32 citations · 55 across the 32 of their papers we have counts for
8 papers · 1 filter
Learning to See Low-Light Images via Feature Domain Adaptation
Qirui Yang, Qihua Cheng, Huanjing Yue +3
Raw low light image enhancement (LLIE) has achieved much better performance than the sRGB domain enhancement methods due to the merits of raw data. However, the ambiguity between n…
RISAM: Referring Image Segmentation via Mutual-Aware Attention Features
Mengxi Zhang, Yiming Liu, Xiangjun Yin +2
Referring image segmentation (RIS) aims to segment a particular region based on a language expression prompt. Existing methods incorporate linguistic features into visual features…
Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations
Huanjing Yue, Yijia Cheng, Xin Liu +1
Capturing screen contents by smartphone cameras has become a common way for information sharing. However, these images and videos are often degraded by moiré patterns, which are ca…
Multi-scale Promoted Self-adjusting Correlation Learning for Facial Action Unit Detection
Xin Liu, Kaishen Yuan, Xuesong Niu +4
Facial Action Unit (AU) detection is a crucial task in affective computing and social robotics as it helps to identify emotions expressed through facial expressions. Anatomically,…
rPPG-MAE: Self-supervised Pre-training with Masked Autoencoders for Remote Physiological Measurement
Xin Liu, Yuting Zhang, Zitong Yu +3
Remote photoplethysmography (rPPG) is an important technique for perceiving human vital signs, which has received extensive attention. For a long time, researchers have focused on…
RViDeformer: Efficient Raw Video Denoising Transformer with a Larger Benchmark Dataset
Huanjing Yue, Cong Cao, Lei Liao +1
In recent years, raw video denoising has garnered increased attention due to the consistency with the imaging process and well-studied noise modeling in the raw domain. However, tw…
HDR Video Reconstruction with a Large Dynamic Dataset in Raw and sRGB Domains
Huanjing Yue, Yubo Peng, Biting Yu +3
High dynamic range (HDR) video reconstruction is attracting more and more attention due to the superior visual quality compared with those of low dynamic range (LDR) videos. The av…
Unsupervised HDR Image and Video Tone Mapping via Contrastive Learning
Cong Cao, Huanjing Yue, Xin Liu +1
Capturing high dynamic range (HDR) images (videos) is attractive because it can reveal the details in both dark and bright regions. Since the mainstream screens only support low dy…