CSpace

浏览/检索结果: 共19条,第1-10条 帮助

已选(0)清除 条数/页:   排序方式:
DrawingInStyles: Portrait Image Generation and Editing With Spatially Conditioned StyleGAN 期刊论文
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2023, 卷号: 29, 期号: 10, 页码: 4074-4088
作者:  Su, Wanchao;  Ye, Hui;  Chen, Shu-Yu;  Gao, Lin;  Fu, Hongbo
收藏  |  浏览/下载:7/0  |  提交时间:2023/12/04
Faces  Semantics  Image synthesis  Codes  Training  Transforms  Spatial resolution  Sketch-based portrait generation  suggestive interfaces  data-driven approaches  StyleGAN  conditional generation  
General Greedy De-Bias Learning 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 8, 页码: 9789-9805
作者:  Han, Xinzhe;  Wang, Shuhui;  Su, Chi;  Huang, Qingming;  Tian, Qi
收藏  |  浏览/下载:7/0  |  提交时间:2023/12/04
Task analysis  Correlation  Training  Data models  Question answering (information retrieval)  Visualization  Image classification  Curriculum learning  dataset biases  greedy strategy  robust learning  
Rethinking Label Flipping Attack: From Sample Masking to Sample Thresholding 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 6, 页码: 7668-7685
作者:  Xu, Qianqian;  Yang, Zhiyong;  Zhao, Yunrui;  Cao, Xiaochun;  Huang, Qingming
收藏  |  浏览/下载:7/0  |  提交时间:2023/12/04
Data models  Training data  Training  Deep learning  Predictive models  Testing  Optimization  Label flipping attack  machine learning  
QoE Assessment Model Based on Continuous Deep Learning for Video in Wireless Networks 期刊论文
IEEE TRANSACTIONS ON MOBILE COMPUTING, 2023, 卷号: 22, 期号: 6, 页码: 3619-3633
作者:  Liu, Xuewen;  Chuai, Gang;  Wang, Xin;  Xu, Zhiwei;  Gao, Weidong
收藏  |  浏览/下载:7/0  |  提交时间:2023/12/04
Quality of experience  Quality of service  Training  Data models  Wireless networks  Computational modeling  Mobile computing  Data-driven QoE assessment  continual deep learning  QoE  QoS mapping  wireless network  cascaded DNNs  
Semi-Supervised CT Lesion Segmentation Using Uncertainty-Based Data Pairing and SwapMix 期刊论文
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2023, 卷号: 42, 期号: 5, 页码: 1546-1562
作者:  Qiao, Pengchong;  Li, Han;  Song, Guoli;  Han, Hu;  Gao, Zhiqiang;  Tian, Yonghong;  Liang, Yongsheng;  Li, Xi;  Zhou, S. Kevin;  Chen, Jie
收藏  |  浏览/下载:7/0  |  提交时间:2023/12/04
Lesions  Image segmentation  Computed tomography  Uncertainty  Training  Predictive models  Data models  Semi-supervised learning  lesion segmentation  unreliable pseudo labels  
MaxMatch: Semi-Supervised Learning With Worst-Case Consistency 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 5, 页码: 5970-5987
作者:  Jiang, Yangbangyan;  Li, Xiaodan;  Chen, Yuefeng;  He, Yuan;  Xu, Qianqian;  Yang, Zhiyong;  Cao, Xiaochun;  Huang, Qingming
收藏  |  浏览/下载:7/0  |  提交时间:2023/12/04
Predictive models  Training  Data models  Semantics  Perturbation methods  Computational modeling  Benchmark testing  Semi-supervised learning  consistency regularization  worst-case consistency  image classification  
Long-Tailed Visual Recognition via Improved Cross-Window Self-Attention and TrivialAugment 期刊论文
IEEE ACCESS, 2023, 卷号: 11, 页码: 49601-49610
作者:  Song, Ying;  Li, Mengxing;  Wang, Bo
收藏  |  浏览/下载:7/0  |  提交时间:2023/12/04
Convolutional neural networks  Continuous wavelet transforms  Data models  Training  Computer vision  Transformers  Transfer learning  Long-tailed recognition  self-attention  vision transformer  CNN  TrivialAugment  
A Comprehensive Framework for Long-Tailed Learning via Pretraining and Normalization 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 页码: 13
作者:  Kang, Nan;  Chang, Hong;  Ma, Bingpeng;  Shan, Shiguang
收藏  |  浏览/下载:22/0  |  提交时间:2022/12/07
Training  Tail  Task analysis  Head  Visualization  Feature extraction  Data models  Classifier design  contrastive learning  long-tailed recognition  normalization  
Weakly Supervised Anomaly Detection in Videos Considering the Openness of Events 期刊论文
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 页码: 13
作者:  Zhang, Chen;  Li, Guorong;  Xu, Qianqian;  Zhang, Xinfeng;  Su, Li;  Huang, Qingming
收藏  |  浏览/下载:23/0  |  提交时间:2022/12/07
Anomaly detection  Videos  Open data  Data models  Training  Feature extraction  Predictive models  Anomaly detection  surveillance videos  openness  meta-learning  
Motion Feature Aggregation for Video-Based Person Re-Identification 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 3908-3919
作者:  Gu, Xinqian;  Chang, Hong;  Ma, Bingpeng;  Shan, Shiguang
收藏  |  浏览/下载:20/0  |  提交时间:2022/12/07
Feature extraction  Optical imaging  Computational modeling  Spatiotemporal phenomena  Data mining  Training  Tracking  Video-based person re-identification  temporal information modeling  motion feature extraction