2 papers
cs.CV2025
ContextFusion and Bootstrap: An Effective Approach to Improve Slot Attention-Based Object-Centric Learning
Pinzhuo Tian, Shengjie Yang, Hang Yu +1
A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in a…
cs.CV2025
PAD: Phase-Amplitude Decoupling Fusion for Multi-Modal Land Cover Classification
Huiling Zheng, Xian Zhong, Bin Liu +3
The fusion of Synthetic Aperture Radar (SAR) and RGB imagery for land cover classification remains challenging due to modality heterogeneity and underexploited spectral complementa…