← Search

Qihang Wu

3 accepted papers

2025

CroPe: Cross-Modal Semantic Compensation Adaptation for All Adverse Scene Understanding

NeurIPS 2025poster

Scene understanding in adverse conditions, such as fog, snow, and night, is challenging due to the visual appearance degeneration. In this context, we propose a Cross-modal Semantic Compensation Adaptation method (CroPe) for scene understanding. Distinct from the existing methods, which only use the…

Cited by 0SourceScholar
2025

External Reliable Information-enhanced Multimodal Contrastive Learning for Fake News Detection

AAAI 2025technical

With the rapid development of the Internet, the information dissemination paradigm has changed and the efficiency has been improved greatly. While this also brings the quick spread of fake news and leads to negative impacts on cyberspace. Currently, the information presentation formats have evolved…

2025

Mix-Mask Augmentation and Self-Reconstruction for Cross-Domain Few-Shot Hyperspectral Image Classification

ICASSP 2025accepted

Recently, the metric-based prototypical methods achieves promising performance in few-shot learning (FSL) for hyperspectral image (HSI) classification. However, the existing models are easily affected by the noisy pixels of different categories around the center pixel of the patch, and tend to focus…

Cited by 0SourceScholar