中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共14条，第1-10条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
Meta Auxiliary Learning for Facial Action Unit Detection 期刊论文
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2023, 卷号: 14, 期号: 3, 页码: 2526-2538
作者:  Li, Yong;  Shan, Shiguang
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
Facial action unit detection  auxiliary learning  meta learning  
Person Search by a Bi-Directional Task-Consistent Learning Model 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 卷号: 25, 页码: 1190-1203
作者:  Wang, Cheng;  Ma, Bingpeng;  Chang, Hong;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：8/0  |  提交时间：2023/12/04
Task analysis  Detectors  Training  Robustness  Proposals  Feature extraction  Cameras  Deep neural networks  Person search  
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  
SANet: Statistic Attention Network for Video-Based Person Re-Identification 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 卷号: 32, 期号: 6, 页码: 3866-3879
作者:  Bai, Shutao;  Ma, Bingpeng;  Chang, Hong;  Huang, Rui;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：25/0  |  提交时间：2022/12/07
Feature extraction  Task analysis  Computational modeling  Visualization  Video sequences  Fuses  Computer science  Person re-identification  self-attention  long-range dependencies  high-order statistics  
Graph Jigsaw Learning for Cartoon Face Recognition 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 3961-3972
作者:  Li, Yong;  Lao, Lingjie;  Cui, Zhen;  Shan, Shiguang;  Yang, Jian
收藏  |  浏览/下载：22/0  |  提交时间：2022/12/07
Face recognition  Shape  Training  Image color analysis  Layout  Convolutional neural networks  Task analysis  Cartoon face recognition  jigsaw solving  graph convolutional network  self-supervised learning  
IAUnet: Global Context-Aware Feature Learning for Person Reidentification 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 卷号: 32, 期号: 10, 页码: 4460-4474
作者:  Hou, Ruibing;  Ma, Bingpeng;  Chang, Hong;  Gu, Xinqian;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：35/0  |  提交时间：2021/12/01
Context modeling  Feature extraction  Computational modeling  Semantics  Aggregates  Visualization  Task analysis  Feature enhancing  interaction-aggregation  person reidentification (reID)  spatial-temporal context modeling  
Learning to Learn Adaptive Classifier-Predictor for Few-Shot Learning 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 卷号: 32, 期号: 8, 页码: 3458-3470
作者:  Lai, Nan;  Kan, Meina;  Han, Chunrui;  Song, Xingguang;  Shan, Shiguang
收藏  |  浏览/下载：35/0  |  提交时间：2021/12/01
Task analysis  Adaptation models  Training  Predictive models  Feature extraction  Generators  Computational modeling  Few-shot learning  meta-learning  predict classifier weights  task-adaptive predictor  
Learning to Learn Adaptive Classifier-Predictor for Few-Shot Learning (vol 32, pg 3458, 2021) 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 卷号: 32, 期号: 8, 页码: 3784-3784
作者:  Lai, Nan;  Kan, Meina;  Han, Chunrui;  Song, Xingguang;  Shan, Shiguang
收藏  |  浏览/下载：34/0  |  提交时间：2021/12/01
Visual concept conjunction learning with recurrent neural networks 期刊论文
NEUROCOMPUTING, 2020, 卷号: 395, 页码: 229-236
作者:  Liang, Kongming;  Chang, Hong;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：44/0  |  提交时间：2020/12/10
Attribute learning  Concept conjunction  Visual relationship detection  Image retrieval  
Learning deep face representation with long-tail data: An aggregate-and-disperse approach 期刊论文
PATTERN RECOGNITION LETTERS, 2020, 卷号: 133, 页码: 48-54
作者:  Ma, Yuhao;  Kan, Meina;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：61/0  |  提交时间：2020/12/10
Face recognition  Deep representation learning  Long-tail distribution  Aggregate-and-disperse