Showing 2025Show all
2 papers · 1 filter
cs.CV2025
Frequency-Domain Decomposition and Recomposition for Robust Audio-Visual Segmentation
Yunzhe Shen, Kai Peng, Leiye Liu +6
Audio-visual segmentation (AVS) plays a critical role in multimodal machine learning by effectively integrating audio and visual cues to precisely segment objects or regions within…
cs.CV2025
DefMamba: Deformable Visual State Space Model
Leiye Liu, Miao Zhang, Jihao Yin +4
Recently, state space models (SSM), particularly Mamba, have attracted significant attention from scholars due to their ability to effectively balance computational efficiency and…