3 papers
cs.CV2026
Overcoming Attention Drift: Homogeneity-Heterogeneity Guided Feature Aggregation for Low-Light Remote Sensing Image Enhancement
Yaozi Zhong, Xingxing Yang, Shaohui Mei +1
Restoring high-fidelity remote sensing imagery from extreme low-light degradation is indispensable for reliable Earth observation and downstream machine vision. However, under seve…
cs.CV2025
Rethinking Occlusion in FER: A Semantic-Aware Perspective and Go Beyond
Huiyu Zhai, Xingxing Yang, Yalan Ye +3
Facial expression recognition (FER) is a challenging task due to pervasive occlusion and dataset biases. Especially when facial information is partially occluded, existing FER mode…
cs.CV2025
DeepSPG: Exploring Deep Semantic Prior Guidance for Low-light Image Enhancement with Multimodal Learning
Jialang Lu, Huayu Zhao, Huiyu Zhai +2
There has long been a belief that high-level semantics learning can benefit various downstream computer vision tasks. However, in the low-light image enhancement (LLIE) community,…