Photo Aesthetics Ranking Network with Attributes and Content Adaptation

By Shu Kong, Xiaohui Shen, Zhe L. Lin, Radomír Mech, Charless C. Fowlkes. 2016

538 citations recorded by the source corpus.

Real-world applications could benefit from the ability to automatically generate a fine-grained ranking of photo aesthetics. However, previous methods for image aesthetics analysis have primarily focused on the coarse, binary categorization of images into high- or low-aesthetic categories. In this work, we propose to learn a deep convolutional neural network to rank photo aesthetics in which the relative ranking of photo aesthetics are directly modeled in the loss function. Our model incorporates joint learning of meaningful photographic attributes and image content information which can help regularize the complicated photo aesthetics rating problem.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning to Explain With Complemental Examples (2018, background): “AADB is a dataset created for the automatic image aesthetics rating.”
Recurrent Pixel Embedding for Instance Grouping (2017, background): “While other work has advocated online bootstrapping methods for hard-pixel mining or mini-batch selection [61, 47, 79, 89], our approach is much simpler.”
A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping (2019, methodology): “[54], [55] have shown that image aesthetics representation may be better learned in an end-to-end data-driven manner.”
Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels (2023, background): “While visual quality is also considered influential to visual aesthetics, the higher-level visual attributes, such as content, lighting, color, composition (Kong et al., 2016) are considered more important for IAA.”
Deep Image Harmonization (2017, methodology): “In addition, we apply an aesthetics prediction model [11] to filter out lowquality images.”
Learned perceptual image enhancement (2017, methodology): “In terms of rank correlation, NIMA(VGG16) and NIMA(Inception-v2) outperform [19].”
Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives (2022, background): “Semantics and Composition are two key factors deciding the aesthetics of a video [24, 58, 62].”
GANalyze: Toward Visual Definitions of Cognitive Image Properties (2019, methodology): “Indeed, the architecture of the AestheticsNet includes attribute-adaptive layers to predict these factors, now highlighted by our visualizations.”
Image Aesthetic Assessment: An experimental survey (2016, methodology): “96 - The authors in [22], [25], [26], [28], [29], [30], [33], [34], [35] have not released detailed results.”
NIMA: Neural Image Assessment (2017, methodology): “To the best of our knowledge, [14] is the only work ar X iv :1 70 9.”
Exploring CLIP for Assessing the Look and Feel of Images (2022, methodology): “Existing methods for abstract perception assessment mainly focus on aesthetic image assessment (Murray, Marchesotti, and Perronnin 2012; Kong et al. 2016; Sheng et al. 2018; Zeng et al. 2019; Shu et al. 2021; Jin et al. 2022) and image emotion analysis (Calvo and Lang 2004; Zhang et al. 2013; He,…”
Perceptual Quality Assessment of Smartphone Photography (2020, result): “, AlexNet [15] and VGG16 [31]), which is consistent with the observations in [14].”