{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T07:55:27Z","timestamp":1782460527507,"version":"3.54.5"},"reference-count":46,"publisher":"Tsinghua University Press","issue":"1","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,11,28]],"date-time":"2020-11-28T00:00:00Z","timestamp":1606521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1007\/s41095-020-0193-5","type":"journal-article","created":{"date-parts":[[2020,11,28]],"date-time":"2020-11-28T08:02:43Z","timestamp":1606550563000},"page":"139-152","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Learning to assess visual aesthetics of food images"],"prefix":"10.26599","volume":"7","author":[{"given":"Kekai","family":"Sheng","sequence":"first","affiliation":[{"name":"Youtu Lab, Tencent, Shanghai 200233, China; NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiming","family":"Dong","sequence":"additional","affiliation":[{"name":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibin","family":"Huang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing 100085, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menglei","family":"Chai","sequence":"additional","affiliation":[{"name":"Snap Inc., Santa Monica, 90405, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[{"name":"AI Lab, Tencent Inc., Shenzhen 518000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing 100085, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bao-Gang","family":"Hu","sequence":"additional","affiliation":[{"name":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"193_CR1","unstructured":"Manna, L. Digital food photography. Cengage Learning PTR, 2015."},{"key":"193_CR2","unstructured":"Murray, N.; Marchesotti, L.; Perronnin, F. Ava: A large-scale database for aesthetic visual analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2408\u20132415, 2012."},{"key":"193_CR3","unstructured":"Ma, S.; Liu, J.; Chen, C. W. A-lamp: Adaptive layout-aware multi-patch deep convolutional neural network for photo aesthetic assessment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 722\u2013731, 2017."},{"key":"193_CR4","doi-asserted-by":"crossref","unstructured":"Hosu, V.; Goldl\u00fccke, B.; Saupe, D. Efiective aesthetics prediction with multi-level spatially pooled features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 9367\u20139375, 2019.","DOI":"10.1109\/CVPR.2019.00960"},{"key":"193_CR5","first-page":"446","volume-title":"Computer Vision-ECCV 2014. Lecture Notes in Computer Science, Vol. 8694","author":"L Bossard","year":"2014","unstructured":"Bossard, L.; Guillaumin, M.; van Gool, L. Food-101\u2014mining discriminative components with random forests. In: Computer Vision-ECCV 2014. Lecture Notes in Computer Science, Vol. 8694. Fleet, D.; Pajdla, T.; Schiele, B.; Tuytelaars, T. Eds. Springer Cham, 446\u2013461, 2014."},{"issue":"3","key":"193_CR6","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/s11390-016-1642-6","volume":"31","author":"X J Zhang","year":"2016","unstructured":"Zhang, X. J.; Lu, Y. F.; Zhang, S. H. Multi-task learning for food identification and analysis with deep convolutional neural networks. Journal of Computer Science and Technology Vol. 31, No. 3, 489\u2013500, 2016.","journal-title":"Journal of Computer Science and Technology"},{"key":"193_CR7","doi-asserted-by":"crossref","unstructured":"Salvador, A.; Hynes, N.; Aytar, Y.; Marin, J.; Oi, F.; Weber, I.; Torralba, A. Learning cross-modal embeddings for cooking recipes and food images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3068\u20133076, 2017.","DOI":"10.1109\/CVPR.2017.327"},{"key":"193_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y.; Sheopuri, A. Applying image analysis to assess food aesthetics and uniqueness. In: Proceedings of the IEEE International Conference on Image Processing, 311\u2013314, 2015.","DOI":"10.1109\/ICIP.2015.7350810"},{"key":"193_CR9","unstructured":"Luo, W.; Wang, X.; Tang, X. Content-based photo quality assessment. In: Proceedings of the IEEE International Conference on Computer Vision, 2206\u20132213, 2011."},{"key":"193_CR10","unstructured":"Chen, X.; Zhu, Y.; Zhou, H.; Diao, L.; Wang, D. ChineseFoodNet: A large-scale image dataset for chinese food recognition. arXiv preprint arXiv:1705.02743, 2017."},{"key":"193_CR11","doi-asserted-by":"crossref","unstructured":"Sheng, K. K.; Dong, W. M.; Huang, H. B.; Ma, C. Y.; Hu, B. G. Gourmet photography dataset for aesthetic assessment of food images. In: Proceedings of the SIGGRAPH Asia 2018 Technical Briefs, Article No. 20, 2018.","DOI":"10.1145\/3283254.3283260"},{"key":"193_CR12","first-page":"288","volume-title":"Computer Vision-ECCV 2006. Lecture Notes in Computer Science, Vol. 3953","author":"R Datta","year":"2006","unstructured":"Datta, R.; Joshi, D.; Li, J.; Wang, J. Z. Studying aesthetics in photographic images using a computational approach. In: Computer Vision-ECCV 2006. Lecture Notes in Computer Science, Vol. 3953. Leonardis, A.; Bischof, H.; Pinz, A. Eds. Springer Berlin Heidelberg, 288\u2013301, 2006."},{"issue":"7","key":"193_CR13","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TMM.2013.2268051","volume":"15","author":"F L Zhang","year":"2013","unstructured":"Zhang, F. L., Wang, M.; Hu, S. M. Aesthetic image enhancement by dependence-aware object recomposition. IEEE Transactions on Multimedia Vol. 15, No. 7, 1480\u20131490, 2013.","journal-title":"IEEE Transactions on Multimedia"},{"key":"193_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1007\/978-3-319-46448-0_40","volume-title":"Computer Vision-ECCV 2016","author":"S Kong","year":"2016","unstructured":"Kong, S.; Shen, X. H.; Lin, Z.; Mech, R.; Fowlkes, C. Photo aesthetics ranking network with attributes and content adaptation. In: Computer Vision-ECCV 2016. Lecture Notes in Computer Science, Vol. 9905. Leibe, B.; Matas, J.; Sebe, N.; Welling, M. Eds. Springer Cham, 662\u2013679, 2016."},{"key":"193_CR15","doi-asserted-by":"crossref","unstructured":"Lu, X.; Lin, Z.; Shen, X.; Mech, R.; Wang, J. Z. Deep multi-patch aggregation network for image style, aesthetics, and quality estimation. In: Proceedings of the IEEE International Conference on Computer Vision, 990\u2013998, 2015.","DOI":"10.1109\/ICCV.2015.119"},{"issue":"8","key":"193_CR16","doi-asserted-by":"publisher","first-page":"3998","DOI":"10.1109\/TIP.2018.2831899","volume":"27","author":"H Talebi","year":"2018","unstructured":"Talebi, H., Milanfar, P. NIMA: Neural image assessment. IEEE Transactions on Image Processing Vol. 27, No. 8, 3998\u20134011, 2018.","journal-title":"IEEE Transactions on Image Processing"},{"key":"193_CR17","doi-asserted-by":"crossref","unstructured":"Sheng, K. K.; Dong, W. M.; Ma, C. Y.; Mei, X.; Huang, F. Y.; Hu, B. G. Attention-based multipatch aggregation for image aesthetic assessment. In: Proceedings of the 26th ACM International Conference on Multimedia, 879\u2013886, 2018.","DOI":"10.1145\/3240508.3240554"},{"issue":"10","key":"193_CR18","doi-asserted-by":"publisher","first-page":"5100","DOI":"10.1109\/TIP.2018.2845100","volume":"27","author":"M Kucer","year":"2018","unstructured":"Kucer, M.; Loui, A. C.; Messinger, D. W. Leveraging expert feature knowledge for predicting image aesthetics. IEEE Transactions on Image Processing Vol. 27, No. 10, 5100\u20135112, 2018.","journal-title":"IEEE Transactions on Image Processing"},{"key":"193_CR19","doi-asserted-by":"publisher","unstructured":"Liu, Z. G.; Wang, Z. P.; Yao, Y. Y.; Zhang, L. M.; Shao, L. Deep active learning with contaminated tags for image aesthetics assessment. IEEE Transactions on Image Processing doi: https:\/\/doi.org\/10.1109\/TIP.2018.2828326, 2018.","DOI":"10.1109\/TIP.2018.2828326"},{"key":"193_CR20","unstructured":"Sun, R.; Lian, Z.; Tang, Y.; Xiao, J. Aesthetic visual quality evaluation of Chinese handwritings. In: Proceedings of the International Joint Conferences on Artificial Intelligence, 2510\u20132516, 2015."},{"key":"193_CR21","doi-asserted-by":"crossref","unstructured":"Chang, H. W.; Yu, F.; Wang, J.; Ashley, D.; Finkelstein, A. Automatic triage for a photo series. ACM Transactions on Graphics Vol. 35, No. 4, Article No. 148, 2016.","DOI":"10.1145\/2897824.2925908"},{"key":"193_CR22","unstructured":"Chang, K.-Y.; Lu, K.-H.; Chen, C.-S. Aesthetic critiques generation for photos. In: Proceedings of the IEEE International Conference on Computer Vision, 3514\u20133523, 2017."},{"key":"193_CR23","doi-asserted-by":"crossref","unstructured":"Hung, W.-C.; Zhang, J.; Shen, X.; Lin, Z.; Lee, J.-Y.; Yang, M.-H. Learning to blend photos. In: Proceedings of the European Conference on Computer Vision, 70\u201386, 2018.","DOI":"10.1007\/978-3-030-01234-2_5"},{"key":"193_CR24","doi-asserted-by":"crossref","unstructured":"Yu, W. H.; Zhang, H. D.; He, X. N.; Chen, X.; Xiong, L.; Qin, Z. Aesthetic-based clothing recommendation. In: Proceedings of the World Wide Web Conference, 649\u2013658, 2018.","DOI":"10.1145\/3178876.3186146"},{"key":"193_CR25","doi-asserted-by":"crossref","unstructured":"Hassannejad, H.; Matrella, G.; Ciampolini, P.; de Munari, I.; Mordonini, M.; Cagnoni, S. Food image recognition using very deep convolutional networks. In: Proceedings of the 2nd International Workshop on Multimedia Assisted Dietary Management, 41\u201349, 2016.","DOI":"10.1145\/2986035.2986042"},{"key":"193_CR26","unstructured":"Meyers, A.; Johnston, N.; Rathod, V.; Korattikara, A.; Gorban, A.; Silberman, N.; Guadarrama, S.; Papandreou, G.; Huang, J.; Murphy, K. P. Im2Calories: Towards an automated mobile vision food diary. In: Proceedings of the IEEE International Conference on Computer Vision, 1233\u20131241, 2015."},{"key":"193_CR27","unstructured":"Hinton, G. E.; Vinyals, O.; Dean, J. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2014."},{"key":"193_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy, C.; Vanhoucke, V.; Iofie, S.; Shlens, J.; Z. Wojna. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818\u20132826, 2016.","DOI":"10.1109\/CVPR.2016.308"},{"issue":"1","key":"193_CR29","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research Vol. 15, No. 1, 1929\u20131958, 2014.","journal-title":"Journal of Machine Learning Research"},{"issue":"6","key":"193_CR30","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A.; Sutskever, I.; Hinton, G. E. ImageNet classification with deep convolutional neural networks. Communications of the ACM Vol. 60, No. 6, 84\u201390, 2017.","journal-title":"Communications of the ACM"},{"key":"193_CR31","doi-asserted-by":"crossref","unstructured":"Hein, M.; Andriushchenko, M.; Bitterwolf, J. Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 41\u201350, 2019.","DOI":"10.1109\/CVPR.2019.00013"},{"key":"193_CR32","doi-asserted-by":"crossref","unstructured":"Manning, C. D.; Raghavan, P.; Sch\u00fctze, H. Introduction to Information Retrieval. Cambridge University Press, 2008.","DOI":"10.1017\/CBO9780511809071"},{"key":"193_CR33","unstructured":"Deng, J.; Dong, W.; Socher, R.; Li, L.-J.; Li, K.; Fei-Fei, L. ImageNet: A large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 248\u2013255, 2009."},{"key":"193_CR34","doi-asserted-by":"crossref","unstructured":"Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1\u20139, 2015.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"193_CR35","doi-asserted-by":"crossref","unstructured":"He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"3","key":"193_CR36","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva, A.; Torralba, A. Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision Vol. 42, No. 3, 145\u2013175, 2001.","journal-title":"International Journal of Computer Vision"},{"key":"193_CR37","unstructured":"Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556v6, 2015."},{"issue":"6","key":"193_CR38","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B L Zhou","year":"2018","unstructured":"Zhou, B. L.; Lapedriza, A.; Khosla, A.; Oliva, A.; Torralba, A. Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 40, No. 6, 1452\u20131464, 2018.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"193_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, R.; Efros, A. A.; Shechtman, E.; Wang, O. The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 586\u2013595, 2018.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"193_CR40","doi-asserted-by":"crossref","unstructured":"Mai, L.; Jin, H.; Liu, F. Composition-preserving deep photo aesthetics assessment. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 497\u2013506, 2016.","DOI":"10.1109\/CVPR.2016.60"},{"issue":"11","key":"193_CR41","doi-asserted-by":"publisher","first-page":"2815","DOI":"10.1109\/TMM.2019.2911428","volume":"21","author":"X D Zhang","year":"2019","unstructured":"Zhang, X. D.; Gao, X. B.; Lu, W.; He, L. H. A gated peripheral-foveal convolutional neural network for unified image aesthetic prediction. IEEE Transactions on Multimedia Vol. 21, No. 11, 2815\u20132826, 2019.","journal-title":"IEEE Transactions on Multimedia"},{"key":"193_CR42","doi-asserted-by":"crossref","unstructured":"Deng, Y.; Loy, C. C.; Tang, X. Aesthetic-driven image enhancement by adversarial learning. In: Proceedings of the 26th ACM International Conference on Multimedia, 870\u2013878, 2018.","DOI":"10.1145\/3240508.3240531"},{"key":"193_CR43","doi-asserted-by":"crossref","unstructured":"Hu, Y.; He, H.; Xu, C.; Wang, B.; Lin, S. Exposure: A white-box photo post-processing framework. ACM Transactions on Graphics Vol. 37, No. 2, Article No. 26, 2018.","DOI":"10.1145\/3181974"},{"issue":"5","key":"193_CR44","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1109\/TPAMI.2016.2637331","volume":"40","author":"Z Xu","year":"2018","unstructured":"Xu, Z.; Huang, S. L.; Zhang, Y.; Tao, D. C. Webly-supervised fine-grained visual categorization via deep domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 40, No. 5, 1100\u20131113, 2018.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"193_CR45","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1111\/cgf.12760","volume":"34","author":"K K Sheng","year":"2015","unstructured":"Sheng, K. K.; Dong, W. M.; Kong, Y.; Mei, X.; Li, J. L.; Wang, C. J.; Huang, F.; Hu, B. Evaluating the quality of face alignment without ground truth. Computer Graphics Forum Vol. 34, No. 7, 213\u2013223, 2015.","journal-title":"Computer Graphics Forum"},{"key":"193_CR46","unstructured":"Papadopoulos, D. P.; Tamaazousti, Y.; Oi, F.; Weber, I.; Torralba, A. How to make a pizza: Learning a compositional layer-based GAN model. In: proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8002\u20138011, 2019."}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-020-0193-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s41095-020-0193-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-020-0193-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10897406\/10897416.pdf?arnumber=10897416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:38:25Z","timestamp":1762367905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10897416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":46,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1007\/s41095-020-0193-5","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2021,3]]},"assertion":[{"value":"9 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}