AoSRNet: All-in-One Scene Recovery Networks via multi-knowledge integration

Y Lu, D Yang, Y Gao, RW Liu, J Liu, Y Guo - Knowledge-Based Systems, 2024 - Elsevier
Scattering and attenuation of light in no-homogeneous imaging media or inconsistent light
intensity will cause insufficient contrast and color distortion in the collected images, which …

Strengthening attention: knowledge distillation via cross-layer feature fusion for image classification

Z Zhai, J Liang, B Cheng, L Zhao, J Qian - International Journal of …, 2024 - Springer
Deep learning has achieved great success in computer vision, especially in image
classification tasks. How to improve the generalization ability and compactness of deep …

A bidirectional fusion branch network with penalty term-based trihard loss for person re-identification

Z Deng, S Liu, P He, Y Song, Q Tang, WB Li - Journal of Visual …, 2023 - Elsevier
Person re-identification (Re-ID) is the recognition of the same person in different camera
views. Because of the existence of highly similar persons and great differences of the same …