A Gated Peripheral-Foveal Convolutional Neural Network for Unified Image Aesthetic Prediction

• Published in: IEEE transactions on multimedia Vol. 21; no. 11; pp. 2815 - 2826
• Main Authors: Zhang, Xiaodan, Gao, Xinbo, Lu, Wen, He, Lihuo
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.11.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Convolutional neural networks; Data integration; Datasets; Deep learning; Feature extraction; Fovea; image aesthetics; Image resolution; Logic gates; Multisensor fusion; Neural networks; Peripheral vision; Regression analysis; Task analysis; Visual acuity; Visual aesthetic quality assessment; Visual stimuli; Visualization

Learning fine-grained details is a key issue in image aesthetic assessment. Most of the previous methods extract the fine-grained details via random cropping strategy, which may undermine the integrity of semantic information. Extensive studies show that humans perceive fine-grained details with a m...