Zero-Reference Low-Light Enhancement via Physical Quadruple Priors

W Wang, H Yang, J Fu, J Liu - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
Understanding illumination and reducing the need for supervision pose a significant
challenge in low-light enhancement. Current approaches are highly sensitive to data usage …

Multi-scale contrastive adaptor learning for segmenting anything in underperformed scenes

K Zhou, Z Qiu, D Fu - Neurocomputing, 2024 - Elsevier
Foundational vision models, such as the Segment Anything Model (SAM), have achieved
significant breakthroughs through extensive pre-training on large-scale visual datasets …

A Wavelet-Based Memory Autoencoder for Noncontact Fingerprint Presentation Attack Detection

YP Liu, H Yu, H Fang, Z Li, P Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Fingerprint presentation attack detection (FPAD) is essential in fingerprint identification
systems. Noncontact methods such as fingerprint biometrics are becoming popular because …

A Lightweight Recurrent Grouping Attention Network for Video Super-Resolution

Y Zhu, G Li - Sensors, 2023 - mdpi.com
Effective aggregation of temporal information of consecutive frames is the core of achieving
video super-resolution. Many scholars have utilized structures such as sliding windows and …

Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution

C Fu, H Yuan, S Jiang, G Zhang, L Shen… - arXiv preprint arXiv …, 2024 - arxiv.org
By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution
ones, space-time video super-resolution techniques can enhance visual experiences and …

3DAttGAN: A 3D Attention-Based Generative Adversarial Network for Joint Space-Time Video Super-Resolution

C Fu, H Yuan, L Shen, R Hamzaoui… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Joint space-time video super-resolution aims to increase both the spatial resolution and the
frame rate of a video sequence. As a result, details become more apparent, leading to a …

A Hybrid Transformer-Mamba Network for Single Image Deraining

S Sun, W Ren, J Zhou, J Gan, R Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Existing deraining Transformers employ self-attention mechanisms with fixed-range
windows or along channel dimensions, limiting the exploitation of non-local receptive fields …

Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific Data

G Song, D Fu, Z Qiu, J Meng, D Zhang - arXiv preprint arXiv:2409.07942, 2024 - arxiv.org
Uncertainty estimation is crucial in scientific data for machine learning. Current uncertainty
estimation methods mainly focus on the model's inherent uncertainty, while neglecting the …

Unsupervised Domain Adaptation via Bidirectional Cross-Attention Transformer

X Wang, P Guo, Y Zhang - … Machine Learning and Knowledge Discovery in …, 2023 - Springer
Abstract Unsupervised Domain Adaptation (UDA) seeks to utilize the knowledge acquired
from a source domain, abundant in labeled data, and apply it to a target domain that …