A Unified Probabilistic Formulation of Image Aesthetic Assessment

Zeng, Hui; Cao, Zisheng; Zhang, Lei; Bovik, Alan C.

doi:10.1109/tip.2019.2941778

Cited by 82 publications

(70 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our experiment is conducted on the official split of AVA dataset as previous works [6,15,20,23,44,48]. It consists of ∼ 250 images, and officially divided into a training set with ∼ 230 and a testing set with ∼ 20 images.…”

Section: Experiments and Analysis 41 Experimental Setupmentioning

confidence: 99%

“…We choose the results of Model 4 from ablation studies to compare with 5 recent relevant works. For the 4 methods by Talebi et al [32], Zhang et al [48], Li et al [15] and Zeng et al [44], we refer to the results from their original papers. For the work by Hosu et al [6], since the original work is trained subject to score regression, we have modified the model by replacing its output layer with a 10-way softmax layer and re-trained it with normalized EMD loss (Eq.…”

Section: Peer Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

Object-level Attention for Aesthetic Rating Distribution Prediction

Hou

Yang

Wang

2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

We study the problem of image aesthetic assessment (IAA) and aim to automatically predict the image aesthetic quality in the form of discrete distribution, which is particularly important in IAA due to its nature of having possibly higher diversification of agreement for aesthetics. Previous works show the effectiveness of utilizing objectagnostic attention mechanisms to selectively concentrate on more contributive regions for IAA, e.g., attention is learned to weight pixels of input images when inferring aesthetic values. However, as suggested by some neuropsychology studies, the basic units of human attention are visual objects, i.e., the trace of human attention follows a series of objects. This inspires us to predict contributions of different regions at object level for better aesthetics evaluation. With our framework, region-of-interests (RoIs) are proposed by an object detector, and each RoI is associated with a regional feature vector. Then the contribution of each regional feature to the aesthetics prediction is adaptively determined. To the best of our knowledge, this is the first work modeling object-level attention for IAA and experimental results confirm the superiority of our framework over previous relevant methods. CCS CONCEPTS • Applied computing → Media arts; • Computing methodologies → Computer vision; Neural networks.

show abstract

Section: Experiments and Analysis 41 Experimental Setupmentioning

confidence: 99%

Section: Peer Comparisonmentioning

confidence: 99%

Object-level Attention for Aesthetic Rating Distribution Prediction

Hou

Yang

Wang

2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Talebi and Milanfar [22] predicted the distribution of aesthetic scores using a convolutional neural network. Zeng et al [23] presented a unified probabilistic formulation for image aesthetic assessment, while Zhang et al [24] achieved unified aesthetic prediction through a gated peripheral-foveal convolutional neural network. More recently, Pan et al [25] developed an image aesthetic assessment model assisted by attributes through adversarial learning.…”

Section: Generic Image Aesthetic Assessmentmentioning

confidence: 99%

Joint regression and learning from pairwise rankings for personalized image aesthetic assessment

et al. 2021

View full text Add to dashboard Cite

Recent image aesthetic assessment methods have achieved remarkable progress due to the emergence of deep convolutional neural networks (CNNs). However, these methods focus primarily on predicting generally perceived preference of an image, making them usually have limited practicability, since each user may have completely different preferences for the same image. To address this problem, this paper presents a novel approach for predicting personalized image aesthetics that fit an individual user’s personal taste. We achieve this in a coarse to fine manner, by joint regression and learning from pairwise rankings. Specifically, we first collect a small subset of personal images from a user and invite him/her to rank the preference of some randomly sampled image pairs. We then search for the K-nearest neighbors of the personal images within a large-scale dataset labeled with average human aesthetic scores, and use these images as well as the associated scores to train a generic aesthetic assessment model by CNN-based regression. Next, we fine-tune the generic model to accommodate the personal preference by training over the rankings with a pairwise hinge loss. Experiments demonstrate that our method can effectively learn personalized image aesthetic preferences, clearly outperforming state-of-the-art methods. Moreover, we show that the learned personalized image aesthetic benefits a wide variety of applications.

show abstract

“…C. Data uncertainty in image aesthetics assessment Modeling data uncertainty is beneficial to aesthetics assessment. [13] finds IAA problem benefit from data uncertainty modeling due to the ambiguity. They propose a unified probabilistic formulation to deal with IAA and introduce Gaussian uncertainty for score (MOS) distribution.…”

Section: B Data Uncertainty In Deep Learningmentioning

confidence: 99%

“…Since the IAA problem is ambiguous, the constructed dataset is annotated noisily [13] [14] [15] [16]. As AAA introduces more targets to predict (i.e.…”

Section: Introductionmentioning

confidence: 99%

Data Covariance Learning in Aesthetic Attributes Assessment

Chen¹

2020

JAMP

View full text Add to dashboard Cite

A Unified Probabilistic Formulation of Image Aesthetic Assessment

Cited by 82 publications

References 32 publications

Object-level Attention for Aesthetic Rating Distribution Prediction

Object-level Attention for Aesthetic Rating Distribution Prediction

Joint regression and learning from pairwise rankings for personalized image aesthetic assessment

Data Covariance Learning in Aesthetic Attributes Assessment

Contact Info

Product

Resources

About