6 papers
The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview
Kai Liu, Haoyang Yue, Zeli Lin +65
This paper presents the NTIRE 2026 Remote Sensing Infrared Image Super-Resolution (x4) Challenge, one of the associated challenges of NTIRE 2026. The challenge aims to recover high…
Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
Hengwei Zhao, Zhengzhong Tu, Zhuo Zheng +4
Positive-Unlabeled (PU) learning aims to train a binary classifier (positive vs. negative) where only limited positive data and abundant unlabeled data are available. While widely…
CuriosAI Submission to the EgoExo4D Proficiency Estimation Challenge 2025
Hayato Tanoue, Hiroki Nishihara, Yuma Suzuki +9
This report presents the CuriosAI team's submission to the EgoExo4D Proficiency Estimation Challenge at CVPR 2025. We propose two methods for multi-view skill assessment: (1) a mul…
HOpenCls: Training Hyperspectral Image Open-Set Classifiers in Their Living Environments
Hengwei Zhao, Xinyu Wang, Zhuo Zheng +2
Hyperspectral image (HSI) open-set classification is critical for HSI classification models deployed in real-world environments, where classifiers must simultaneously classify know…
Learning a Cross-modality Anomaly Detector for Remote Sensing Imagery
Jingtao Li, Xinyu Wang, Hengwei Zhao +2
Remote sensing anomaly detector can find the objects deviating from the background as potential targets for Earth monitoring. Given the diversity in earth anomaly types, designing…
AnomalyCD: A benchmark for Earth anomaly change detection with high-resolution and time-series observations
Jingtao Li, Qian Zhu, Xinyu Wang +2
Various Earth anomalies have destroyed the stable, balanced state, resulting in fatalities and serious destruction of property. With the advantages of large-scale and precise obser…