Search

Your search keyword '"Ma, Qiufang"' showing total 23 results
Start Over Author "Ma, Qiufang"

Refine your results

more »

more »

more »
23 results on '"Ma, Qiufang"'

1. Hybrid Transformer and CNN Attention Network for Stereo Image Super-resolution

Author

Cheng, Ming, Ma, Haoyu, Ma, Qiufang, Sun, Xiaopeng, Li, Weiqi, Zhang, Zhenyu, Sheng, Xuhan, Zhao, Shijie, Li, Junlin, and Zhang, Li

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Multi-stage strategies are frequently employed in image restoration tasks. While transformer-based methods have exhibited high efficiency in single-image super-resolution tasks, they have not yet shown significant advantages over CNN-based methods in stereo super-resolution tasks. This can be attributed to two key factors: first, current single-image super-resolution transformers are unable to leverage the complementary stereo information during the process; second, the performance of transformers is typically reliant on sufficient data, which is absent in common stereo-image super-resolution algorithms. To address these issues, we propose a Hybrid Transformer and CNN Attention Network (HTCAN), which utilizes a transformer-based network for single-image enhancement and a CNN-based network for stereo information fusion. Furthermore, we employ a multi-patch training strategy and larger window sizes to activate more input pixels for super-resolution. We also revisit other advanced techniques, such as data augmentation, data ensemble, and model ensemble to reduce overfitting and data bias. Finally, our approach achieved a score of 23.90dB and emerged as the winner in Track 1 of the NTIRE 2023 Stereo Image Super-Resolution Challenge., Comment: 10 pages, 3 figures, accepted by CVPR workshop 2023

Published
2023

2. OPDN: Omnidirectional Position-aware Deformable Network for Omnidirectional Image Super-Resolution

Author

Sun, Xiaopeng, Li, Weiqi, Zhang, Zhenyu, Ma, Qiufang, Sheng, Xuhan, Cheng, Ming, Ma, Haoyu, Zhao, Shijie, Zhang, Jian, Li, Junlin, and Zhang, Li

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

360{\deg} omnidirectional images have gained research attention due to their immersive and interactive experience, particularly in AR/VR applications. However, they suffer from lower angular resolution due to being captured by fisheye lenses with the same sensor size for capturing planar images. To solve the above issues, we propose a two-stage framework for 360{\deg} omnidirectional image superresolution. The first stage employs two branches: model A, which incorporates omnidirectional position-aware deformable blocks (OPDB) and Fourier upsampling, and model B, which adds a spatial frequency fusion module (SFF) to model A. Model A aims to enhance the feature extraction ability of 360{\deg} image positional information, while Model B further focuses on the high-frequency information of 360{\deg} images. The second stage performs same-resolution enhancement based on the structure of model A with a pixel unshuffle operation. In addition, we collected data from YouTube to improve the fitting ability of the transformer, and created pseudo low-resolution images using a degradation network. Our proposed method achieves superior performance and wins the NTIRE 2023 challenge of 360{\deg} omnidirectional image super-resolution., Comment: Accepted to CVPRW 2023

Published
2023

4. NTIRE 2023 Challenge on Stereo Image Super-Resolution: Methods and Results

Author

Wang, Longguang, primary, Guo, Yulan, additional, Wang, Yingqian, additional, Li, Juncheng, additional, Gu, Shuhang, additional, Timofte, Radu, additional, Cheng, Ming, additional, Ma, Haoyu, additional, Ma, Qiufang, additional, Sun, Xiaopeng, additional, Zhao, Shijie, additional, Sheng, Xuhan, additional, Ding, Yukan, additional, Sun, Ming, additional, Wen, Xing, additional, Zhang, Dafeng, additional, Li, Jia, additional, Wang, Fan, additional, Xie, Zheng, additional, He, Zongyao, additional, Qiu, Zidian, additional, Pan, Zilin, additional, Zhan, Zhihao, additional, Xian, Xingyuan, additional, Jin, Zhi, additional, Zhou, Yuanbo, additional, Deng, Wei, additional, Nie, Ruofeng, additional, Zhang, Jiajun, additional, Gao, Qinquan, additional, Tong, Tong, additional, Zhang, Kexin, additional, Zhang, Junpei, additional, Peng, Rui, additional, Ma, Yanbiao, additional, Jiao, Licheng, additional, Bai, Haoran, additional, Kong, Lingshun, additional, Pan, Jinshan, additional, Dong, Jiangxin, additional, Tang, Jinhui, additional, Cao, Pu, additional, Huang, Tianrui, additional, Yang, Lu, additional, Song, Qing, additional, Chen, Bingxin, additional, He, Chunhua, additional, Chen, Meiyun, additional, Guo, Zijie, additional, Luo, Shaojuan, additional, Cao, Chengzhi, additional, Wang, Kunyu, additional, Zhang, Fanrui, additional, Zhang, Qiang, additional, Mehta, Nancy, additional, Murala, Subrahmanyam, additional, Dudhane, Akshay, additional, Wang, Yujin, additional, Li, Lingen, additional, Gendy, Garas, additional, Sabor, Nabil, additional, Hou, Jingchao, additional, He, Guanghui, additional, Chen, Junyang, additional, Li, Hao, additional, Shi, Yukai, additional, Yang, Zhijing, additional, Zou, Wenbin, additional, Zhang, Yunchen, additional, Jiang, Mingchao, additional, Yu, Zhongxin, additional, Tan, Ming, additional, Gao, Hongxia, additional, Luo, Ziwei, additional, Gustafsson, Fredrik K., additional, Zhao, Zheng, additional, Sjölund, Jens, additional, Schön, Thomas B., additional, Chen, Jingxiang, additional, Yang, Bo, additional, Zhang, XiSheryl, additional, Li, Chenghua, additional, Yuan, Weijun, additional, Li, Zhan, additional, Deng, Ruting, additional, Zeng, Jintao, additional, Mahajan, Pulkit, additional, Mistry, Sahaj, additional, Chatterjee, Shreyas, additional, Jakhetiya, Vinit, additional, Subudhi, Badri, additional, Jaiswal, Sunil, additional, Zhang, Zhao, additional, Zheng, Huan, additional, Zhao, Suiyi, additional, Gao, Yangcheng, additional, Wei, Yanyan, additional, Wang, Bo, additional, Li, Gen, additional, Li, Aijin, additional, Sun, Lei, additional, Chen, Ke, additional, Tang, Congling, additional, Li, Yunzhe, additional, Chen, Jun, additional, Chiang, Yuan-Chun, additional, Chen, Yi-Chung, additional, Huang, Zhi-Kai, additional, Yang, Hao-Hsiang, additional, Chen, I-Hsiang, additional, Kuo, Sy-Yen, additional, Wang, Yiheng, additional, Zhu, Gang, additional, Yang, Xingyi, additional, Liu, Songhua, additional, Jing, Yongcheng, additional, Hu, Xingyu, additional, Song, Jianwen, additional, Sun, Changming, additional, Sowmya, Arcot, additional, Park, Seung Ho, additional, Lei, Xiaoyan, additional, Wang, Jingchao, additional, Zhai, Chenbo, additional, Zhang, Yufei, additional, Cao, Weifeng, additional, and Zhang, Wenlong, additional

Published
2023
Full Text
View/download PDF

10. Research on Financing Difficulties of Small and Medium-sized Enterprises in Anhui Province under the Background of Big Data

Author

Ma Qiufang

Subjects
Finance, Credit rating, Government, Qualitative analysis, Quantitative analysis (finance), business.industry, Still face, Big data, Financing system, business, System construction
Abstract

Under the background of Big Data, small and medium-sized enterprises in Anhui Province still face many problems. The outstanding problem is financing. Based on qualitative analysis and quantitative analysis, this paper studies the current situation of small and medium-sized enterprises in Anhui Province and the financing difficulties of small and medium-sized enterprises under the background of Big Data, this paper puts forward some countermeasures to solve the financing problems of small and medium-sized enterprises in Anhui province under the background of Big Data: strengthening the financing consciousness and self-management system construction of small and medium-sized enterprises; We will improve the financial financing system for small and medium-sized enterprises, create new channels for their financing, strengthen the construction of the concept of credit guarantee and upgrade their credit rating, and make full use of state policies.

Published
2020

13. Research on Regional Economic Development of Anhui Province Based on Diffusion Effect

Author

Ma Qiufang

Subjects
Environmental sciences, Economic growth, Diffusion effect, Economics, GE1-350
Abstract

In the development of regional economy, giving full play to the advantages of diffusion effect can effectively promote the overall development of regional economy and improve the quality and efficiency of economic development. Based on the development of regional economy in Anhui Province, this paper discusses in detail the mechanism of diffusion effect and the great role that diffusion effect plays in the economic development of Hefei economic circle and Wanjiang city belt.

Published
2021

23. Lung cancer diagnosis of CT images using metaheuristics and deep learning

Author

Ma, Qiufang and Jimenez, Giorgos

Abstract

Lung cancer is the uncontrolled growth of cells in the lung that is made up of two spongy organs located in the chest. These cells may penetrate outside the lung in a process called metastasis and spread to the tissues and organs of the body and increase the risk of death from this disease. CT scan of pulmonary nodules is one of the methods of early detection of lung cancer. One of the main challenges in diagnosing pulmonary nodules is the difficulty of identifying and distinguishing pulmonary nodules from lung components. In this study, a computer-aided detection system is introduced to identify these nodules. In the study, after image preprocessing, an image segmentation based on Otsu followed by mathematical morphology is proposed. Then, optimal features are selected based on a new metaheuristic method. Consequently, the characteristics are injected into an improved convolutional neural network (CNN)-based classifier to provide a high accuracy diagnosis system. The optimization of the Otsu method, feature selection, and CNN classifier is established by a new modified version of the Red Fox Optimizer (RFO) algorithm. The approach is then applied to three popular lung cancer datasets and the results are compared with three state-of-the-art methods to show the proposed method’s higher efficiency.

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results