{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T13:52:23Z","timestamp":1758808343185,"version":"3.41.0"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2018,9,1]],"date-time":"2018-09-01T00:00:00Z","timestamp":1535760000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61571102","61602091","61372187"],"award-info":[{"award-number":["61571102","61602091","61372187"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012551","name":"Applied Basic Research Programs of Science and Technology in Sichuan","doi-asserted-by":"publisher","award":["2018JY0035"],"award-info":[{"award-number":["2018JY0035"]}],"id":[{"id":"10.13039\/100012551","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Police College Research Program","award":["13SCJYKY42","13SCJYKY43"],"award-info":[{"award-number":["13SCJYKY42","13SCJYKY43"]}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing: Image Communication"],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1016\/j.image.2018.05.006","type":"journal-article","created":{"date-parts":[[2018,5,29]],"date-time":"2018-05-29T10:37:08Z","timestamp":1527590228000},"page":"12-21","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":18,"special_numbering":"C","title":["Visual aesthetic understanding: Sample-specific aesthetic classification and deep activation map visualization"],"prefix":"10.1016","volume":"67","author":[{"given":"Chao","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Ce","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Xun","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Yipeng","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jimin","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Tammam","family":"Tillo","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.image.2018.05.006_b1","doi-asserted-by":"crossref","unstructured":"X. Lu, Z. Lin, X. Shen, R. Mech, J.Z. Wang, Deep multi-patch aggregation network for image style, aesthetics, and quality estimation, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 990\u2013998.","DOI":"10.1109\/ICCV.2015.119"},{"key":"10.1016\/j.image.2018.05.006_b2","unstructured":"J. Guo, S. Gould, Deep CNN ensemble with data augmentation for object detection, 2015, arXiv preprint. arXiv:1506.07224."},{"key":"10.1016\/j.image.2018.05.006_b3","doi-asserted-by":"crossref","unstructured":"L. Mai, H. Jin, F. Liu, Composition-preserving deep photo aesthetics assessment, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 497\u2013506.","DOI":"10.1109\/CVPR.2016.60"},{"issue":"8","key":"10.1016\/j.image.2018.05.006_b4","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1109\/TMM.2013.2269899","article-title":"Content-based photo quality assessment","volume":"15","author":"Tang","year":"2013","journal-title":"IEEE Trans. Multimed."},{"issue":"2","key":"10.1016\/j.image.2018.05.006_b5","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.05.006_b6","doi-asserted-by":"crossref","unstructured":"N. Murray, L. Marchesotti, F. Perronnin, AVA: A large-scale database for aesthetic visual analysis, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 2408\u20132415.","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"10.1016\/j.image.2018.05.006_b7","doi-asserted-by":"crossref","unstructured":"L. Marchesotti, F. Perronnin, D. Larlus, G. Csurka, Assessing the aesthetic quality of photographs using generic image descriptors, in: IEEE International Conference on Computer Vision, 2011, pp. 1784\u20131791.","DOI":"10.1109\/ICCV.2011.6126444"},{"key":"10.1016\/j.image.2018.05.006_b8","unstructured":"A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, in: Advances in Neural Information Processing Systems, 2012, pp. 1097\u20131105."},{"key":"10.1016\/j.image.2018.05.006_b9","doi-asserted-by":"crossref","unstructured":"X. Lu, Z. Lin, H. Jin, J. Yang, J.Z. Wang, Rapid: Rating pictorial aesthetics using deep learning, in: ACM International Conference on Multimedia, 2014, pp. 457\u2013466.","DOI":"10.1145\/2647868.2654927"},{"issue":"3","key":"10.1016\/j.image.2018.05.006_b10","doi-asserted-by":"crossref","first-page":"1482","DOI":"10.1109\/TIP.2017.2651399","article-title":"Deep aesthetic quality assessment with semantic information","volume":"26","author":"Kao","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.image.2018.05.006_b11","doi-asserted-by":"crossref","unstructured":"B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, A. Torralba, Learning deep features for discriminative localization, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2921\u20132929.","DOI":"10.1109\/CVPR.2016.319"},{"issue":"2","key":"10.1016\/j.image.2018.05.006_b12","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1109\/TPAMI.2010.70","article-title":"Learning to detect a salient object","volume":"33","author":"Liu","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2018.05.006_b13","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1016\/j.image.2016.05.004","article-title":"Hierarchical aesthetic quality assessment using deep convolutional neural networks","volume":"47","author":"Kao","year":"2016","journal-title":"Signal Process., Image Commun."},{"key":"10.1016\/j.image.2018.05.006_b14","doi-asserted-by":"crossref","unstructured":"C. Huang, Y. Li, C. Change Loy, X. Tang, Learning deep representation for imbalanced classification, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 5375\u20135384.","DOI":"10.1109\/CVPR.2016.580"},{"key":"10.1016\/j.image.2018.05.006_b15","series-title":"Neural Networks (IJCNN), 2016 International Joint Conference on","first-page":"4368","article-title":"Training deep neural networks on imbalanced data sets","author":"Wang","year":"2016"},{"key":"10.1016\/j.image.2018.05.006_b16","doi-asserted-by":"crossref","unstructured":"S. Kong, X. Shen, Z. Lin, R. Mech, C. Fowlkes, Photo aesthetics ranking network with attributes and content adaptation, in: European Conference on Computer Vision, 2016, pp. 662\u2013679.","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"10.1016\/j.image.2018.05.006_b17","series-title":"Cognition in the Wild. 1995, vol. 14","first-page":"399","author":"Hutchins","year":"1995"},{"issue":"6","key":"10.1016\/j.image.2018.05.006_b18","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1109\/TNNLS.2014.2336852","article-title":"Blind image quality assessment via deep learning","volume":"26","author":"Hou","year":"2015","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"2","key":"10.1016\/j.image.2018.05.006_b19","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/1348246.1348248","article-title":"Image retrieval: Ideas, influences, and trends of the new age","volume":"40","author":"Datta","year":"2008","journal-title":"ACM Comput. Surv."},{"issue":"6","key":"10.1016\/j.image.2018.05.006_b20","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1145\/2661229.2661287","article-title":"Mirror mirror: Crowdsourcing better portraits","volume":"33","author":"Zhu","year":"2014","journal-title":"ACM Trans. Graph."},{"issue":"11","key":"10.1016\/j.image.2018.05.006_b21","doi-asserted-by":"crossref","first-page":"1955","DOI":"10.1109\/TPAMI.2010.36","article-title":"Age synthesis and estimation via faces: A survey","volume":"32","author":"Fu","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.image.2018.05.006_b22","doi-asserted-by":"crossref","unstructured":"H. Han, C. Otto, A.K. Jain, Age estimation from face images: Human vs. machine performance, in: IEEE International Conference on Biometrics, 2013, pp. 1\u20138.","DOI":"10.1109\/ICB.2013.6613022"},{"issue":"11","key":"10.1016\/j.image.2018.05.006_b23","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.image.2018.05.006_b24","unstructured":"G.E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, R.R. Salakhutdinov, Improving neural networks by preventing co-adaptation of feature detectors, 2012, arXiv preprint. arXiv:1207.0580."},{"key":"10.1016\/j.image.2018.05.006_b25","unstructured":"K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, 2014, arXiv preprint. arXiv:1409.1556."},{"key":"10.1016\/j.image.2018.05.006_b26","doi-asserted-by":"crossref","unstructured":"C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going deeper with convolutions, 2014, arXiv preprint. arXiv:1409.4842.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10.1016\/j.image.2018.05.006_b27","doi-asserted-by":"crossref","unstructured":"G. Levi, T. Hassner, Age and gender classification using convolutional neural networks, in: IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW, 2015, pp. 34\u201342.","DOI":"10.1109\/CVPRW.2015.7301352"},{"key":"10.1016\/j.image.2018.05.006_b28","series-title":"Asian Conference on Computer Vision","first-page":"144","article-title":"Age estimation by multi-scale convolutional network","author":"Yi","year":"2015"},{"key":"10.1016\/j.image.2018.05.006_b29","doi-asserted-by":"crossref","unstructured":"T. Malisiewicz, A. Gupta, A. Efros, et al., Ensemble of exemplar-SVMs for object detection and beyond, in: IEEE International Conference on Computer Vision, 2011, pp. 89\u201396.","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"10.1016\/j.image.2018.05.006_b30","doi-asserted-by":"crossref","unstructured":"R. Datta, D. Joshi, J. Li, J.Z. Wang, Studying aesthetics in photographic images using a computational approach, in: European Conference on Computer Vision, 2006, pp. 288\u2013301.","DOI":"10.1007\/11744078_23"},{"issue":"3","key":"10.1016\/j.image.2018.05.006_b31","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1007\/s11263-014-0789-2","article-title":"Discovering beautiful attributes for aesthetic image analysis","volume":"113","author":"Marchesotti","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.image.2018.05.006_b32","unstructured":"Y. Deng, C.C. Loy, X. Tang, Image aesthetic assessment: An experimental survey, 2016, arXiv preprint. arXiv:1610.00838."},{"key":"10.1016\/j.image.2018.05.006_b33","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1016\/j.image.2016.05.009","article-title":"A multi-scene deep learning model for image aesthetic evaluation","volume":"47","author":"Wang","year":"2016","journal-title":"Signal Process., Image Commun."},{"key":"10.1016\/j.image.2018.05.006_b34","unstructured":"F. Stentiford, Attention based auto image cropping, in: Workshop on Computational Attention and Applications, ICVS, 2007."},{"key":"10.1016\/j.image.2018.05.006_b35","doi-asserted-by":"crossref","unstructured":"J. Chen, G. Bai, S. Liang, Z. Li, Automatic image cropping: A computational complexity study, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 507\u2013515.","DOI":"10.1109\/CVPR.2016.61"},{"key":"10.1016\/j.image.2018.05.006_b36","doi-asserted-by":"crossref","unstructured":"M. Nishiyama, T. Okabe, Y. Sato, I. Sato, Sensation-based photo cropping, in: Proceedings of the 17th ACM International Conference on Multimedia, 2009, pp. 669\u2013672.","DOI":"10.1145\/1631272.1631384"},{"key":"10.1016\/j.image.2018.05.006_b37","doi-asserted-by":"crossref","unstructured":"C. Fang, Z. Lin, R. M\u011bch, X. Shen, Automatic image cropping using visual composition, boundary simplicity and content preservation models, in: Proceedings of the 22nd ACM International Conference on Multimedia, 2014, pp. 1105\u20131108.","DOI":"10.1145\/2647868.2654979"},{"key":"10.1016\/j.image.2018.05.006_b38","doi-asserted-by":"crossref","unstructured":"Y.-L. Chen, T.-W. Huang, K.-H. Chang, Y.-C. Tsai, H.-T. Chen, B.-Y. Chen, Quantitative analysis of automatic image cropping algorithms: A dataset and comparative study, in: IEEE Winter Conference on Applications of Computer Vision, 2017, pp. 226\u2013234.","DOI":"10.1109\/WACV.2017.32"},{"key":"10.1016\/j.image.2018.05.006_b39","doi-asserted-by":"crossref","unstructured":"K. Yueying, R. He, H. Kaiqi, Automatic image cropping with aesthetic map and gradient energy map, in: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2017, pp. 1982\u20131986.","DOI":"10.1109\/ICASSP.2017.7952503"},{"key":"10.1016\/j.image.2018.05.006_b40","unstructured":"K. Schwarz, P. Wieschollek, H. Lensch, Will people like your image? 2016, arXiv preprint. arXiv:1611.05203."}],"container-title":["Signal Processing: Image Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596518303515?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0923596518303515?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T20:34:48Z","timestamp":1751661288000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0923596518303515"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":40,"alternative-id":["S0923596518303515"],"URL":"https:\/\/doi.org\/10.1016\/j.image.2018.05.006","relation":{},"ISSN":["0923-5965"],"issn-type":[{"type":"print","value":"0923-5965"}],"subject":[],"published":{"date-parts":[[2018,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Visual aesthetic understanding: Sample-specific aesthetic classification and deep activation map visualization","name":"articletitle","label":"Article Title"},{"value":"Signal Processing: Image Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.image.2018.05.006","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2018 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}