中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共105条，第1-10条 帮助

限定条件                
已选(0)清除 条数/页：   排序方式：
Improving Face Anti-spoofing via Advanced Multi-perspective Feature Learning 期刊论文
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2023, 卷号: 19, 期号: 6, 页码: 18
作者:  Wang, Zhuming;  Xu, Yaowen;  Wu, Lifang;  Han, Hu;  Ma, Yukun;  Li, Zun
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
Face anti-spoofing  multi-perspective  universal cues  
Vision-based food nutrition estimation via RGB-D fusion network 期刊论文
FOOD CHEMISTRY, 2023, 卷号: 424, 页码: 10
作者:  Shao, Wenjing;  Min, Weiqing;  Hou, Sujuan;  Luo, Mengjiang;  Li, Tianhao;  Zheng, Yuanjie;  Jiang, Shuqiang
收藏  |  浏览/下载：9/0  |  提交时间：2023/12/04
Food nutrient  Nutrition estimation  Food composition  Deep learning  RGB-D fusion  
Dual Compensation Residual Networks for Class Imbalanced Learning 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 10, 页码: 11733-11752
作者:  Hou, Ruibing;  Chang, Hong;  Ma, Bingpeng;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：8/0  |  提交时间：2023/12/04
Class imbalance learning  class-incremental learning  residual path  
CNIM-GCN: Consensus Neighbor Interaction-based Multi-channel Graph Convolutional Networks 期刊论文
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 卷号: 226, 页码: 11
作者:  Zhu, Xiaofei;  Li, Chenghong;  Guo, Jiafeng;  Dietze, Stefan
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
Network representation learning  Deep learning  Graph convolutional networks  Node classification  
Large Scale Visual Food Recognition 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 8, 页码: 9932-9949
作者:  Min, Weiqing;  Wang, Zhiling;  Liu, Yuxin;  Luo, Mengjiang;  Kang, Liping;  Wei, Xiaoming;  Wei, Xiaolin;  Jiang, Shuqiang
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
Image recognition  Visualization  Task analysis  Benchmark testing  Representation learning  Training  Semantics  Food dataset  food recognition  large-scale datasets  fine-grained recognition  
BoAu: Malicious traffic detection with noise labels based on boundary augmentation 期刊论文
COMPUTERS & SECURITY, 2023, 卷号: 131, 页码: 13
作者:  Yuan, Qingjun;  Liu, Chang;  Yu, Wentao;  Zhu, Yuefei;  Xiong, Gang;  Wang, Yongjuan;  Gou, Gaopeng
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
Malicious traffic detection  Deep learning  Learning with noise labels  Decision boundaries  Encrypted traffic  
Context-Aware Proposal-Boundary Network With Structural Consistency for Audiovisual Event Localization 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 页码: 11
作者:  Wang, Hao;  Zha, Zheng-Jun;  Li, Liang;  Chen, Xuejin;  Luo, Jiebo
收藏  |  浏览/下载：8/0  |  提交时间：2023/12/04
Audiovisual learning  context learning  event localization  
Self-Regulated Learning for Egocentric Video Activity Anticipation 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 6, 页码: 6715-6730
作者:  Qi, Zhaobo;  Wang, Shuhui;  Su, Chi;  Su, Li;  Huang, Qingming;  Tian, Qi
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
Predictive models  Dairy products  Semantics  Feature extraction  Visualization  Activity recognition  Task analysis  Egocentric video activity anticipaiton  third-person video activity anticipaiton  contrastive learning  multi-task learning  self-regulated learning  
Bi-STAN: bilinear spatial-temporal attention network for wearable human activity recognition 期刊论文
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2023, 页码: 17
作者:  Gao, Chenlong;  Chen, Yiqiang;  Jiang, Xinlong;  Hu, Lisha;  Zhao, Zhicheng;  Zhang, Yuxin
收藏  |  浏览/下载：13/0  |  提交时间：2023/07/12
Human activity recognition  Spatial-temporal attention  Bilinear pooling  Low-redundancy  
Viewpoint-Adaptive Representation Disentanglement Network for Change Captioning 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 卷号: 32, 页码: 2620-2635
作者:  Tu, Yunbin;  Li, Liang;  Su, Li;  Du, Junping;  Lu, Ke;  Huang, Qingming
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
Task analysis  Image coding  Adaptation models  Encoding  Computer science  Transformers  Semantics  Change captioning  representation disentanglement  viewpoint-adaptive  position-embedded representation learning