16 citations · 28 across the 10 of their papers we have counts for
11 papers · 1 filter
AllRestorer: All-in-One Transformer for Image Restoration under Composite Degradations
Jiawei Mao, Yu Yang, Xuesong Yin +2
Image restoration models often face the simultaneous interaction of multiple degradations in real-world scenarios. Existing approaches typically handle single or composite degradat…
Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization
Jiawei Mao, Xiaoke Huang, Yunfei Xie +7
This paper introduces Story-Iter, a new training-free iterative paradigm to enhance long-story generation. Unlike existing methods that rely on fixed reference images to construct…
SwinStyleformer is a favorable choice for image inversion
Jiawei Mao, Guangyi Zhao, Xuesong Yin +1
This paper proposes the first pure Transformer structure inversion network called SwinStyleformer, which can compensate for the shortcomings of the CNNs inversion framework by hand…
Restorer: Removing Multi-Degradation with All-Axis Attention and Prompt Guidance
Jiawei Mao, Juncheng Wu, Yuyin Zhou +2
There are many excellent solutions in image restoration.However, most methods require on training separate models to restore images with different types of degradation.Although exi…
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…
More comprehensive facial inversion for more effective expression recognition
Jiawei Mao, Guangyi Zhao, Yuanqi Chang +3
Facial expression recognition (FER) plays a significant role in the ubiquitous application of computer vision. We revisit this problem with a new perspective on whether it can acqu…
Token Transformer: Can class token help window-based transformer build better long-range interactions?
Jiawei Mao, Yuanqi Chang, Xuesong Yin
Compared with the vanilla transformer, the window-based transformer offers a better trade-off between accuracy and efficiency. Although the window-based transformer has made great…
Improvements to Self-Supervised Representation Learning for Masked Image Modeling
Jiawei Mao, Xuesong Yin, Yuanqi Chang +1
This paper explores improvements to the masked image modeling (MIM) paradigm. The MIM paradigm enables the model to learn the main object features of the image by masking the input…