中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共11条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
Infant cry classification using an efficient graph structure and attention-based model 期刊论文
KUWAIT JOURNAL OF SCIENCE, 2024, 卷号: 51, 期号: 3, 页码: 9
作者:  Qiao, Xuesong;  Jiao, Siwen;  Li, Han;  Liu, Gengyuan;  Gao, Xuan;  Li, Zhanshan
收藏  |  浏览/下载：1/0  |  提交时间：2024/12/06
Neural network  Multi-head attention  Infant cry  Audio classification  
Research on Aspect-Level Sentiment Analysis Based on Adversarial Training and Dependency Parsing 期刊论文
ELECTRONICS, 2024, 卷号: 13, 期号: 10, 页码: 16
作者:  Xu, Erfeng;  Zhu, Junwu;  Zhang, Luchen;  Wang, Yi;  Lin, Wei
收藏  |  浏览/下载：1/0  |  提交时间：2024/12/06
multi head attention mechanism  dependency syntactic relationships  adjacency matrix  adversarial training  
CRIC: A VQA Dataset for Compositional Reasoning on Vision and Commonsense 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 5, 页码: 5561-5578
作者:  Gao, Difei;  Wang, Ruiping;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：15/0  |  提交时间：2023/12/04
Visualization  Task analysis  Tail  Head  Annotations  Magnetic heads  Mouth  Visual question answering  compositional reasoning  commonsense reasoning  dataset construction  
3D Face Reconstruction and Gaze Tracking in the HMD for Virtual Interaction 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 3166-3179
作者:  Chen, Shu-Yu;  Lai, Yu-Kun;  Xia, Shihong;  Rosin, Paul L.;  Gao, Lin
收藏  |  浏览/下载：15/0  |  提交时间：2023/12/04
Communication  eye tracking  head-mounted display  real-time facial performance capture  user interaction  virtual reality  
BLPSeg: Balance the Label Preference in Scribble-Supervised Semantic Segmentation 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 4921-4934
作者:  Wang, Yude;  Zhang, Jie;  Kan, Meina;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：15/0  |  提交时间：2023/12/04
Annotations  Semantic segmentation  Training  Task analysis  Head  Semantics  Costs  Scribble-supervised  weakly supervised  semantic segmentation  
Spatial-Temporal Graph Network for Video Crowd Counting 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 卷号: 33, 期号: 1, 页码: 228-241
作者:  Wu, Zhe;  Zhang, Xinfeng;  Tian, Geng;  Wang, Yaowei;  Huang, Qingming
收藏  |  浏览/下载：24/0  |  提交时间：2023/07/12
Computational modeling  Predictive models  Analytical models  Long short term memory  Optical flow  Integrated circuit modeling  Head  Video-based crowd counting  spatiotemporal graph attention  multi-scale module  
Knowledge matters: Chest radiology report generation with general and specific knowledge 期刊论文
MEDICAL IMAGE ANALYSIS, 2022, 卷号: 80, 页码: 11
作者:  Yang, Shuxin;  Wu, Xian;  Ge, Shen;  Zhou, S. Kevin;  Xiao, Li
收藏  |  浏览/下载：19/0  |  提交时间：2023/07/12
Chest radiology report generation  Knowledge graph  Multi-head attention  
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：31/0  |  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  
Femoral head segmentation based on improved fully convolutional neural network for ultrasound images 期刊论文
SIGNAL IMAGE AND VIDEO PROCESSING, 2020, 卷号: 14, 期号: 5, 页码: 1043-1051
作者:  Chen, Lei;  Cui, Yutao;  Song, Hong;  Huang, Bingxuan;  Yang, Jian;  Zhao, Di;  Xia, Bei
收藏  |  浏览/下载：60/0  |  提交时间：2020/12/10
Developmental dysplasia of the hip  Femoral head segmentation  Fully convolutional neural networks  Feature visualization  
RhythmNet: End-to-End Heart Rate Estimation From Face via Spatial-Temporal Representation 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 卷号: 29, 页码: 2409-2423
作者:  Niu, Xuesong;  Shan, Shiguang;  Han, Hu;  Chen, Xilin
收藏  |  浏览/下载：59/0  |  提交时间：2020/12/10
Heart rate  Estimation  Webcams  Databases  Skin  Image color analysis  Head  Remote heart rate estimation  rPPG  spatial-temporal representation  end-to-end learning