About

Jiaying Liu is an Associate Professor in the Department of Communication at UC Santa Barbara. She received her Ph.D. from the Annenberg School for Communication at the University of Pennsylvania. Her primary research interests lie at the intersection of health communication, social psychology, message effects, and computational social science methods. Her work focuses on understanding the factors and underlying processes that lead to risky health decision-making and exploring how communications can be optimally leveraged to promote desirable health behavior changes. Dr. Liu's research involves longitudinal analysis of nationally representative survey data, online and eye-tracking experiments, combining crowdsourcing and machine-based textual analysis, and employing neuroimaging methods to examine communication mechanisms. She is actively involved in highly collaborative, interdisciplinary work, with her research published in leading journals across communication, public health, and psychology. She serves as a senior editor for Health Communication and directs the Communication, Health, and Emerging Media Laboratory (CHARM Lab). She is also the principal investigator on multiple NIH awards and a co-investigator on others, contributing significantly to the field of health communication and media effects.

Research topics

• Computer Science
• Artificial Intelligence
• Computer vision

Selected publications

• Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement

  IEEE Transactions on Image Processing · 2021 · 669 citations

  Senior authorCorresponding
  • Artificial Intelligence
  • Computer Science
  • Artificial Intelligence

  Due to the absence of a desirable objective for low-light image enhancement, previous data-driven methods may provide undesirable enhanced results including amplified noise, degraded contrast and biased colors. In this work, inspired by Retinex theory, we design an end-to-end signal prior-guided layer separation and data-driven mapping network with layer-specified constraints for single-image low-light enhancement. A Sparse Gradient Minimization sub-Network (SGM-Net) is constructed to remove the low-amplitude structures and preserve major edge information, which facilitates extracting paired illumination maps of low/normal-light images. After the learned decomposition, two sub-networks (Enhance-Net and Restore-Net) are utilized to predict the enhanced illumination and reflectance maps, respectively, which helps stretch the contrast of the illumination map and remove intensive noise in the reflectance map. The effects of all these configured constraints, including the signal structure regularization and losses, combine together reciprocally, which leads to good reconstruction results in overall visual quality. The evaluation on both synthetic and real images, particularly on those containing intensive noise, compression artifacts and their interleaved artifacts, shows the effectiveness of our novel models, which significantly outperforms the state-of-the-art methods.

  DOI

• From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement

  2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2020 · 609 citations

  Senior authorCorresponding
  • Artificial Intelligence
  • Computer Science
  • Artificial Intelligence

  Under-exposure introduces a series of visual degradation, i.e. decreased visibility, intensive noise, and biased color, etc. To address these problems, we propose a novel semi-supervised learning approach for low-light image enhancement. 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. The architecture is powerful and flexible to have the merit of training with both paired and unpaired data. On one hand, the proposed network is well designed to extract a series of coarse-to-fine band representations, whose estimations are mutually beneficial in a recursive process. On the other hand, the extracted band representation of the enhanced image in the first stage of DRBN (recursive band learning) bridges the gap between the restoration knowledge of paired data and the perceptual quality preference to real high-quality images. Its second stage (band recomposition) learns to recompose the band representation towards fitting perceptual properties of high-quality images via adversarial learning. With the help of this two-stage design, our approach generates enhanced results with well-reconstructed details and visually promising contrast and color distributions. Qualitative and quantitative evaluations demonstrate the superiority of our DRBN.

  DOI

• LR3M: Robust Low-Light Enhancement via Low-Rank Regularized Retinex Model

  IEEE Transactions on Image Processing · 2020 · 387 citations

  Senior authorCorresponding
  • Artificial Intelligence
  • Computer Science
  • Artificial Intelligence

  Noise causes unpleasant visual effects in low-light image/video enhancement. In this paper, we aim to make the enhancement model and method aware of noise in the whole process. To deal with heavy noise which is not handled in previous methods, we introduce a robust low-light enhancement approach, aiming at well enhancing low-light images/videos and suppressing intensive noise jointly. Our method is based on the proposed Low-Rank Regularized Retinex Model (LR3M), which is the first to inject low-rank prior into a Retinex decomposition process to suppress noise in the reflectance map. Our method estimates a piece-wise smoothed illumination and a noise-suppressed reflectance sequentially, avoiding remaining noise in the illumination and reflectance maps which are usually presented in alternative decomposition methods. After getting the estimated illumination and reflectance, we adjust the illumination layer and generate our enhancement result. Furthermore, we apply our LR3M to video low-light enhancement. We consider inter-frame coherence of illumination maps and find similar patches through reflectance maps of successive frames to form the low-rank prior to make use of temporal correspondence. Our method performs well for a wide variety of images and videos, and achieves better quality both in enhancing and denoising, compared with the state-of-the-art methods.

  DOI

Frequent coauthors

• Wenhan Yang

  First Hospital of China Medical University

  140 shared

• Zongming Guo

  Peking University

  123 shared

• Fan Zou

  70 shared

• Xinyang Li

  Institute of Optics and Electronics, Chinese Academy of Sciences

  54 shared

• Jing Zuo

  48 shared

• Shuai Yang

  46 shared

• Wenjing Wang

  Beijing University of Posts and Telecommunications

  38 shared

• Yueyu Hu

  36 shared

Awards & honors

• K01 award from the National Institutes of Health
• R21 award from the National Institutes of Health
• two R01 awards from the National Institutes of Health

Similar researchers at University of California, Santa Barbara

• Craig Hawkerh-169
• Richard Mayerh-147
• Guillermo C. Bazanh-141
• Steven P. DenBaarsh-124
• Kenneth S. Kosikh-120