From the 1 of 7 linked papers with an AI index.
7 papers
ReLATE: Reliability-Guided Evidence Fusion for Robust UAV--Satellite cross-view Geo-Localization
Haochen Jiang, Jialei Pan, Yuzhe Sun +4
The paper introduces UAVSat-Deg, a large benchmark for evaluating UAV‑to‑satellite geo‑localization under various image degradations, and proposes ReLATE, a reliability‑guided feat…
CroBIM-V: Memory-Quality Controlled Remote Sensing Referring Video Object Segmentation
H. Jiang, Y. Sun, Z. Dong +2
Remote sensing video referring object segmentation (RS-RVOS) is challenged by weak target saliency and severe visual information truncation in dynamic scenes, making it extremely d…
CroBIM-U: Uncertainty-Driven Referring Remote Sensing Image Segmentation
Yuzhe Sun, Zhe Dong, Haochen Jiang +2
Referring remote sensing image segmentation aims to localize specific targets described by natural language within complex overhead imagery. However, due to extreme scale variation…
PhyDAE: Physics-Guided Degradation-Adaptive Experts for All-in-One Remote Sensing Image Restoration
Zhe Dong, Yuzhe Sun, Haochen Jiang +2
Remote sensing images inevitably suffer from various degradation factors during acquisition, including atmospheric interference, sensor limitations, and imaging conditions. These c…
DiffRIS: Enhancing Referring Remote Sensing Image Segmentation with Pre-trained Text-to-Image Diffusion Models
Zhe Dong, Yuzhe Sun, Tianzhu Liu +1
Referring remote sensing image segmentation (RRSIS) enables the precise delineation of regions within remote sensing imagery through natural language descriptions, serving critical…
Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation
Zhe Dong, Yuzhe Sun, Tianzhu Liu +2
Given a natural language expression and a remote sensing image, the goal of referring remote sensing image segmentation (RRSIS) is to generate a pixel-level mask of the target obje…