CASIA OpenIR

Browse/Search Results:  1-10 of 43 Help

  Show only claimed items
Selected(0)Clear Items/Page:    Sort:
A Comparative Study of CNN- and Transformer-Based Visual Style Transfer 期刊论文
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2022, 卷号: 37, 期号: 3, 页码: 601-614
Authors:  Wei, Hua-Peng;  Deng, Ying-Ying;  Tang, Fan;  Pan, Xing-Jia;  Dong, Wei-Ming
Favorite  |  View/Download:48/0  |  Submit date:2022/07/25
transformer  convolution neural network  visual style transfer  comparative study  
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training 会议论文
, New Orleans, Louisiana & Online, 2022-6-19
Authors:  Li, Zhaowen;  Zhu, Yousong;  Yang, Fan;  Li, Wei;  Zhao, Chaoyang;  Chen, Yingying;  Chen, Zhiyang;  Xie, Jiahao;  Wu, Liwei;  Zhao, Rui;  Tang, Ming;  Wang, Jinqiao
Adobe PDF(1929Kb)  |  Favorite  |  View/Download:85/6  |  Submit date:2022/04/01
Deep learning signatures reveal multiscale intratumor heterogeneity associated with biological functions and survival in recurrent nasopharyngeal carcinoma 期刊论文
EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, 2022, 页码: 11
Authors:  Zhao, Xun;  Liang, Yu-Jing;  Zhang, Xu;  Wen, Dong-Xiang;  Fan, Wei;  Tang, Lin-Quan;  Dong, Di;  Tian, Jie;  Mai, Hai-Qiang
Favorite  |  View/Download:73/0  |  Submit date:2022/06/10
Recurrent nasopharyngeal carcinoma  Survival analysis  Radiomics  Deep learning  
SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin Transformer 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2022, 卷号: 9, 期号: 7, 页码: 1200-1217
Authors:  Jiayi Ma;  Linfeng Tang;  Fan Fan;  Jun Huang;  Xiaoguang Mei;  Yong Ma
Adobe PDF(22803Kb)  |  Favorite  |  View/Download:58/11  |  Submit date:2022/06/27
StyTr2: Image Style Transfer with Transformers 会议论文
, New Orleans, Louisiana, 2022-6
Authors:  Deng, Yingying;  Tang, Fan;  Dong, Weiming;  Ma, Chongyang;  Pan, Xingjia;  Wang, Lei;  Xu, Changsheng
Adobe PDF(10025Kb)  |  Favorite  |  View/Download:59/2  |  Submit date:2022/06/14
Non-dominated sorting based multi-page photo collage 期刊论文
Computational Visual Media, 2021, 卷号: 8, 期号: 2
Authors:  Song,Yu;  Tang,Fan;  Dong,Weiming;  Xu,Changsheng
Favorite  |  View/Download:52/0  |  Submit date:2021/12/28
multi-page photo collage  balance-aware measurements  non-dominated sorting  genetic algorithm  
Transformers in computational visual media: A survey 期刊论文
Computational Visual Media, 2021, 卷号: 8, 期号: 1, 页码: 33-62
Authors:  Xu,Yifan;  Wei,Huapeng;  Lin,Minxuan;  Deng,Yingying;  Sheng,Kekai;  Zhang,Mengdan;  Tang,Fan;  Dong,Weiming;  Huang,Feiyue;  Xu,Changsheng
Adobe PDF(5366Kb)  |  Favorite  |  View/Download:64/2  |  Submit date:2021/12/28
visual transformer  computational visual media (CVM)  high-level vision  low-level vision  image generation  multi-modal learning  
Text Style Transfer With Decorative Elements 会议论文
International Conference on Multimedia Information Processing and Retrieval, Tokyo, Japan, September 10, 2021
Authors:  Yuting,Ma;  Fan,Tang;  Weiming,Dong;  Changsheng,Xu
Adobe PDF(8683Kb)  |  Favorite  |  View/Download:142/20  |  Submit date:2021/06/17
text style transfer, decorative elements extraction, decoration recomposition  
A deep learning-based radiomic nomogram for prognosis and treatment decision in advanced nasopharyngeal carcinoma: A multicentre study 期刊论文
EBIOMEDICINE, 2021, 卷号: 70, 页码: 10
Authors:  Zhong, Lianzhen;  Dong, Di;  Fang, Xueliang;  Zhang, Fan;  Zhang, Ning;  Zhang, Liwen;  Fang, Mengjie;  Jiang, Wei;  Liang, Shaobo;  Li, Cong;  Liu, Yujia;  Zhao, Xun;  Cao, Runnan;  Shan, Hong;  Hu, Zhenhua;  Ma, Jun;  Tang, Linglong;  Tian, Jie
Adobe PDF(3679Kb)  |  Favorite  |  View/Download:91/4  |  Submit date:2021/11/03
Multi-task deep learning  Radiomic nomogram  Survival analysis  Treatment decision  Advanced nasopharyngeal carcinoma  
SiamCPN: Visual tracking with the Siamese center-prediction network 期刊论文
COMPUTATIONAL VISUAL MEDIA, 2021, 卷号: 7, 期号: 2, 页码: 253-265
Authors:  Chen, Dong;  Tang, Fan;  Dong, Weiming;  Yao, Hanxing;  Xu, Changsheng
Favorite  |  View/Download:84/0  |  Submit date:2021/06/15
Siamese network  single object tracking  anchor-free  center point detection