{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:20:56Z","timestamp":1740108056594,"version":"3.37.3"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T00:00:00Z","timestamp":1641427200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T00:00:00Z","timestamp":1641427200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001807","name":"FAPESP","doi-asserted-by":"crossref","award":["2018\/22482-0","2019\/07316-0"],"award-info":[{"award-number":["2018\/22482-0","2019\/07316-0"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003593","name":"CNPq","doi-asserted-by":"crossref","award":["04266\/2020-5"],"award-info":[{"award-number":["04266\/2020-5"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s00521-021-06601-7","type":"journal-article","created":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T00:05:58Z","timestamp":1641427558000},"page":"4459-4471","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Robust image features for classification and zero-shot tasks by merging visual and semantic attributes"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1367-9561","authenticated-orcid":false,"given":"Damares Crystina Oliveira","family":"de Resende","sequence":"first","affiliation":[]},{"given":"Moacir Antonelli","family":"Ponti","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,6]]},"reference":[{"issue":"4","key":"6601_CR1","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1002\/wics.101","volume":"2","author":"H Abdi","year":"2010","unstructured":"Abdi H, Williams LJ (2010) Principal component analysis. Wiley Interdiscip Rev Comput Stat 2(4):433\u2013459","journal-title":"Wiley Interdiscip Rev Comput Stat"},{"issue":"7","key":"6601_CR2","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1109\/TPAMI.2015.2487986","volume":"38","author":"Z Akata","year":"2015","unstructured":"Akata Z, Perronnin F, Harchaoui Z, Schmid C (2015) Label-embedding for image classification. IEEE Transactions Pattern Anal Mach Intell 38(7):1425\u20131438","journal-title":"IEEE Transactions Pattern Anal Mach Intell"},{"key":"6601_CR3","doi-asserted-by":"crossref","unstructured":"Almousli H, Vincent P (2013) Semi supervised autoencoders: better focusing model capacity during feature extraction In: International Conference on Neural Information Processing, Springer pp 328\u2013335","DOI":"10.1007\/978-3-642-42054-2_41"},{"issue":"2","key":"6601_CR4","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1037\/0033-295X.94.2.115","volume":"94","author":"I Biederman","year":"1987","unstructured":"Biederman I (1987) Recognition-by-components: a theory of human image understanding. Psychol Rev 94(2):115","journal-title":"Psychol Rev"},{"key":"6601_CR5","doi-asserted-by":"crossref","unstructured":"Brodersen KH, Ong CS, Stephan KE, Buhmann JM (2010) The balanced accuracy and its posterior distribution In: 2010 20th International Conference on Pattern Recognition IEEE pp 3121\u20133124","DOI":"10.1109\/ICPR.2010.764"},{"key":"6601_CR6","doi-asserted-by":"crossref","unstructured":"Cavallari G, Ribeiro L, Ponti M (2018) Unsupervised representation learning using convolutional and stacked auto-encoders: a domain and cross-domain feature space analysis In: 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) IEEE pp 440\u2013446","DOI":"10.1109\/SIBGRAPI.2018.00063"},{"issue":"1\u201317","key":"6601_CR7","first-page":"1","volume":"12","author":"L Cayton","year":"2005","unstructured":"Cayton L (2005) Algorithms for manifold learning. Univ California San Diego Tech Rep 12(1\u201317):1","journal-title":"Univ California San Diego Tech Rep"},{"key":"6601_CR8","unstructured":"Chollet F (2015) Keras https:\/\/github.com\/fchollet\/keras"},{"key":"6601_CR9","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database In: CVPR09","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6601_CR10","doi-asserted-by":"crossref","unstructured":"Deselaers T, Ferrari V (2011) Visual and semantic similarity in imagenet In: CVPR 2011, pp 1777\u20131784 IEEE","DOI":"10.1109\/CVPR.2011.5995474"},{"key":"6601_CR11","doi-asserted-by":"crossref","unstructured":"Farhadi A, Endres I, Hoiem D, Forsyth D (2009) Describing objects by their attributes In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE pp 1778\u20131785","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"6601_CR12","doi-asserted-by":"crossref","unstructured":"Ge Z, Demyanov S, Bozorgtabar B, Abedini M, Chakravorty R, Bowling A, Garnavi R (2017) Exploiting local and generic features for accurate skin lesions classification using clinical and dermoscopy imaging In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), IEEE pp 986\u2013990","DOI":"10.1109\/ISBI.2017.7950681"},{"key":"6601_CR13","volume-title":"Syntactic pattern recognition: an introduction","author":"RC Gonzalez","year":"1978","unstructured":"Gonzalez RC, Thomason MG (1978) Syntactic pattern recognition: an introduction. Addison-Wesley, Reading, MA"},{"issue":"12","key":"6601_CR14","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1162\/0899766042321814","volume":"16","author":"DR Hardoon","year":"2004","unstructured":"Hardoon DR, Szedmak S, Shawe-Taylor J (2004) Canonical correlation analysis: an overview with application to learning methods. Neural Comput 16(12):2639\u20132664","journal-title":"Neural Comput"},{"key":"6601_CR15","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition In: Proceedings of the IEEE conference on computer vision and pattern recognition pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"6601_CR16","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1007\/978-1-4612-4380-9_14","volume-title":"Breakthroughs in statistics","author":"H Hotelling","year":"1992","unstructured":"Hotelling H (1992) Relations between two sets of variates. Breakthroughs in statistics. Springer, New York, NY, pp 162\u2013190"},{"key":"6601_CR17","unstructured":"Jayaraman D, Grauman K (2014) Zero-shot recognition with unreliable attributes In: Advances in neural information processing systems pp 3464\u20133472"},{"key":"6601_CR18","doi-asserted-by":"crossref","unstructured":"Juan DC, Lu CT, Li Z, Peng F, Timofeev A, Chen YT, Gao Y, Duerig T, Tomkins A, Ravi S (2019) Graph-rise: Graph-regularized image semantic embedding arXiv preprint arXiv:1902.10814","DOI":"10.1145\/3336191.3371784"},{"key":"6601_CR19","doi-asserted-by":"crossref","unstructured":"Kodirov E, Xiang T, Gong S (2017) Semantic autoencoder for zero-shot learning In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp 3174\u20133183","DOI":"10.1109\/CVPR.2017.473"},{"key":"6601_CR20","doi-asserted-by":"crossref","unstructured":"Lampert CH, Nickisch H, Harmeling S (2009) Learning to detect unseen object classes by between-class attribute transfer In: 2009 IEEE Conference on Computer Vision and Pattern Recognition IEEE pp 951\u2013958","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"6601_CR21","doi-asserted-by":"crossref","unstructured":"Lin TY, RoyChowdhury A, Maji S (2015) Bilinear cnn models for fine-grained visual recognition In: Proceedings of the IEEE International Conference on Computer Vision pp 1449\u20131457","DOI":"10.1109\/ICCV.2015.170"},{"key":"6601_CR22","unstructured":"Lu Y (2015) Unsupervised learning on neural network outputs: with application in zero-shot learning arXiv preprint arXiv:1506.00990"},{"key":"6601_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-94989-5","volume-title":"Machine learning: a practical approach on the statistical learning theory","author":"RF Mello","year":"2018","unstructured":"Mello RF, Ponti MA (2018) Machine learning: a practical approach on the statistical learning theory. Springer, New York"},{"key":"6601_CR24","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space arXiv preprint arXiv:1301.3781"},{"key":"6601_CR25","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp 3111\u20133119."},{"key":"6601_CR26","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines In: ICML"},{"issue":"1\u20132","key":"6601_CR27","first-page":"59","volume":"108","author":"G Patterson","year":"2014","unstructured":"Patterson G, Xu C, Su H, Hays J (2014) The sun attribute database: beyond categories for deeper scene understanding. Int J Computer V 108(1\u20132):59\u201381","journal-title":"Int J Computer V"},{"key":"6601_CR28","doi-asserted-by":"crossref","unstructured":"Ponti MA, Ribeiro LSF, Nazare TS, Bui T, Collomosse J (2017) Everything you wanted to know about deep learning for computer vision but were afraid to ask In: 30th SIBGRAPI conference on graphics, patterns and images tutorials (SIBGRAPI-T), IEEE pp 17\u201341","DOI":"10.1109\/SIBGRAPI-T.2017.12"},{"key":"6601_CR29","doi-asserted-by":"crossref","unstructured":"Ponti MA, Santos FPd, Ribeiro LSF, Cavallari GB (2021) Training deep networks from zero to hero: avoiding pitfalls and going beyond In: SIBGRAPI - Conference on graphics, patterns and images","DOI":"10.1109\/SIBGRAPI54419.2021.00011"},{"key":"6601_CR30","unstructured":"Ranzato M, Boureau YL, Chopra S, LeCun Y (2007) A unified energy-based framework for unsupervised learning In: Artificial Intelligence and Statistics, pp 371\u2013379"},{"key":"6601_CR31","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement arXiv preprint arXiv:1804.02767"},{"key":"6601_CR32","unstructured":"Ren Z, Jin H, Lin Z, Fang C, Yuille A (2015) Multi-instance visual-semantic embedding arXiv preprint arXiv:1512.06963"},{"key":"6601_CR33","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"PJ Rousseeuw","year":"1987","unstructured":"Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53\u201365","journal-title":"J Comput Appl Math"},{"issue":"5500","key":"6601_CR34","doi-asserted-by":"publisher","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","volume":"290","author":"ST Roweis","year":"2000","unstructured":"Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323\u20132326","journal-title":"Science"},{"key":"6601_CR35","unstructured":"Silberer C, Ferrari V, Lapata M (2013) Models of semantic representation with visual attributes In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), vol\u00a01, pp 572\u2013582"},{"issue":"1","key":"6601_CR36","first-page":"59","volume":"100","author":"Y Su","year":"2012","unstructured":"Su Y, Jurie F (2012) Improving image classification using semantic attributes. Int J Computer V 100(1):59\u201377","journal-title":"Int J Computer V"},{"key":"6601_CR37","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"6601_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"issue":"5500","key":"6601_CR39","doi-asserted-by":"publisher","first-page":"2319","DOI":"10.1126\/science.290.5500.2319","volume":"290","author":"JB Tenenbaum","year":"2000","unstructured":"Tenenbaum JB, De Silva V, Langford JC (2000) A global geometric framework for nonlinear dimensionality reduction. Science 290(5500):2319\u20132323","journal-title":"Science"},{"key":"6601_CR40","doi-asserted-by":"crossref","unstructured":"Vogel J, Schiele B (2004) Natural scene retrieval based on a semantic modeling step In: International Conference on Image and Video Retrieval Springer pp 207\u2013215","DOI":"10.1007\/978-3-540-27814-6_27"},{"key":"6601_CR41","unstructured":"Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The Caltech-UCSD Birds-200-2011 Dataset Tech Rep CNS-TR-2011-001, California Institute of Technology"},{"key":"6601_CR42","doi-asserted-by":"crossref","unstructured":"Wang J, Yang Y, Mao J, Huang Z, Huang C, Xu W (2016) Cnn-rnn: a unified framework for multi-label image classification In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2285\u20132294","DOI":"10.1109\/CVPR.2016.251"},{"key":"6601_CR43","doi-asserted-by":"crossref","unstructured":"Xian Y, Akata Z, Sharma G, Nguyen Q, Hein M, Schiele B (2016) Latent embeddings for zero-shot classification In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 69\u201377","DOI":"10.1109\/CVPR.2016.15"},{"issue":"9","key":"6601_CR44","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.1109\/TPAMI.2018.2857768","volume":"41","author":"Y Xian","year":"2018","unstructured":"Xian Y, Lampert CH, Schiele B, Akata Z (2018) Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. IEEE Transactions Pattern Anal Mach Intell 41(9):2251\u20132265","journal-title":"IEEE Transactions Pattern Anal Mach Intell"},{"key":"6601_CR45","doi-asserted-by":"crossref","unstructured":"Xian Y, Lorenz T, Schiele B, Akata Z (2018) Feature generating networks for zero-shot learning In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00581"},{"key":"6601_CR46","doi-asserted-by":"crossref","unstructured":"Xian Y, Schiele B, Akata Z (2017) Zero-shot learning - the good, the bad and the ugly In: IEEE Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2017.328"},{"key":"6601_CR47","doi-asserted-by":"crossref","unstructured":"Xiao J, Hays J, Ehinger K.A, Oliva A, Torralba A (2010) Sun database: large-scale scene recognition from abbey to zoo In: 2010 IEEE computer society conference on computer vision and pattern recognition, IEEE pp 3485\u20133492","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"6601_CR48","doi-asserted-by":"crossref","unstructured":"Xu H, Qi G, Li J, Wang M, Xu K, Gao H (2018) Fine-grained image classification by visual-semantic embedding In: IJCAI, pp 1043\u20131049","DOI":"10.24963\/ijcai.2018\/145"},{"key":"6601_CR49","unstructured":"Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? In: Advances in neural information processing systems, pp 3320\u20133328"},{"issue":"10","key":"6601_CR50","doi-asserted-by":"publisher","first-page":"2801","DOI":"10.1109\/TMM.2018.2812605","volume":"20","author":"J Zhang","year":"2018","unstructured":"Zhang J, Wu Q, Shen C, Zhang J, Lu J (2018) Multilabel image classification with regional latent semantic dependencies. IEEE Transactions Multimedia 20(10):2801\u20132813","journal-title":"IEEE Transactions Multimedia"},{"key":"6601_CR51","unstructured":"Zhang Z, Saligrama V (20136 Zero-shot learning via joint latent similarity embedding In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp 6034\u20136042"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06601-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06601-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06601-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,2]],"date-time":"2022-03-02T16:26:54Z","timestamp":1646238414000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06601-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,6]]},"references-count":51,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["6601"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06601-7","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2022,1,6]]},"assertion":[{"value":"24 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Source code can be found at a public Git repository .","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}]}}