activity
20242026
collaborators

10 papers

eess.AS2026

Time-Unconditional Generative Speech Enhancement via Autonomous Rectified Flow

Wen Zhang, Wenbin Jiang, Yang Zhang +1

Most generative speech enhancement methods rely on explicit time-step embeddings for temporal conditioning. In this paper, we propose the Autonomous Rectified Flow framework, which…

cs.CV2026

M-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection

Jiyuan Liu, Jia Lin, Xiaofei Zhou +3

The Segment Anything Model 2 (SAM2) has emerged as a foundation model for universal segmentation. Owing to its generalizable visual representations, SAM2 has been successfully appl…

cs.CV2026

G2HFNet: GeoGran-Aware Hierarchical Feature Fusion Network for Salient Object Detection in Optical Remote Sensing Images

Bin Wan, Runmin Cong, Xiaofei Zhou +3

Remote sensing images captured from aerial perspectives often exhibit significant scale variations and complex backgrounds, posing challenges for salient object detection (SOD). Ex…

cs.CV2026

RSONet: Region-guided Selective Optimization Network for RGB-T Salient Object Detection

Bin Wan, Runmin Cong, Xiaofei Zhou +3

This paper focuses on the inconsistency in salient regions between RGB and thermal images. To address this issue, we propose the Region-guided Selective Optimization Network for RG…

cs.CV2026

RDNet: Region Proportion-Aware Dynamic Adaptive Salient Object Detection Network in Optical Remote Sensing Images

Bin Wan, Runmin Cong, Xiaofei Zhou +3

Salient object detection (SOD) in remote sensing images faces significant challenges due to large variations in object sizes, the computational cost of self-attention mechanisms, a…

cs.CV2025

SAM-DAQ: Segment Anything Model with Depth-guided Adaptive Queries for RGB-D Video Salient Object Detection

Jia Lin, Xiaofei Zhou, Jiyuan Liu +4

Recently segment anything model (SAM) has attracted widespread concerns, and it is often treated as a vision foundation model for universal segmentation. Some researchers have atte…