中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共9条，第1-9条 帮助

限定条件    
已选(0)清除 条数/页：   排序方式：
Context Disentangling and Prototype Inheriting for Robust Visual Grounding 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 卷号: 46, 期号: 5, 页码: 3213-3229
作者:  Tang, Wei;  Li, Liang;  Liu, Xuejing;  Jin, Lu;  Tang, Jinhui;  Li, Zechao
收藏  |  浏览/下载：3/0  |  提交时间：2024/05/20
Visualization  Grounding  Prototypes  Transformers  Task analysis  Linguistics  Feature extraction  Context disentangling  open-vocabulary scene  prototype discovering  robust grounding  visual grounding (VG)  
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  
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  
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：8/0  |  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  
Not All Samples are Trustworthy: Towards Deep Robust SVP Prediction 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 卷号: 44, 期号: 6, 页码: 3154-3169
作者:  Xu, Qianqian;  Yang, Zhiyong;  Jiang, Yangbangyan;  Cao, Xiaochun;  Yao, Yuan;  Huang, Qingming
收藏  |  浏览/下载：21/0  |  提交时间：2022/12/07
Noise measurement  Annotations  Task analysis  Predictive models  Robustness  Visualization  Training  Subjective visual property (SVP)  robustness  outlier detection  probabilistic model  
Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2019, 卷号: 41, 期号: 7, 页码: 1747-1760
作者:  Liang, Kongming;  Chang, Hong;  Ma, Bingpeng;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：77/0  |  提交时间：2019/08/16
Attribute learning  zero-shot learning  image understanding  
Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 卷号: 38, 期号: 12, 页码: 2457-2471
作者:  Liu, Risheng;  Zhong, Guangyu;  Cao, Junjie;  Lin, Zhouchen;  Shan, Shiguang;  Luo, Zhongxuan
收藏  |  浏览/下载：40/0  |  提交时间：2019/12/13
Visual diffusion  PDE governed combinatorial optimization  submodularity  saliency detection  object tracking  
Multi-View Discriminant Analysis 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 卷号: 38, 期号: 1, 页码: 188-194
作者:  Kan, Meina;  Shan, Shiguang;  Zhang, Haihong;  Lao, Shihong;  Chen, Xilin
收藏  |  浏览/下载：57/0  |  提交时间：2019/12/13
Multi-view discriminant analysis  cross-view recognition  heterogeneous recognition  common space  
Maximal Linear Embedding for Dimensionality Reduction 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 卷号: 33, 期号: 9, 页码: 1776-1792
作者:  Wang, Ruiping;  Shan, Shiguang;  Chen, Xilin;  Chen, Jie;  Gao, Wen
收藏  |  浏览/下载：65/0  |  提交时间：2019/12/16
Dimensionality reduction  manifold learning  maximal linear patch  landmarks-based global alignment