2 papers
cs.CV2025
Investigation of Frame Differences as Motion Cues for Video Object Segmentation
Sota Kawamura, Hirotada Honda, Shugo Nakamura +1
Automatic Video Object Segmentation (AVOS) refers to the task of autonomously segmenting target objects in video sequences without relying on human-provided annotations in the firs…
cs.LG2023
From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach
Tuan Nguyen, Hirotada Honda, Takashi Sano +3
We propose the Kuramoto Graph Neural Network (KuramotoGNN), a novel class of continuous-depth graph neural networks (GNNs) that employs the Kuramoto model to mitigate the over-smoo…