4 papers
Viewport-Unaware Blind Omnidirectional Image Quality Assessment: A Unified and Generalized Approach
Jiebin Yan, Kangcheng Wu, Jingwen Hou +3
Blind omnidirectional image quality assessment (BOIQA) presents a great challenge to the visual quality assessment community, due to different storage formats and diverse user view…
Uncertainty Awareness on Unsupervised Domain Adaptation for Time Series Data
Weide Liu, Xiaoyang Zhong, Lu Wang +4
Unsupervised domain adaptation methods seek to generalize effectively on unlabeled test data, especially when encountering the common challenge in time series data that distributio…
Diffusion-based Facial Aesthetics Enhancement with 3D Structure Guidance
Lisha Li, Jingwen Hou, Weide Liu +2
Facial Aesthetics Enhancement (FAE) aims to improve facial attractiveness by adjusting the structure and appearance of a facial image while preserving its identity as much as possi…
Enhancing Incomplete Multi-modal Brain Tumor Segmentation with Intra-modal Asymmetry and Inter-modal Dependency
Weide Liu, Jingwen Hou, Xiaoyang Zhong +4
Deep learning-based brain tumor segmentation (BTS) models for multi-modal MRI images have seen significant advancements in recent years. However, a common problem in practice is th…