2 papers
cs.CV2020
Arbitrary-sized Image Training and Residual Kernel Learning: Towards Image Fraud Identification
Hongyu Li, Xiaogang Huang, Zhihui Fu +1
Preserving original noise residuals in images are critical to image fraud identification. Since the resizing operation during deep learning will damage the microstructures of image…
cs.CV2018
Two-Layer Mixture Network Ensemble for Apparel Attributes Classification
Tianqi Han, Zhihui Fu, Hongyu Li
Recognizing apparel attributes has recently drawn great interest in the computer vision community. Methods based on various deep neural networks have been proposed for image classi…