5 papers
Fracast-0: Fractal Weight Sharing for a Time Series Foundation Model with Only 85K Parameters
Tianxiang Zhan, Huanyao Zhang, Yuanpeng He
Time series foundation models must preserve multi-domain breadth, probabilistic output, and multiple temporal scales, but parameter count grows when each scale receives a separate…
Co-Evidential Fusion with Information Volume for Medical Image Segmentation
Yuanpeng He, Lijian Li, Tianxiang Zhan +3
Although existing semi-supervised image segmentation methods have achieved good performance, they cannot effectively utilize multiple sources of voxel-level uncertainty for targete…
Residual Feature-Reutilization Inception Network for Image Classification
Yuanpeng He, Wenjie Song, Lijian Li +2
Capturing feature information effectively is of great importance in the field of computer vision. With the development of convolutional neural networks (CNNs), concepts like residu…
Generalized Uncertainty-Based Evidential Fusion with Hybrid Multi-Head Attention for Weak-Supervised Temporal Action Localization
Yuanpeng He, Lijian Li, Tianxiang Zhan +2
Weakly supervised temporal action localization (WS-TAL) is a task of targeting at localizing complete action instances and categorizing them with video-level labels. Action-backgro…
A Matrix-based Distance of Pythagorean Fuzzy Set and its Application in Medical Diagnosis
Yuanpeng He, Lijian Li, Tianxiang Zhan
The pythagorean fuzzy set (PFS) which is developed based on intuitionistic fuzzy set, is more efficient in elaborating and disposing uncertainties in indeterminate situations, whic…