The DOI matches its Crossref record; 100 of the 100 references it cites were found in a registry or an index.
Image Aesthetic Assessment: An experimental survey
Open accessAbstract
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.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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].”
MethodInception-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
Visual categorization with bags of keypoints
Csurka, G. (2004) · Cited by 4,379
Research works printed but not linked: 12
- sheikh, 0, A visual information fidelity approach to video quality assessment, Proc 1st Int Workshop Video Processing and Quality Metrics for Consumer Electronics, 23
- kao, 2016, Visual aesthetic quality assessment with multi-task deep learning
- zhang, 2016, Describing human aesthetic perception by deeply-learned attributes from Flickr
- london, 2005, Photography
- fechner, 1876, Vorschule der Aesthetik, 1
- marchesotti, 0, Learning beautiful (and ugly) attributes, Proc British Machine Vision Conf (BMVC), 7, 1
- itten, 1975, Design and Form The Basic Course at the Bauhaus and Later
- freeman, 2007, The Complete Guide to Light and Lighting in Digital Photography (A Lark Photography Book)
- nishiyama, 0, Sensation-based photo cropning, Proc ACM Int Conf Multimedia, 669
- zeki, 1999, Inner Vision An Exploration of Art and the Brain
- van der maaten, 2008, Visualizing data using t-SNE, J Machine Learning Res, 9, 2579
- ang, 2002, Digital Photographer's Handbook
Cited by
Perceptual image quality assessment: a survey
Zhai, G., & Min, X. (2020) · Science China Information Sciences · doi:10.1007/s11432-019-2757-1 · Cited by 655
A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping
Wang, W., Shen, J., & Ling, H. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2840724 · Cited by 348
“Many methods have been proposed for this topic, as surveyed in [43].”
MethodDistort-and-Recover: Color Enhancement Using Deep Reinforcement Learning
Park, J., Lee, J.-Y., Yoo, D., & Kweon, I. S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00621 · Cited by 211
“There has been a long line of works to assess the aesthetic scores of images as summarized in [2], but there is still no winning method that gives satisfying results.”
BackgroundPersonality-Assisted Multi-Task Learning for Generic and Personalized Image Aesthetics Assessment
Li, L., Zhu, H., Zhao, S., Ding, G., & Lin, W. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2968285 · Cited by 163
“The ACC is the most popular criteria for evaluating the performance of classification [1], and is computed by”
BackgroundA2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping
Li, D., Wu, H., Zhang, J., & Huang, K. (2018) · 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/cvpr.2018.00855 · Cited by 138
“Recently, thanks to the fast development of deep learning and newly proposed large scale datasets [22], there are many new works [16, 20, 8] which accomplish aesthetic quality assessment with convolutional neural networks.”
Background
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Image Aesthetic Assessment: An experimental survey. https://app.cochat.ai/papers/10.1109/msp.2017.2696576
- The paper
- Deng, Y., Loy, C. C., & Tang, X. (2017). Image Aesthetic Assessment: An experimental survey. IEEE Signal Processing Magazine. https://doi.org/10.1109/msp.2017.2696576
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.