Search

Your search keyword '"Huang, Wenxin"' showing total 747 results
Start Over Author "Huang, Wenxin"
Sorry, I don't understand your search. ×
747 results on '"Huang, Wenxin"'

2. Dynamic Association Learning of Self-Attention and Convolution in Image Restoration

Author

Jiang, Kui, Jia, Xuemei, Huang, Wenxin, Wang, Wenbin, Wang, Zheng, and Jiang, Junjun

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

CNNs and Self attention have achieved great success in multimedia applications for dynamic association learning of self-attention and convolution in image restoration. However, CNNs have at least two shortcomings: 1) limited receptive field; 2) static weight of sliding window at inference, unable to cope with the content diversity.In view of the advantages and disadvantages of CNNs and Self attention, this paper proposes an association learning method to utilize the advantages and suppress their shortcomings, so as to achieve high-quality and efficient inpainting. We regard rain distribution reflects the degradation location and degree, in addition to the rain distribution prediction. Thus, we propose to refine background textures with the predicted degradation prior in an association learning manner. As a result, we accomplish image deraining by associating rain streak removal and background recovery, where an image deraining network and a background recovery network are designed for two subtasks. The key part of association learning is a novel multi-input attention module. It generates the degradation prior and produces the degradation mask according to the predicted rainy distribution. Benefited from the global correlation calculation of SA, MAM can extract the informative complementary components from the rainy input with the degradation mask, and then help accurate texture restoration. Meanwhile, SA tends to aggregate feature maps with self-attention importance, but convolution diversifies them to focus on the local textures. A hybrid fusion network involves one residual Transformer branch and one encoder-decoder branch. The former takes a few learnable tokens as input and stacks multi-head attention and feed-forward networks to encode global features of the image. The latter, conversely, leverages the multi-scale encoder-decoder to represent contexture knowledge., Comment: in Chinese language, Journal of Image and Graphics. arXiv admin note: substantial text overlap with arXiv:2207.10455

Published
2023

4. Hmem: A Holistic Memory Performance Metric for Cloud Computing

Author

Li, Yuyang, Li, Ning, Zhang, Yilei, Guo, Jianmei, Huang, Bo, Xing, Mengbang, Huang, Wenxin, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Hunold, Sascha, editor, Xie, Biwei, editor, and Shu, Kai, editor

Published
2024
Full Text
View/download PDF

5. CSEC: A Chinese Semantic Error Correction Dataset for Written Correction

Author

Huang, Wenxin, Dong, Xiao, Wang, Meng-xiang, Liu, Guangya, Yu, Jianxing, Zhu, Huaijie, Yin, Jian, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Luo, Biao, editor, Cheng, Long, editor, Wu, Zheng-Guang, editor, Li, Hongyi, editor, and Li, Chaojie, editor

Published
2024
Full Text
View/download PDF

18. Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach

Author

Zhong, Xian, Gu, Cheng, Huang, Wenxin, Li, Lin, Chen, Shuqin, and Lin, Chia-Wen

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Few-shot learning is a challenging problem that has attracted more and more attention recently since abundant training samples are difficult to obtain in practical applications. Meta-learning has been proposed to address this issue, which focuses on quickly adapting a predictor as a base-learner to new tasks, given limited labeled samples. However, a critical challenge for meta-learning is the representation deficiency since it is hard to discover common information from a small number of training samples or even one, as is the representation of key features from such little information. As a result, a meta-learner cannot be trained well in a high-dimensional parameter space to generalize to new tasks. Existing methods mostly resort to extracting less expressive features so as to avoid the representation deficiency. Aiming at learning better representations, we propose a meta-learning approach with complemented representations network (MCRNet) for few-shot image classification. In particular, we embed a latent space, where latent codes are reconstructed with extra representation information to complement the representation deficiency. Furthermore, the latent space is established with variational inference, collaborating well with different base-learners, and can be extended to other models. Finally, our end-to-end framework achieves the state-of-the-art performance in image classification on three standard few-shot learning datasets., Comment: 25th International Conference on Pattern Recognition (ICPR2020)

Published
2020

23. Elastic–Plastic Fully π‐Conjugated Polymer with Excellent Energy Dissipation Capacity for Ultra‐Deep‐Blue Flexible Polymer Light‐Emitting Diodes with CIEy = 0.04

Author

Chen, Wenyu, primary, Yu, Ningning, additional, Gong, Huaqiang, additional, Li, Mengyuan, additional, Xu, Weifeng, additional, Zhuo, Zhiqiang, additional, Sun, Zhiyang, additional, Ni, Mingjian, additional, Huang, Wenxin, additional, Yang, Jing, additional, Lin, Yingru, additional, Wang, Lizhi, additional, Li, Hao, additional, Liang, Xinyu, additional, Sun, Ning, additional, Sun, Lili, additional, Bai, Lubing, additional, Han, Yamin, additional, Tao, Youtian, additional, Xu, Man, additional, Yin, Chengrong, additional, An, Xiang, additional, Lin, Jinyi, additional, and Huang, Wei, additional

Published
2024
Full Text
View/download PDF

32. Patching Your Clothes: Semantic-Aware Learning for Cloth-Changed Person Re-Identification

Author

Jia, Xuemei, Zhong, Xian, Ye, Mang, Liu, Wenxuan, Huang, Wenxin, Zhao, Shilei, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Þór Jónsson, Björn, editor, Gurrin, Cathal, editor, Tran, Minh-Triet, editor, Dang-Nguyen, Duc-Tien, editor, Hu, Anita Min-Chun, editor, Huynh Thi Thanh, Binh, editor, and Huet, Benoit, editor

Published
2022
Full Text
View/download PDF

48. Triphenylamine Spiro‐functionalized Light‐emitting Conjugated Polymer with an Ultra‐Deep‐Blue Narrowband Emission for Large‐area Printed Display

Author

Li, Mengyuan, primary, Zhang, Yahui, additional, Yu, Ningning, additional, Chen, Wenyu, additional, Gong, Huaqiang, additional, Zheng, Yingying, additional, Ni, Mingjian, additional, Han, Yamin, additional, Sun, Ning, additional, Bai, Lubing, additional, An, Xiang, additional, Yang, Jing, additional, Lin, Yingru, additional, Huang, Wenxin, additional, Zhuo, Zhiqiang, additional, Liang, Xinyu, additional, Wang, Lizhi, additional, Sun, Lili, additional, Xu, Man, additional, Lin, Jinyi, additional, and Huang, Wei, additional

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results