3 papers
cs.CV2026
VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion
Zaidao Han, Risa Higashita, Jiang Liu
Camera-based 3D Semantic Scene Completion (SSC) is a critical task for autonomous driving and robotic scene understanding. It aims to infer a complete 3D volumetric representation…
cs.CV2025
Pathology Context Recalibration Network for Ocular Disease Recognition
Zunjie Xiao, Xiaoqing Zhang, Risa Higashita +1
Pathology context and expert experience play significant roles in clinical ocular disease diagnosis. Although deep neural networks (DNNs) have good ocular disease recognition resul…
cs.CV2025
Expert-Like Reparameterization of Heterogeneous Pyramid Receptive Fields in Efficient CNNs for Fair Medical Image Classification
Xiao Wu, Xiaoqing Zhang, Zunjie Xiao +3
Efficient convolutional neural network (CNN) architecture design has attracted growing research interests. However, they typically apply single receptive field (RF), small asymmetr…