Y
Yuming Fang
Researcher at Jiangxi University of Finance and Economics
Publications - 239
Citations - 7196
Yuming Fang is an academic researcher from Jiangxi University of Finance and Economics. The author has contributed to research in topics: Image quality & Computer science. The author has an hindex of 35, co-authored 204 publications receiving 4800 citations. Previous affiliations of Yuming Fang include National University of Singapore & Peking University.
Papers
More filters
Journal ArticleDOI
Saliency Detection in the Compressed Domain for Adaptive Image Retargeting
TL;DR: The proposed image retargeting algorithm effectively preserves the visually important regions for images, efficiently removes the less crucial regions, and therefore significantly outperforms the relevant state-of-the-art algorithms, as demonstrated with the in-depth analysis in the extensive experiments.
Journal ArticleDOI
No-Reference Quality Assessment of Contrast-Distorted Images Based on Natural Scene Statistics
TL;DR: A simple but effective method for no-reference quality assessment of contrast distorted images based on the principle of natural scene statistics (NSS), which demonstrates the promising performance of the proposed method based on three publicly available databases.
Proceedings ArticleDOI
From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement
TL;DR: A deep recursive band network (DRBN) is proposed to recover a linear band representation of an enhanced normal-light image with paired low/normal-light images, and then obtain an improved one by recomposing the given bands via another learnable linear transformation based on a perceptual quality-driven adversarial learning with unpaired data.
Journal ArticleDOI
A Saliency Detection Model Using Low-Level Features Based on Wavelet Transform
TL;DR: A novel saliency detection model is introduced by utilizing low-level features obtained from the wavelet transform domain to modulate local contrast at a location with its global saliency computed based on the likelihood of the features.
Journal ArticleDOI
A Video Saliency Detection Model in Compressed Domain
TL;DR: A novel video saliency detection model based on feature contrast in compressed domain is proposed that can predict the salient regions efficiently for video frames and shows superior performance on a public database.