4 papers
Image Segmentation via Variational Model Based Tailored UNet: A Deep Variational Framework
Kaili Qi, Wenli Yang, Ye Li +1
Traditional image segmentation methods, such as variational models based on partial differential equations (PDEs), offer strong mathematical interpretability and precise boundary m…
Let the Model Learn to Feel: Mode-Guided Tonality Injection for Symbolic Music Emotion Recognition
Haiying Xia, Zhongyi Huang, Yumei Tan +1
Music emotion recognition is a key task in symbolic music understanding (SMER). Recent approaches have shown promising results by fine-tuning large-scale pre-trained models (e.g.,…
Robust Variational Model Based Tailored UNet: Leveraging Edge Detector and Mean Curvature for Improved Image Segmentation
Kaili Qi, Zhongyi Huang, Wenli Yang
To address the challenge of segmenting noisy images with blurred or fragmented boundaries, this paper presents a robust version of Variational Model Based Tailored UNet (VM_TUNet),…
Image Restoration Models with Optimal Transport and Total Variation Regularization
Weijia Huang, Zhongyi Huang, Wenli Yang +1
In this paper, we propose image restoration models using optimal transport (OT) and total variation regularization. We present theoretical results of the proposed models based on t…