start-page: 21 year: November 2016 end-page: 31 ident: bib0028 article-title: Reorganized DCT-based image representation for reduced reference stereoscopic image quality assessment publication-title: Neurocomputing – volume: 18 start-page: 2104 year: 2016 end-page: 2114 ident: bib0054 article-title: Learning blind quality evaluator for stereoscopic images using joint sparse representation publication-title: IEEE Trans. Multimedia – volume: 23 start-page: 4850 year: 2014 end-page: 4862 ident: bib0017 article-title: Blind image quality assessment using joint statistics of gradient magnitude and Laplacian features publication-title: IEEE Trans. Image Process. – volume: 22 start-page: 1940 year: 2013 end-page: 1953 ident: bib0055 article-title: Perceptual full-reference quality assessment of stereoscopic images by considering binocular visual characteristics publication-title: IEEE Trans. Image Process. – volume: 13 start-page: 824 year: 2011 end-page: 829 ident: bib0009 article-title: Reduced-reference image quality assessment using reorganized DCT-based image representation publication-title: IEEE Trans. Multimedia – volume: 28 start-page: 1143 year: October 2013 end-page: 1155 ident: bib0022 article-title: Full-reference quality assessment of stereopairs accounting for rivalry publication-title: Signal Process. – volume: 24 start-page: 3810 year: 2015 end-page: 3825 ident: bib0025 article-title: 3D-MAD: a full reference stereoscopic image quality estimator based on binocular lightness and contrast perception publication-title: IEEE Trans. Image Process. – reference: Final Report from the Video Quality Experts Group on the Validation of Objective Models of Video Quality Assessment, Phase II, Video Quality Experts Group (VQEG), Tech. Rep., 2003. – volume: 26 start-page: 1202 year: 2017 end-page: 1215 ident: bib0004 article-title: Perceptual depth quality in distorted stereoscopic images publication-title: IEEE Trans. Image Process. – volume: 24 start-page: 591 year: 2014 end-page: 602 ident: bib0030 article-title: No-reference quality assessment for stereoscopic images based on binocular quality perception publication-title: IEEE Trans. Circuits Syst. Video Technol. – volume: 43 start-page: 1 year: 2016 end-page: 14 ident: bib0033 article-title: No-reference stereoscopic image quality assessment using natural scene statistics publication-title: Signal Process. – start-page: 1493 year: 2013 end-page: 1501 ident: bib0044 article-title: Adaptive multi-column deep neural networks with application to robust image denoising publication-title: Proc. Conf. Adv. Neural Inform. Process. Syst. – volume: 27 start-page: 2486 year: 2016 end-page: 2498 ident: bib0043 article-title: Deep learning of part-based representation of data using sparse autoencoders with nonnegativity constraints publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 16 start-page: 1190 year: 1995 end-page: 1208 ident: bib0051 article-title: A limited memory algorithm for bound constrained optimization publication-title: SIAM J. Sci. Comput. – volume: 21 start-page: 3339 year: 2012 end-page: 3352 ident: bib0016 article-title: Blind image quality assessment: a natural scene statistics approach in the DCT domain publication-title: IEEE Trans. Image Process. – volume: 26 start-page: 62 year: 2015 end-page: 69 ident: bib0042 article-title: Learning understandable neural networks with nonnegative weight constraints publication-title: IEEE Trans. Neural Networks Learn. Syst. – volume: 21 start-page: 4695 year: 2012 end-page: 4708 ident: bib0015 article-title: No-reference image quality assessment in the spatial domain publication-title: IEEE Trans. Image Process. – volume: 20 start-page: 3350 year: 2011 end-page: 3364 ident: bib0014 article-title: Blind image quality assessment: from natural scene statistics to perceptual quality publication-title: IEEE Trans. Image Process. – volume: 24 start-page: 2971 year: 2015 end-page: 2983 ident: bib0024 article-title: Full-reference quality assessment of stereoscopic images by learning binocular receptive field properties publication-title: IEEE Trans. Image Process. – volume: 2 start-page: 1 year: 2009 end-page: 127 ident: bib0037 article-title: Learning deep architectures for AI publication-title: Found. Trends Mach. Learn. – volume: 26 start-page: 3789 year: 2017 end-page: 3801 ident: bib0005 article-title: Enhancement of visual comfort and sense of presence on stereoscopic 3D images publication-title: IEEE Trans. Image Process. – volume: 19 start-page: 237 year: 1996 end-page: 260 ident: bib0053 article-title: A Bayesian approach to binocular stereopsis publication-title: Int. J. Comput. Vis. – volume: 23 start-page: 302 year: 2016 end-page: 306 ident: bib0003 article-title: On predicting visual comfort of stereoscopic images: a learning to rank based approach publication-title: IEEE Signal Process. Lett. – volume: 24 start-page: 2098 year: 2015 end-page: 2109 ident: bib0010 article-title: Fractal analysis for reduced reference image quality assessment publication-title: IEEE Trans. Image Process. – volume: 23 start-page: 1527 year: 2014 end-page: 1542 ident: bib0023 article-title: Quality assessment of stereoscopic 3D image compression by binocular integration behaviors publication-title: IEEE Trans. Image Process. – volume: 401 start-page: 788 year: 1999 end-page: 791 ident: bib0040 article-title: Learning the parts of objects by nonnegative matrix factorization publication-title: Nature – volume: 25 start-page: 372 year: 2016 end-page: 387 ident: bib0058 article-title: Massive online crowdsourced study of subjective and objective picture quality publication-title: IEEE Trans. Image Process. – volume: 18 start-page: 2457 year: 2016 end-page: 2469 ident: bib0019 article-title: Blind image quality assessment using statistical structural and luminance features publication-title: IEEE Trans. Multimedia – volume: 33 start-page: 123 year: November. 2015 end-page: 133 ident: bib0012 article-title: Supervised dictionary learning for blind image quality assessment using quality-constraint sparse coding publication-title: J. Vis. Commun. Image Represent. – year: 1994 ident: bib0045 article-title: Autoencoders, minimum description length, and Helmholtz free energy publication-title: Proc. Conf. Adv. Neural Inform. Process. Syst. – volume: 24 start-page: 281 year: 2013 end-page: 316 ident: bib0021 article-title: A perceptual metric for stereoscopic image quality assessment based on the binocular energy publication-title: Multidimens. Syst. Signal Process. – volume: 28 start-page: 870 year: 2013 end-page: 883 ident: bib0056 article-title: Subjective evaluation of stereoscopic image quality publication-title: Signal Process. – year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0034 article-title: Learning structure of stereoscopic image for no-reference quality assessment with convolutional neural network publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2016.01.034 – volume: 27 start-page: 2486 issue: 12 year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0043 article-title: Deep learning of part-based representation of data using sparse autoencoders with nonnegativity constraints publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2015.2479223 – volume: 17 start-page: 50 issue: January (1) year: 2014 ident: 10.1016/j.patcog.2017.11.001_bib0018 article-title: Using free energy principle for blind image quality assessment publication-title: IEEE Trans. Multimedia – volume: 37 start-page: 114 issue: 2 year: 1985 ident: 10.1016/j.patcog.2017.11.001_bib0052 article-title: The precedence of binocular fusion over binocular rivalry publication-title: Attent. Percept. Psychophys. doi: 10.3758/BF03202845 – volume: 22 start-page: 3379 issue: September (9) year: 2013 ident: 10.1016/j.patcog.2017.11.001_bib0031 article-title: No-reference quality assessment of natural stereopairs publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2013.2267393 – volume: 215 start-page: 21 year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0028 article-title: Reorganized DCT-based image representation for reduced reference stereoscopic image quality assessment publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.06.116 – volume: 16 start-page: 1190 issue: 5 year: 1995 ident: 10.1016/j.patcog.2017.11.001_bib0051 article-title: A limited memory algorithm for bound constrained optimization publication-title: SIAM J. Sci. Comput. doi: 10.1137/0916069 – volume: 44 start-page: 1958 issue: 9 year: 2011 ident: 10.1016/j.patcog.2017.11.001_bib0001 article-title: 3D video and free viewpoint video—from capture to display publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2010.09.005 – volume: 151 start-page: 683 year: 2015 ident: 10.1016/j.patcog.2017.11.001_bib0029 article-title: Natural image statistics based 3D reduced reference image quality assessment in contourlet domain publication-title: Neurocomputing doi: 10.1016/j.neucom.2014.05.090 – volume: 22 start-page: 1940 issue: May (5) year: 2013 ident: 10.1016/j.patcog.2017.11.001_bib0055 article-title: Perceptual full-reference quality assessment of stereoscopic images by considering binocular visual characteristics publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2013.2240003 – start-page: 1185 year: 2007 ident: 10.1016/j.patcog.2017.11.001_bib0046 article-title: Sparse feature learning for deep belief networks – volume: 18 start-page: 2104 issue: 10 year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0054 article-title: Learning blind quality evaluator for stereoscopic images using joint sparse representation publication-title: IEEE Trans. Multimedia doi: 10.1109/TMM.2016.2594142 – volume: 26 start-page: 3789 issue: August (8) year: 2017 ident: 10.1016/j.patcog.2017.11.001_bib0005 article-title: Enhancement of visual comfort and sense of presence on stereoscopic 3D images publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2017.2702383 – volume: 24 start-page: 281 issue: June (2) year: 2013 ident: 10.1016/j.patcog.2017.11.001_bib0021 article-title: A perceptual metric for stereoscopic image quality assessment based on the binocular energy publication-title: Multidimens. Syst. Signal Process. doi: 10.1007/s11045-012-0178-3 – volume: 24 start-page: 3400 issue: November (11) year: 2015 ident: 10.1016/j.patcog.2017.11.001_bib0026 article-title: Quality prediction of asymmetrically distorted stereoscopic 3D images publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2015.2446942 – volume: 26 start-page: 1202 issue: March (3) year: 2017 ident: 10.1016/j.patcog.2017.11.001_bib0004 article-title: Perceptual depth quality in distorted stereoscopic images publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2016.2642791 – year: 1988 ident: 10.1016/j.patcog.2017.11.001_bib0048 – volume: 40 start-page: 1946 issue: 7 year: 2007 ident: 10.1016/j.patcog.2017.11.001_bib0011 article-title: Motion blur identification in noisy images using mathematical models and statistical measures publication-title: Pattern Recognit doi: 10.1016/j.patcog.2006.11.022 – volume: 25 start-page: 372 issue: January (1) year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0058 article-title: Massive online crowdsourced study of subjective and objective picture quality publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2015.2500021 – ident: 10.1016/j.patcog.2017.11.001_bib0057 – start-page: 1493 year: 2013 ident: 10.1016/j.patcog.2017.11.001_bib0044 article-title: Adaptive multi-column deep neural networks with application to robust image denoising – volume: 45 start-page: 299 issue: 1 year: 2012 ident: 10.1016/j.patcog.2017.11.001_bib0008 article-title: Scalable image quality assessment with 2D mel-cepstrum and machine learning approach publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2011.06.023 – volume: 28 start-page: 1143 year: 2013 ident: 10.1016/j.patcog.2017.11.001_bib0022 article-title: Full-reference quality assessment of stereopairs accounting for rivalry publication-title: Signal Process. – volume: 18 start-page: 2457 issue: December (12) year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0019 article-title: Blind image quality assessment using statistical structural and luminance features publication-title: IEEE Trans. Multimedia doi: 10.1109/TMM.2016.2601028 – volume: 21 start-page: 3339 issue: August (8) year: 2012 ident: 10.1016/j.patcog.2017.11.001_bib0016 article-title: Blind image quality assessment: a natural scene statistics approach in the DCT domain publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2012.2191563 – volume: 4 start-page: 509 issue: 5 year: 1994 ident: 10.1016/j.patcog.2017.11.001_bib0039 article-title: Recognition of objects and their component parts: responses of single units in the temporal cortex of the macaque publication-title: Cerebral Cortex doi: 10.1093/cercor/4.5.509 – volume: 29 start-page: 2115 issue: 12 year: 1996 ident: 10.1016/j.patcog.2017.11.001_bib0002 article-title: Effects of camera alignment errors on stereoscopic depth estimates publication-title: Pattern Recognit. doi: 10.1016/S0031-3203(96)00051-9 – volume: 23 start-page: 302 issue: February (2) year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0003 article-title: On predicting visual comfort of stereoscopic images: a learning to rank based approach publication-title: IEEE Signal Process. Lett. doi: 10.1109/LSP.2016.2516521 – volume: 24 start-page: 11640 year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0006 article-title: Optimizing visual comfort for stereoscopic 3D display based on color-plus-depth signals publication-title: Opt. Express doi: 10.1364/OE.24.011640 – year: 1994 ident: 10.1016/j.patcog.2017.11.001_bib0045 article-title: Autoencoders, minimum description length, and Helmholtz free energy – volume: 103 start-page: 1141 issue: 4 year: 2006 ident: 10.1016/j.patcog.2017.11.001_bib0050 article-title: A gain-control theory of binocular combination publication-title: Proc. Nation. Acad. Sci. USA doi: 10.1073/pnas.0509629103 – volume: 13 start-page: 1 issue: 1 year: 1994 ident: 10.1016/j.patcog.2017.11.001_bib0038 article-title: Neural mechanisms of form and motion processing in the primate visual system publication-title: Neuron doi: 10.1016/0896-6273(94)90455-3 – volume: 18 start-page: 1077 issue: June (6) year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0032 article-title: Binocular responses for no-reference 3D image quality assessment publication-title: IEEE Trans. Multimedia doi: 10.1109/TMM.2016.2542580 – volume: 401 start-page: 788 issue: October (6755) year: 1999 ident: 10.1016/j.patcog.2017.11.001_bib0040 article-title: Learning the parts of objects by nonnegative matrix factorization publication-title: Nature doi: 10.1038/44565 – volume: 33 start-page: 123 year: 2015 ident: 10.1016/j.patcog.2017.11.001_bib0012 article-title: Supervised dictionary learning for blind image quality assessment using quality-constraint sparse coding publication-title: J. Vis. Commun. Image Represent. doi: 10.1016/j.jvcir.2015.09.009 – volume: 13 start-page: 600 issue: April (4) year: 2004 ident: 10.1016/j.patcog.2017.11.001_bib0007 article-title: Image quality assessment: from error visibility to structural similarity publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2003.819861 – volume: 26 start-page: 1044 issue: June (6) year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0041 article-title: No-reference video quality assessment with 3D shearlet transform and convolutional neural networks publication-title: IEEE Trans. Circuits Syst. Video Technol. doi: 10.1109/TCSVT.2015.2430711 – year: 1965 ident: 10.1016/j.patcog.2017.11.001_bib0049 article-title: On binocular rivalry publication-title: Van Gorcum Assen – volume: 19 start-page: 237 issue: 3 year: 1996 ident: 10.1016/j.patcog.2017.11.001_bib0053 article-title: A Bayesian approach to binocular stereopsis publication-title: Int. J. Comput. Vis. doi: 10.1007/BF00055146 – volume: 26 start-page: 62 issue: January (1) year: 2015 ident: 10.1016/j.patcog.2017.11.001_bib0042 article-title: Learning understandable neural networks with nonnegative weight constraints publication-title: IEEE Trans. Neural Networks Learn. Syst. doi: 10.1109/TNNLS.2014.2310059 – volume: 43 start-page: 1 year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0033 article-title: No-reference stereoscopic image quality assessment using natural scene statistics publication-title: Signal Process. – volume: 2 start-page: 1 issue: 1 year: 2009 ident: 10.1016/j.patcog.2017.11.001_bib0037 article-title: Learning deep architectures for AI publication-title: Found. Trends Mach. Learn. doi: 10.1561/2200000006 – year: 2005 ident: 10.1016/j.patcog.2017.11.001_bib0047 – volume: 13 start-page: 824 issue: August (4) year: 2011 ident: 10.1016/j.patcog.2017.11.001_bib0009 article-title: Reduced-reference image quality assessment using reorganized DCT-based image representation publication-title: IEEE Trans. Multimedia doi: 10.1109/TMM.2011.2109701 – volume: 28 start-page: 870 issue: September (8) year: 2013 ident: 10.1016/j.patcog.2017.11.001_bib0056 article-title: Subjective evaluation of stereoscopic image quality publication-title: Signal Process. – volume: 40 start-page: 1 issue: January (1) year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0013 article-title: Blind image quality assessment by relative gradient statistics and adaboosting neural network publication-title: Signal Process. – volume: 23 start-page: 4850 issue: November (11) year: 2014 ident: 10.1016/j.patcog.2017.11.001_bib0017 article-title: Blind image quality assessment using joint statistics of gradient magnitude and Laplacian features publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2014.2355716 – volume: 17 start-page: 2338 issue: December (12) year: 2015 ident: 10.1016/j.patcog.2017.11.001_bib0027 article-title: Reduced reference stereoscopic image quality assessment based on binocular perceptual information publication-title: IEEE Trans. Multimedia doi: 10.1109/TMM.2015.2493781 – volume: 24 start-page: 2098 issue: July (7) year: 2015 ident: 10.1016/j.patcog.2017.11.001_bib0010 article-title: Fractal analysis for reduced reference image quality assessment publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2015.2413298 – volume: 23 start-page: 1527 issue: April (4) year: 2014 ident: 10.1016/j.patcog.2017.11.001_bib0023 article-title: Quality assessment of stereoscopic 3D image compression by binocular integration behaviors publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2014.2302686 – volume: 24 start-page: 2971 issue: October (10) year: 2015 ident: 10.1016/j.patcog.2017.11.001_bib0024 article-title: Full-reference quality assessment of stereoscopic images by learning binocular receptive field properties publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2015.2436332 – volume: 2008 year: 2009 ident: 10.1016/j.patcog.2017.11.001_bib0020 article-title: Quality assessment of stereoscopic images publication-title: EURASIP J. Image Video Process. – volume: 24 start-page: 3810 issue: November (11) year: 2015 ident: 10.1016/j.patcog.2017.11.001_bib0025 article-title: 3D-MAD: a full reference stereoscopic image quality estimator based on binocular lightness and contrast perception publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2015.2456414 – volume: 25 start-page: 2059 issue: May (5) year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0035 article-title: Toward a blind deep quality evaluator for stereoscopic images based on monocular and binocular interactions publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2016.2538462 – volume: 47 start-page: 346 year: 2016 ident: 10.1016/j.patcog.2017.11.001_bib0036 article-title: No-reference stereoscopic image quality assessment using binocular self-similarity and deep neural network publication-title: Signal Process. – volume: 21 start-page: 4695 issue: December (12) year: 2012 ident: 10.1016/j.patcog.2017.11.001_bib0015 article-title: No-reference image quality assessment in the spatial domain publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2012.2214050 – volume: 24 start-page: 591 issue: April (4) year: 2014 ident: 10.1016/j.patcog.2017.11.001_bib0030 article-title: No-reference quality assessment for stereoscopic images based on binocular quality perception publication-title: IEEE Trans. Circuits Syst. Video Technol. – volume: 20 start-page: 3350 issue: December (12) year: 2011 ident: 10.1016/j.patcog.2017.11.001_bib0014 article-title: Blind image quality assessment: from natural scene statistics to perceptual quality publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2011.2147325 |
| SSID | ssj0017142 |
| Score | 2.4006042 |
| Snippet | •A three-column deep non-negativity constrained sparse autoencoder is proposed for BSIQA.•Both feature evolution and feature mapping are addressed in a unified... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 242 |
| SubjectTerms | Deep learning Image quality assessment No-reference/referenceless Nonnegativity constrained Sparse autoencoder Stereoscopic 3D image |
| Title | Learning a referenceless stereopair quality engine with deep nonnegativity constrained sparse autoencoder |
| URI | https://dx.doi.org/10.1016/j.patcog.2017.11.001 |
| Volume | 76 |
| WOSCitedRecordID | wos000424853800019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: ScienceDirect customDbUrl: eissn: 1873-5142 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017142 issn: 0031-3203 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1ba9swFBYh3cNedh_rbuhhb0HFsewc-7GU7lJC6Vi35c1IllxcQmpyKe2_2E_u0c2xydgN9qIEJXKEzpdz09EnQt5BpDOZgGIVQM6SRHImy1yzrILK4DmNLdnztymcnmazWX42GPwIZ2Gu57BYZDc3efNfRY19KGxzdPYvxN0-FDvwPQodWxQ7tn8k-GlIdohRe4fI3OgzQ4mgMUaul_4o5e1IWzZCl4xVWjejhal7uQhXSpTGeTR3SKBXippnudIjsVlfGe5L5at6vV97Zmk6zdEYX4-03d0_qX1K-nO9aYKhtKSQwqZpcfHavqljNPiu61W9M_4Dvt7W3TTFOOtUt9jcWTg_sy1WsvqYjxmPI6fitFPBGXCGblxPR0NPyfrPnL2OHc3vjilwWYnLgwZN2tWFKeKDA8PX6ifVJ9n-4jgssQG7dYxGfS-GNM-GZO_w0_HspN2ZgnHiGOj9zMNxTFszuPtbP3d3Oi7M-SPywMce9NBh5jEZ6MUT8jDc60G9mn9K6gAhKmgPQnQLIeohRB2EqIEQNRCiPQjRDoSogxDtQOgZ-fr--PzoI_NXcrASY8s105AJWSkAKaOKl1Kn6F_LnCdVNsFYbcxRJUykkkmacqjQgqH_C5GKVaSl4qD4czLEaegXhIqJrlKR8jIXaEjiVGIsL3ik80mlzO73PuFh5YrS89Wb-c6LUJh4Wbj1Lsx6Yyhr6jP3CWtHNY6v5TffhyCUwvuczpcsEEe_HPnyn0e-Ive3_5DXZLhebvQbcq-8Xter5VsPuDtQcq2M |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Learning+a+referenceless+stereopair+quality+engine+with+deep+nonnegativity+constrained+sparse+autoencoder&rft.jtitle=Pattern+recognition&rft.au=Jiang%2C+Qiuping&rft.au=Shao%2C+Feng&rft.au=Lin%2C+Weisi&rft.au=Jiang%2C+Gangyi&rft.date=2018-04-01&rft.pub=Elsevier+Ltd&rft.issn=0031-3203&rft.eissn=1873-5142&rft.volume=76&rft.spage=242&rft.epage=255&rft_id=info:doi/10.1016%2Fj.patcog.2017.11.001&rft.externalDocID=S0031320317304582 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon |