Image Aesthetic Assessment: An experimental survey
Open accessThe DOI matches its Crossref record; 100 of the 100 references it cites were found in a registry or an index.
Abstract
This article reviews recent computer vision techniques used in the assessment of image aesthetic quality. Image aesthetic assessment aims at computationally distinguishing high-quality from low-quality photos based on photographic rules, typically in the form of binary classification or quality scoring. A variety of approaches has been proposed in the literature to try to solve this challenging problem. In this article, we summarize these approaches based on visual feature types (hand-crafted features and deep features) and evaluation criteria (data set characteristics and evaluation metrics). The main contributions and novelties of the reviewed approaches are highlighted and discussed. In addition, following the emergence of deep-learning techniques, we systematically evaluate recent deep-learning settings that are useful for developing a robust deep model for aesthetic scoring.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In theory, however, LMX can be generically applied to most EAs, e.g.multi-objective EAs [23,29], evolutionary strategies [1,5], or in support of open-ended evolution [121], but simply swapping it in as the genetic variation operator.”
From Language Model Crossover: Variation through Few-Shot Prompting (2024) · cites this paper as [29]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“It is worth pointing out that other more recent and deeper models such as ResNet [63] or Inception-ResNet [64] could serve as a pre-trained model.”
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 6×
“19, we observe that the convolutional response of the vanilla VGG-16 (ImageNet) for object recognition typically finds a precise focus of the salient object in view, while the 1-column CNN baseline (DAN-1-original for aesthetic quality classification) outputs an “aestheticallyoriented” salient region where both the ob…”
InfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · cited 2×
“ence PSNR / SSIM / VIF High-quality Image 7.69 / -0.13 / 0.04 Low-quality Image 8.50 / 0.12 / 0.03 Fig. 2. Quality measurement by Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM) [31] and Visual Information Fidelity (VIF) [32] (higher is better, typically measured against a referencing groundtruth…”
BackgroundMethodInfluentialImage Super-Resolution Using Deep Convolutional Networks
Dong, C., Loy, C. C., He, K., & Tang, X. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2439281 · Cited by 10,105 · cited 1×
“e Quality Metrics Image quality metrics are defined in an attempt to quantitatively measure the objective quality of an image. This is typically used in image restoration applications (superresolution [34], de-blur [35] and de-artifacts [36]) where we have a default high-quality reference image for comparison. However,…”
BackgroundSelf-citationHow transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · cited 1×
“, freezing some earlier layers to prevent overfitting [65].”
BackgroundDimensionality Reduction by Learning an Invariant Mapping
Hadsell, R., Chopra, S., & LeCun, Y. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.100 · Cited by 5,336 · cited 1×
“Pretraining using triplets: The triplet loss is inspired by Dimensionality Reduction by Learning an Invariant Mapping (DrLIM) [68] and Large Margin Nearest Neighbor (LMNN) [69].”
MethodVisual categorization with bags of keypoints
Csurka, G. (2004) · European Conference on Computer Vision · Cited by 4,953
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636 · cited 2×
“It is worth pointing out that other more recent and deeper models such as ResNet [63] or Inception-ResNet [64] could serve as a pre-trained model.”
Research works printed but not linked: 15
- [33] Y. LeCun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard, and L. Jackel, 'Handwritten digit recognition with a backpropagation network,' in Advacnes in Neural Information Processing Systems (NIPS) , 1989. -
- [32] H. R. Sheikh and A. C. Bovik, 'A visual information fidelity approach to video quality assessment,' in The First International Workshop on Video Processing and Quality Metrics for Consumer Electronics . Citeseer, 2005, pp. 23-25. -
- [59] Y. Kao, R. He, and K. Huang, 'Visual aesthetic quality assessment with multi-task deep learning,' arXiv preprint arXiv:1604.04970 , 2016. - · arXiv
- wang, 2016, Brain-inspired deep networks for image aesthetics assessment
- [3] J. S. Barbara London, John Upton, Photography . Pearson, 2005. -
- [5] G. T. Fechner, Vorschule der aesthetik . Breitkopf & H¨ artel, 1876, vol. 1. -
- [48] L. Marchesotti, F. Perronnin, and F. Meylan, 'Learning beautiful (and ugly) attributes.' in British Machine Vision Conference (BMVC) , vol. 7, 2013, pp. 1-11. -
- [77] C.-Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu, 'Deeplysupervised nets.' in International Conference on Artificial Intelligence and Statistics , 2015. -
- [81] A. Krizhevsky, I. Sutskever, and G. E. Hinton, 'Imagenet classification with deep convolutional neural networks,' in Advances in Neural Information Processing Systems (NIPS) , 2012, pp. 1097-1105. -
- [2] I. J, Design and Form: The Basic Course at the Bauhaus and Later . Wiley, Chichester, 1975. -
- [1] M. Freeman, 'The complete guide to light and lighting,' 2007. -
- [104] M. Nishiyama, T. Okabe, Y. Sato, and I. Sato, 'Sensation-based photo cropping,' in Proceedings of the ACM International Conference on Multimedia , 2009, pp. 669-672. -
- [16] S. Zeki and J. Nash, Inner vision: An exploration of art and the brain . Oxford university press Oxford, 1999, vol. 415. -
- [84] L. v. d. Maaten and G. Hinton, 'Visualizing data using t-SNE,' Journal of Machine Learning Research , vol. 9, no. Nov, pp. 25792605, 2008. -
- [18] T. Ang, Digital photographer's handbook . Dorling Kindersley Publishing, Incorporated, 2002. -
Cited by
Items 101–200 of 306
MSTGAR: Multioperator-Based Stereoscopic Thumbnail Generation With Arbitrary Resolution
Chai, X., Shao, F., Jiang, Q., & Ho, Y. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2939707 · Cited by 12
“[28] introduced the aesthetics evaluation-based deep model into the field of automatic image cropping.”
BackgroundMethodInfluentialJoint regression and learning from pairwise rankings for personalized image aesthetic assessment
Zhou, J., Zhang, Q., Fan, J.-H., Sun, W., & Zheng, W. (2021) · Computational Visual Media · doi:10.1007/s41095-021-0207-y · Cited by 12
Narahara, T., & Yamasaki, T. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3214072 · Cited by 11
“For instance, analysis of image aesthetics relates more to color usage, composition, etc., and not to low-level noise in the content [43], [44], [45], [46], [47], [48].”
BackgroundInterpretable Aesthetic Analysis Model for Intelligent Photography Guidance Systems
Wu, X. (2022) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3490099.3511155 · Cited by 11
“Challenges in judging the quality of an image include [7]: (1) computationally analysing and modelling the entangled photographic rules, (2) knowing the aesthetic differences in different images types, such as portrait or scenery, and in different shooting techniques, such as depth of field and…”
MethodGated CNN for visual quality assessment based on color perception
Lu, P., Peng, X., Yu, J., & Peng, X. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.12.007 · Cited by 11
Human-Centric Image Cropping with Partition-Aware and Content-Preserving Features
Zhang, B., Niu, L., Zhao, X., & Zhang, L. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20071-7_11 · Cited by 24
Image Aesthetic Distribution Prediction with Fully Convolutional Network
Fang, H., Cui, C., Deng, X., Nie, X., Jian, M., & Yin, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-73603-7_22 · Cited by 11
Kamath, V., Renuka, A., Kini, V. G., & Prabhu, S. (2024) · IEEE Access · doi:10.1109/access.2024.3381798 · Cited by 16
“So, even if the images are the same size (224 × 224 pixels) after resizing, they may still be different due to the factors stated above [13], [14], [15].”
BackgroundBlind Multimodal Quality Assessment of Low-Light Images
Wang, M., Xu, Z., Xu, M., & Lin, W. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02239-9 · Cited by 16
“In addition, we also review the exploration of multimodality-based quality assessment in user-perceived quality of experience (QoE).”
A Deep Learning-Based Multidimensional Aesthetic Quality Assessment Method for Mobile Game Images
Wang, T., Sun, W., Wu, W., Chen, Y., Min, X., Lu, W. H., Zhang, Z., & Zhai, G. (2022) · IEEE Transactions on Games · doi:10.1109/tg.2022.3212201 · Cited by 12
“As stated in Section I, there are three categories of NR-IQA methods: Natural scene statistics (NSS)-based methods [14], [15], [16], [17], [18], HVS model-based methods [19], [20], and learning-based methods [21], [22], [23], [24], [25], [26], [27], [28].”
BackgroundMethodMLANs: Image Aesthetic Assessment via Multi-Layer Aggregation Networks
Meng, X., Gao, F., Shi, S., Zhu, S., & Zhu, J. (2018) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2018.8608132 · Cited by 10
“Afterwards, researchers use machine learning techniques, such as support vector machines and neural networks, to formulate the relationship between features and aesthetic labels [2].”
BackgroundMethodInfluentialAn Application for Aesthetic Quality Assessment in Photography with Interpretability Features
Rubio, F., Flores, M. J., & Puerta, J. M. (2021) · Entropy · doi:10.3390/e23111389 · Cited by 10
“From all the state-of-the-art proposals, 4 models where selected: • DAN1 [19] is a binary classification model obtained from the fine-tuning process.”
BackgroundResultWang, Y., Ye, J., Ning, X., & Gao, L. (2024) · Sustainability · doi:10.3390/su16135674 · Cited by 15
“In addition, following the emergence of deep-learning techniques, they systematically evaluate recent deep-learning settings that are useful for developing a robust deep model for aesthetic scoring [50].”
BackgroundAttribute-Driven Multimodal Hierarchical Prompts for Image Aesthetic Quality Assessment
Zhu, H., Shi, J., Shao, Z., Yao, R., Zhou, Y. Z., Zhao, J., & Li, L. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681175 · Cited by 9
“(b) An image with bad aesthetic quality. abundance of visual content highlights the importance of understanding and evaluating image aesthetic quality in an automated manner.”
Attribute-guided aesthetic assessment for artistic images based on multimodal hybrid network
Xu, X., Huang, S., Li, W., & Wang, F. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129954 · Cited by 11
Hierarchical Features Fusion for Image Aesthetics Assessment
Zhang, W., Zhai, G., Yang, X., & Yan, J. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803599 · Cited by 9
“The aesthetic quality of an image may be affected by various factors including color, lighting, contrast and image composition [1].”
BackgroundStudy of naturalness in tone-mapped images
Le, Q.-T., Ladret, P., Nguyen, H.-T., & Caplier, A. (2020) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2020.102971 · Cited by 9
“This study is not about image aesthetic assessment [15] or image quality assessment [16].”
BackgroundImage Aesthetic Assessment Based on Image Classification and Region Segmentation
Le, Q.-T., Ladret, P., Nguyen, H.-T., & Caplier, A. (2020) · Journal of Imaging · doi:10.3390/jimaging7010003 · Cited by 9
“Generally, there are two main phases in an IAA process [1].”
BackgroundStudy of Natural Scene Categories in Measurement of Perceived Image Quality
Yang, X., Li, F., Li, L., Gu, K., & Liu, H. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3154808 · Cited by 11
“AQA focuses on categorising images into aesthetically higher or lower quality (i.e., a “aesthetics classification” task [50]) and IQA focuses on quantifying the image quality preference induced by visual signal distortions (i.e., a “preference regression” task).”
BackgroundColor Aesthetics and Context-Dependency
Shamoi, P., Inoue, A., & Kawanaka, H. (2022) · Joint International Conference on Soft Computing and Intelligent Systems and International Symposium on Advanced Intelligent Systems (SCIS&ISIS) · doi:10.1109/scisisis55246.2022.10001872 · Cited by 9
“, SVM, NN training) are widely used in image aesthetics [28], [27].”
BackgroundMethodAssessing Eye Aesthetics for Automatic Multi-Reference Eye In-Painting
Yan, B., Lin, Q., Tan, W., & Zhou, S. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01352 · Cited by 12
“The image aesthetic assessment [8, 12, 6] aims to use the computer to simulate human perception and cognition of aesthetic, which has important application prospects in clothing design, beauty makeup, face editing, and pictures beautifying [20, 3], etc.”
BackgroundSocial-sensed Image Aesthetics Assessment
Cui, C., Lin, P., Nie, X., Jian, M., & Yin, Y. (2020) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3414843 · Cited by 9
“Such results also suggest the superiority of the end-to-end learning process for image aesthetics assessment and are accordant with the findings in previous studies [8].”
BackgroundResultInfluentialA New Approach to Landscape Visual Quality Assessment from a Fine-Tuning Perspective
Fan, R., Chen, Y., & Yocom, K. P. (2024) · Land · doi:10.3390/land13050673 · Cited by 10
“…by analyzing the sentiment polarity (positive or negative labels) of the comments and identifying the positive and negative sentiment parts of the venues by using the sentiment analysis technique based on the EASYDL deep learning platform [87] for correlation analysis with other variables [88].”
Recognition of Aquatic Invasive Species Larvae Using Autoencoder-Based Feature Averaging
Chowdhury, S., & Hamerly, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20713-6_11 · Cited by 11
“More recently, deep learning based methods are able to model complex image features much more accurately [14].”
BackgroundPu, Y., Liu, D., Chen, S., & Zhong, Y. (2023) · Applied Sciences · doi:10.3390/app13179763 · Cited by 9
GAIT: Generating Aesthetic Indoor Tours with Deep Reinforcement Learning
Xie, D., Hu, P. F., Sun, X., Pirk, S., Zhang, J., Měch, R., & Kaufman, A. E. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00681 · Cited by 13
“Deng et al. [10] provide a survey of different techniques for aesthetic scoring and report that deep aesthetic assessment methods provide superior performance compared to hand-crafted methods.”
BackgroundFilling the gaps: Reducing the complexity of networks for multi-attribute image aesthetic prediction
Kairanbay, M., See, J., Wong, L.-K., & Hii, Y.-L. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296843 · Cited by 8
“Recent state-ofthe-art solutions for photo aesthetic evaluation are shifting towards using deep learning techniques [1, 2, 3, 4], which has been shown to produce significant improvement over conventional hand-crafted features [5, 6, 7, 8] and generic descriptors [9].”
BackgroundGANmera: Reproducing Aesthetically Pleasing Photographs Using Deep Adversarial Networks
Bow, N. C. N., Wong, L.-K., & See, J. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00271 · Cited by 8
“Comparison of our RGB models with CycleGAN [29], EnhanceGAN [5] and DPE [3].”
BackgroundMethodResultInfluentialImage aesthetic assessment using a saliency symbiosis network
Li, X., Li, X., Zhang, G., & Zhang, X. (2019) · Journal of Electronic Imaging · doi:10.1117/1.jei.28.2.023008 · Cited by 8
“13 16 However, roughly, binary classification does not accurately assess the aesthetic quality of images.”
BackgroundMeta-Learning Multi-task CommunicationPreprint
Liu, P., & Huang, X. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.09988 · Cited by 8
“Image Aesthetic Assessment The image aesthetic assessment can be formulated as a classification problem of predicting an image high-or low-aesthetic categories within the supervised learning framework (Murray et al., 2012; Deng et al., 2017).”
BackgroundLearning Expectation of Label Distribution for Facial Age and Attractiveness EstimationPreprint
Gao, B.-B., Liu, X., Zhou, H.-Y., Wu, J., & Geng, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.01771 · Cited by 20
“It is noteworthy that our approach is easily scalable to others label uncertainty tasks, such as skeletal maturity assessment on pediatric hand radiographs [68], head pose estimation [69], popularity of selfie [70], image aesthetic assessment [71] etc .”
BackgroundLi, H., & Wen, K.-H. (2022) · Sustainability · doi:10.3390/su14074022 · Cited by 8
“Consequently, the outcome meets the requirement of personalized need-based design for different people as well as different regions to achieve the purpose of popularizing science knowledge in the community [50,51].”
BackgroundUnderstanding aesthetics in photography using deep convolutional neural networks
Suchecki, M., & Trzcinski, T. P. (2017) · Signal Processing: Algorithms, Architectures, Arrangements, and Applications · doi:10.23919/spa.2017.8166855 · Cited by 8
“Our method is strongly inspired by previous research on similar problems, which concluded that deep convolutional neural networks perform well in such cases [4], [5], [6], [7].”
MethodPhoto Composition with Real-Time Rating
Li, Y., Yang, C., & Chang, Y.-Z. (2020) · Sensors · doi:10.3390/s20030582 · Cited by 7
“[7] surveyed image aesthetic assessment methods with the aim of being a binary classifier, i.”
BackgroundDeep learning for assessing the aesthetics of professional photographs
Chambe, M., Cozot, R., & Meur, O. L. (2022) · Computer Animation and Virtual Worlds · doi:10.1002/cav.2105 · Cited by 7
Novel groundtruth transformations for the aesthetic assessment problem
Gonzalez-Naharro, L., Flores, M. J., Martínez-Gómez, J., & Puerta, J. M. (2023) · Information Processing & Management · doi:10.1016/j.ipm.2023.103368 · Cited by 7
Towards Demographic-Based Photographic Aesthetics Prediction for Portraitures
Kairanbay, M., See, J., & Wong, L.-K. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-73603-7_43 · Cited by 7
Image Aesthetics Assessment Using Multi Channel Convolutional Neural Networks
Doshi, N., Shikkenawis, G., & Mitra, S. K. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-4018-9_2 · Cited by 7
Semantics-Aware Image Aesthetics Assessment using Tag Matching and Contrastive Ranking
Yang, Z., Li, L., Chen, P., Wu, J., & Dong, W. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680972 · Cited by 7
“IAA approaches have extensive applications [5], such as image recommendation [39], image enhancement [8], and image retrieval [44], etc.”
Deep Learning-Based Layout Analysis Method for Complex Layout Image Elements
Zhong, Y., Pu, Y., Li, X., Zhou, W., He, H., Chen, Y., Zhong, L., & Liu, D. (2025) · Applied Sciences · doi:10.3390/app15147797 · Cited by 6
Data Covariance Learning in Aesthetic Attributes Assessment
Chen, Z. (2020) · Journal of Applied Mathematics and Physics · doi:10.4236/jamp.2020.812212 · Cited by 6
“To make it even worse, these photographic styles might be intertwined with each other [2] [8] [13] and contribute differently to the overall aesthetic score.”
Exploring Metrics to Establish an Optimal Model for Image Aesthetic Assessment and Analysis
Dai, Y. (2022) · Journal of Imaging · doi:10.3390/jimaging8040085 · Cited by 7
“The Expression (8), This image is from the CUHK-PQ dataset with high-quality labeling. predictions of the three FD-determined models are score 5, score 7, The predictions of the three FD-determined models are score 5, score 7, and score 5, respectively; the predictions of the three D-determined models are score 7, sco…”
InfluentialImage Aesthetic Assessment: A Comparative Study of Hand-Crafted & Deep Learning Models
Anwar, A., Kanwal, S., Tahir, M., Saqib, M., Uzair, M., Rahmani, M. K. I., & Ullah, H. (2022) · IEEE Access · doi:10.1109/access.2022.3209196 · Cited by 6
Classical learning or deep learning: a study on food photo aesthetic assessment
Li, Z., Zhang, Z., & Gao, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15791-2 · Cited by 6
“Image aesthetic assessment has been applied to various aspects of life [8, 13, 14, 20, 23, 24, 26, 32, 39], however, the research on food photo aesthetics assessment is relatively few.”
Federated Learning for Personalized Image Aesthetics Assessment
Xiong, Z., Yu, H., & Shen, Z. (2023) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme55011.2023.00065 · Cited by 6
“Based on the difference in assessment objectives, image aesthetics assessment can be divided into generic image aesthetics assessment (GIAA) and personalized image aesthetics assessment (PIAA) [1].”
BackgroundLearning With Noisy Low-Cost MOS for Image Quality Assessment via Dual-Bias Calibration
Wang, L., Wu, Q., Yuan, D., Ngan, K. N., Li, H., Meng, F., & Xu, L. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3543014 · Cited by 10
Thumbnail Image Selection for VOD Services
Tsao, C.-N., Lou, J.-K., & Chen, H. H. (2019) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr.2019.00018 · Cited by 6
“A comprehensive review of these approaches can be found in the literature [7].”
BackgroundCreating Cover Photos (Thumbnail) for Movies and TV Series with Convolutional Neural Network
Cakar, M., Yıldız, K., & Demir, Ö. (2020) · Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu50717.2020.9259872 · Cited by 6
“These studies aimed to measure the aesthetics in the paintings with parameters such as blur, lightness, colors, scene, composition and object existence [9-11].”
BackgroundDebnath, S., & Changder, S. (2020) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661820040082 · Cited by 8
“Y. Deng [27] did a survey on image aesthetic assessment based on all possible visual feature types and the evaluation criteria (dataset characteristics and evaluation metrics).”
BackgroundRetractedAutomated assessment of visual aesthetics of Android user interfaces with deep learning
Lima, A. L. D. S., Martins, O. P. H. R., von Wangenheim, C. G., von Wangenheim, A., Borgatto, A. F., & Hauck, J. C. R. (2022) · Brazilian Symposium on Human Factors in Computing Systems (IHC) · doi:10.1145/3554364.3559113 · Cited by 8
“002 [11] Yubin Deng, Chen Change Loy, and Xiaoou Tang.”
BackgroundAn interpretable approach for automatic aesthetic assessment of remote sensing images
Tong, J., Guo Zhang, A., Kong, P., Rao, Y., Wei, Z., Cui, H., & Guan, Q. (2022) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2022.1077439 · Cited by 6
“They typically cast it as a classification or regression problem (Deng et al., 2017).”
BackgroundThe Photographer’s Visual Grammar: Visual Rightness and Aesthetics of Artistic Photographs
Vissers, N., & Wagemans, J. P. (2023) · Art & Perception · doi:10.1163/22134913-bja10047 · Cited by 6
Personalised Aesthetics with Residual Adapters
Rodríguez-Pardo, C., & Bilen, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-31332-6_44 · Cited by 6
“Some examples of the use of CNNs for image aesthetics prediction and related topics can be found in [2,20,33,6,11,4,9,35,10,17].”
BackgroundDeep Neural Framework With Visual Attention and Global Context for Predicting Image Aesthetics
Xu, Y., Zhang, N., Wei, P., Sang, G., Li, L., & Yuan, F. (2020) · IEEE Access · doi:10.1109/access.2020.3015060 · Cited by 6
“Methods of the second kind rely on impressive progress on deep neural networks for IAQA [9].”
Modeling the Aesthetics of Audio-Scene Reproduction
Mourjopoulos, J. (2020) · Modern acoustics and signal processing · doi:10.1007/978-3-030-00386-9_16 · Cited by 6
A Deep Learning Model for the Assessment of the Visual Aesthetics of Mobile User Interfaces
Lima, A. L. D. S., von Wangenheim, C. G., Martins, O. P. H. R., von Wangenheim, A., Hauck, J. C. R., & Borgatto, A. F. (2024) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2024.3255 · Cited by 6
“…learning models have been applied to quantify the visual aesthetics of the design of GUIs of web-pages [Dou et al ., 2019; Khani et al ., 2016; Xing et al ., 2021] following the success of the evaluation of the aesthetics of photographs [Deng et al ., 2017; Lu et al ., 2014; Malu et al ., 2017].”
MethodInfluentialAn Experience-Based Direct Generation Approach to Automatic Image Cropping
Christensen, C. L., & Vartakavi, A. (2021) · IEEE Access · doi:10.1109/access.2021.3100816 · Cited by 5
“often create thumbnails in fixed aspect ratios but usually do not consider image aesthetics [3], [9].”
BackgroundBuilding CNN-Based Models for Image Aesthetic Score Prediction Using an Ensemble
Dai, Y. (2022) · Journal of Imaging · doi:10.3390/jimaging9020030 · Cited by 7
“Deng, Loy, and Tang (2017) [1] present an experimental survey about this field’s research.”
A Visual Enhancement Network with Feature Fusion for Image Aesthetic Assessment
Zhang, X., Jiang, X., Song, Q., & Zhang, P. (2023) · Electronics · doi:10.3390/electronics12112526 · Cited by 5
Unleashing Attributes-content Adaptation with Multi-color Spaces for Food Photo Aesthetic Assessment
Hidayati, S. C., Firdaus, M. V. R. N., Dianto, R. W. N., & Sarwosri, S. (2024) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc63619.2025.10848973 · Cited by 5
“Traditional methods for assessing photo aesthetics have relied heavily on handcrafted features and basic image processing techniques, which often fail to capture the nuanced visual details and context-dependent attributes critical for high-quality aesthetic evaluations [1].”
Aesthetics-Guided Graph Clustering With Absent Modalities Imputation
Zhang, L., Yao, Y., Zhen-guang, L., & Shao, L. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2897940 · Cited by 5
Deep Learning for motion based video aesthetics
Phatak, M. V., Patwardhan, M. S., & Arya, M. S. (2019) · IEEE Bombay Section Signature Conference (IBSSC) · doi:10.1109/ibssc47189.2019.8973218 · Cited by 5
“The results may be in form of binary classification or regression in quantified form of numeric ratings [3].”
BackgroundTHE EXPLORATION OF LOCAL WISDOM VALUES OF PERFORMING ARTS: AN ART OF KUDA LUMPING SARIMPI
Rahmawati, E., & Putranta, H. (2020) · Humanities & Social Sciences Reviews · doi:10.18510/hssr.2020.8528 · Cited by 9
“The high and low aesthetic quality of performance art is determined by communicative abilities (Anttila et al., 2019; Deng et al., 2017).”
BackgroundARET-IQA: An Aspect-Ratio-Embedded Transformer for Image Quality Assessment
Zhu, H., Zhou, Y. Z., Shao, Z., Du, W.-L., Zhao, J., & Yao, R. (2022) · Electronics · doi:10.3390/electronics11142132 · Cited by 6
Yu, L., & Chung, W. (2023) · Journal of Experimental Nanoscience · doi:10.1080/17458080.2023.2174693 · Cited by 5
“However, arts and crafts works are closely related to people ’ s lives, and they will often contact with the human body [19].”
BackgroundRetractedMorinaga, T., Patanukhom, K., & Somchit, Y. (2024) · Big Data and Cognitive Computing · doi:10.3390/bdcc8060054 · Cited by 4
SoftClusterMix: learning soft boundaries for empirical risk minimization
Florea, C., Vertan, C., & Florea, L. (2023) · Neural computing & applications (Print) · doi:10.1007/s00521-023-08338-x · Cited by 5
“Results are presented in Table 5.”
An Order-Complexity Aesthetic Assessment Model for Aesthetic-aware Music Recommendation
Jin, X., Wu, Z., Wang, J., Xu, D., & Zheng, Y. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612140 · Cited by 4
“It is necessary to consider the aesthetics of artworks because beauty often make people feel pleasant [13].”
BackgroundKeep Knowledge in Perception: Zero-Shot Image Aesthetic Assessment
Wang, G., Tan, Y., Lin, H., & Zhang, C. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447301 · Cited by 4
“The feasibility of this task has been progressively augmented by advancements in deep learning methods based on large-scale databases [2, 3].”
MethodComputational assessment of the aesthetic quality of map colors
Wu, M., Sun, Y., & Xia, X. (2024) · Transactions in GIS · doi:10.1111/tgis.13206 · Cited by 4
“While many efforts have been made to assess aesthetic quality of visual works, such as computational aes - thetics for painting (Li & Chen, 2009), photography (Deng et al., 2017 ), and general color palettes (O'Donovan et al., 2014 ), rate attention has been given to maps.”
Beyond the single picture: Aesthetic experiences with photography series in an exhibition context.
Vissers, N., & Wagemans, J. P. (2021) · Psychology of Aesthetics Creativity and the Arts · doi:10.1037/aca0000417 · Cited by 4
Classification of aesthetic natural scene images using statistical and semantic features
Biswas, K. K., Shivakumara, P., Pal, U., Lü, T., Blumenstein, M., & Lladós, J. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13924-7 · Cited by 4
Automated Adaptive Cinematography for User Interaction in Open World
Yu, Z., Wu, X., Wang, H., Katsaggelos, A. K., & Ren, J. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3347092 · Cited by 4
“Furthermore, to elevate the aesthetic resonance of our frames, we incorporated insights from professional film director shot selections into our model’s loss function, optimizing our automated camera generation algorithm [15].”
MethodDrawing a baseline in aesthetic quality assessment
Rubio, F., Gallego, J. F., & Puerta, J. M. (2018) · International Conference on Machine Vision · doi:10.1117/12.2311288 · Cited by 4
“[20] proposed “balanced accuracy” as a possible solution.”
BackgroundPredicting the Attractiveness of Real-Estate Images by Pairwise Comparison using Deep Learning
Wang, X., Takada, Y., Kado, Y., & Yamasaki, T. (2019) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew.2019.0-106 · Cited by 4
Dai, Y. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09426-z · Cited by 4
Incremental Learning of Multi-Tasking Networks for Aesthetic Radar Map Prediction
Jin, X., Zhou, X., Li, X., Zhang, X., Sun, H., Li, X., & Liu, R. (2019) · IEEE Access · doi:10.1109/access.2019.2958119 · Cited by 4
“At the same time, the deep features got by the convolution neural network have more information than manual features, and it have achieved higher accuracy image aesthetic assessment such as classification [2].”
Aesthetic Evaluation of Food Plate Images using Deep Learning
Mikhailava, V., Pyshkin, E., & Klyuev, V. (2020) · International Conference on Advanced Communication Technology · doi:10.23919/icact48636.2020.9061216 · Cited by 4
“In [15], the authors pointed out an important, challenging issue of image aesthetics assessment, which is about learning category-specific image aesthetics (such as food images, in our case), which requires more specific auxiliary information about the data.”
BackgroundInfluentialCNN-based repetitive self-revised learning for photos' aesthetics imbalanced classification
Dai, Y. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412874 · Cited by 4
Guzzi, F., Kourousias, G., Billè, F., Pugliese, R., Reis, C., Gianoncelli, A., & Carrato, S. (2018) · Journal of Instrumentation · doi:10.1088/1748-0221/13/06/c06002 · Cited by 4
“…be used even to initiate a CNN based metrics: before a direct training of the embedding in the feature space with siamese network and triplets [30], one of the common methods used for object/face recognition was to use a classification approach, to train on the classes, cut out the…”
MethodDeep Conditional Color Harmony Model for Image Aesthetic Assessment
Lu, P., Yu, J., & Peng, X. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8546328 · Cited by 4
“More comprehensive reviews for deep learning based aesthetic assessment can be found in [29].”
BackgroundDigital Image Aesthetic Composition Optimization Based on Perspective Tilt Correction
Shao, H., Wang, Y., Ding, D., & Wang, C. (2020) · Chinese Automation Congress · doi:10.1109/cac51589.2020.9327124 · Cited by 4
“The first direction is to use deep learning and convolutional neural networks to assess the aesthetic quality of images based on massive amounts of labeled data [2].”
BackgroundA Survey of Hand Crafted and Deep Learning Methods for Image Aesthetic Assessment.Preprint
Kanwal, S., Uzair, M., & Ullah, H. (2021) · arXiv (Cornell University) · Cited by 4
You, J., Lin, Y. P., & Hu, B. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104641 · Cited by 5
Less-Known Tourist Attraction Discovery Based on Geo-Tagged Photographs
Lin, J.-Y., Wen, S.-M., Hirota, M., Araki, T., & Ishikawa, H. (2020) · Machine Learning and Knowledge Extraction · doi:10.3390/make2040023 · Cited by 3
Modeling Multiple Aesthetic Views for Series Photo Selection
Huang, J., Gong, Y., Zhang, L., Zhang, J., Nie, L., & Yin, Y. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3290751 · Cited by 6
“Previous studies on aesthetic quality assessment [6] have used hand-designed photographic features, general descriptors, and deep features to solve aesthetic classification or regression problems.”
BackgroundDual-Stream Interaction Network for Assessing Image Technique and Aesthetic Quality
Wei, T., Chen, H., & Jiang, Q. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3510930 · Cited by 5
“Similarly, the assessment of image aesthetic quality involves a comprehensive process that combines subjective and objective evaluations of aesthetic attributes, such as individual artistic perception, visual allure, image texture, and various aesthetic factors [13] [14].”
A User-Centered Approach for Recognizing Convenience Images in Personal Photo Collections
Maszuhn, M., Abdenebaoui, L., & Boll, S. (2021) · International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi50038.2021.9461908 · Cited by 3
“Another seminal approach in the literature consists of selecting images with high aesthetics and quality assessment [6]–[8].”
BackgroundThumbnail Selection with Convolutional Neural Network Based on Emotion Detection
Cakar, M., Yıldız, K., & Demir, Ö. (2021) · International Journal of Advances in Engineering and Pure Sciences · doi:10.7240/jeps.900561 · Cited by 5
The Role of Images in Enriching the Aesthetic Taste
Al-Saadi, S. M., Karbol, H. A. S., & Al-Majidi, B. H. H. (2022) · International Journal of Design & Nature and Ecodynamics · doi:10.18280/ijdne.170109 · Cited by 3
“Because of the difficulty of depicting the idea, it became necessary to embody it in a symbolic body that has meanings related to people, where the symbol contains a lesson by loading the form the content of experience, no matter how simple or complex its entity is [21].”
BackgroundInfluentialImage Synthesis with Aesthetics-Aware Generative Adversarial Network
Zhang, R., Liu, X., Guo, Y., & Hao, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00767-6_16 · Cited by 3
Learning Multi-Scale Attentive Features for Series Photo Selection
Huang, J., Cui, C., Zhang, C., Shen, Z., Yu, J., & Yin, Y. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053731 · Cited by 4
“ResNet50 [13] and SENet [18] were also introduced as baselines, since they are commonly used in previous studies of image aesthetics assessment [2, 19].”
BackgroundMethodAn artistic analysis model based on sequence cartoon images for scratch
Chai, X., Sun, Y., Luo, H., & Guizani, M. (2022) · International Journal of Intelligent Systems · doi:10.1002/int.23017 · Cited by 3
Regression or Classification? New Methods to Evaluate No-Reference Picture and Video Quality ModelsPreprint
Tu, Z., Chen, C.-J., Chen, L., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.00155 · Cited by 3
Natural Language Processing (NLP) Trends
(2022) · doi:10.5121/csit.2022.1201 · Cited by 3
Grand Challenges in Image Processing
(2022) · International Conference for Natural and Applied Sciences (ICNAS) · doi:10.1109/icnas55512.2022.9944686 · Cited by 3
Computer-Aided Colorization State-of-the-Science: A Survey
Cao, Y., Duan, X., Meng, X., Mok, P. Y., Li, P., & Lee, T. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3543527 · Cited by 7
AGIAA-2K: A Fine-grained Dataset for Aesthetic and Alignment Evaluation of AI-Generated Images
Hu, B., Li, N., He, L., Lu, W. B., Li, L., & Gao, X. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890774 · Cited by 4
“…creativity, [7] 250,000 NSIs Aesthetic AADB [8] 10,000 NSIs Aesthetic, Attributes PARA [9] 31,220 NSIs Aesthetic, Quality, Attributes AGIQA-1K [4] 1,080 AGIs Quality AGIQA-3K [5] 2,982 AGIs Quality, Alignment AIGCIQA2023 [6] 2,400 AGIs Quality, Authenticity, Alignment AGIAA-2K 2,064 AGIs…”
ArtFRD: A Fisher-Rao Mixture Metric for Generative Model Aesthetic Evaluation
Huang, C., Jia, Z., Fei, H., Zhu, Y., Yuan, Z., Zhang, J., & Zhou, J. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755259 · Cited by 3
“A closely related area to our work is Image Aesthetics Assessment (IAA) [11, 46], which focuses on predicting the aesthetic quality of individual images based on their visual content.”
Withöft, A., Abdenebaoui, L., & Boll, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-98355-0_8 · Cited by 3
Metadata
- Authors
- Deng, Y., Loy, C. C., & Tang, X.
- Affiliations
- Chinese University of Hong Kong (HK)
- Venue
- IEEE Signal Processing Magazine
- Published
- 2017-07
- Volume
- 34
- Issue
- 4
- Pages
- 80-106
- ISSN
- 1053-5888 (ISSN-L)
- 1558-0792
- OpenAlex
- W2529088810
- Cited by
- 306
- References
- 95
- Citations by year
- 2026: 14 · 2025: 29 · 2024: 26 · 2023: 40 · 2022: 39 · 2021: 39 · 2020: 43 · 2019: 43 · 2018: 29 · 2017: 4
- FWCI
- 13.51
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Signal Processing Magazine (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- image aesthetic assessment, handcrafted features, deep features, deep learning, evaluation metrics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.