16 citations · 29 across the 5 of their papers we have counts for
5 papers
Medical supervised masked autoencoders: Crafting a better masking strategy and efficient fine-tuning schedule for medical image classification
Jiawei Mao, Shujian Guo, Yuanqi Chang +2
Masked autoencoders (MAEs) have displayed significant potential in the classification and semantic segmentation of medical images in the last year. Due to the high similarity of hu…
Star-Net: Improving Single Image Desnowing Model With More Efficient Connection and Diverse Feature Interaction
Jiawei Mao, Yuanqi Chang, Xuesong Yin +1
Compared to other severe weather image restoration tasks, single image desnowing is a more challenging task. This is mainly due to the diversity and irregularity of snow shape, whi…
POSTER++: A simpler and stronger facial expression recognition network
Jiawei Mao, Rui Xu, Xuesong Yin +3
Facial expression recognition (FER) plays an important role in a variety of real-world applications such as human-computer interaction. POSTER achieves the state-of-the-art (SOTA)…
Masked autoencoders are effective solution to transformer data-hungry
Jiawei Mao, Honggu Zhou, Xuesong Yin +1
Vision Transformers (ViTs) outperforms convolutional neural networks (CNNs) in several vision tasks with its global modeling capabilities. However, ViT lacks the inductive bias inh…
SoMoFormer: Social-Aware Motion Transformer for Multi-Person Motion Prediction
Xiaogang Peng, Yaodi Shen, Haoran Wang +3
Multi-person motion prediction remains a challenging problem, especially in the joint representation learning of individual motion and social interactions. Most prior methods only…