activity
20242026
collaborators

6 papers

cs.CV2026

Continual Vision-Language Learning for Remote Sensing: Benchmarking and Analysis

Xingxing Weng, Ruifeng Ni, Chao Pang +5

Current remote sensing vision-language models (RS VLMs) demonstrate impressive performance in image interpretation but rely on static training data, limiting their ability to accom…

cs.CV2025

DragOSM: Extract Building Roofs and Footprints from Aerial Images by Aligning Historical Labels

Kai Li, Xingxing Weng, Yupeng Deng +4

Extracting polygonal roofs and footprints from remote sensing images is critical for large-scale urban analysis. Most existing methods rely on segmentation-based models that assume…

cs.CV2025

High-quality Pseudo-labeling for Point Cloud Segmentation with Scene-level Annotation

Lunhao Duan, Shanshan Zhao, Xingxing Weng +2

This paper investigates indoor point cloud semantic segmentation under scene-level annotation, which is less explored compared to methods relying on sparse point-level labels. In t…

cs.CV2025

Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives

Xingxing Weng, Chao Pang, Gui-Song Xia

Vision-language modeling (VLM) aims to bridge the information gap between images and natural language. Under the new paradigm of first pre-training on massive image-text pairs and…

cs.CV2025

Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation

Chuandong Liu, Xingxing Weng, Shuguo Jiang +3

This paper explores scene affinity (AIScene), namely intra-scene consistency and inter-scene correlation, for semi-supervised LiDAR semantic segmentation in driving scenes. Adoptin…

cs.CV2024

VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis

Chao Pang, Xingxing Weng, Jiang Wu +8

This paper develops a Versatile and Honest vision language Model (VHM) for remote sensing image analysis. VHM is built on a large-scale remote sensing image-text dataset with rich-…