3 papers
cs.CV2025
AttFC: Attention Fully-Connected Layer for Large-Scale Face Recognition with One GPU
Zhuowen Zheng, Yain-Whar Si, Xiaochen Yuan +5
Nowadays, with the advancement of deep neural networks (DNNs) and the availability of large-scale datasets, the face recognition (FR) model has achieved exceptional performance. Ho…
cs.CV2025
MSConv: Multiplicative and Subtractive Convolution for Face Recognition
Si Zhou, Yain-Whar Si, Xiaochen Yuan +5
In Neural Networks, there are various methods of feature fusion. Different strategies can significantly affect the effectiveness of feature representation, consequently influencing…
cs.CV2025
RVAFM: Re-parameterizing Vertical Attention Fusion Module for Handwritten Paragraph Text Recognition
Jinhui Zheng, Zhiquan Liu, Yain-Whar Si +5
Handwritten Paragraph Text Recognition (HPTR) is a challenging task in Computer Vision, requiring the transformation of a paragraph text image, rich in handwritten text, into text…