中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共12条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2026, 卷号: 28, 页码: 297-308
作者:  Li, Yinqi;  Chang, Hong;  Hou, Ruibing;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：1/0  |  提交时间：2026/05/25
Diffusion models  Object detection  Layout  Noise  Training  Noise reduction  Vocabulary  Dogs  Bicycles  Image synthesis  Diffusion model  generative modeling  discriminative Task  object detection  visual recognition  
Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 8, 页码: 10212-10227
作者:  Yang, Chuanguang;  An, Zhulin;  Zhou, Helong;  Zhuang, Fuzhen;  Xu, Yongjun;  Zhang, Qian
收藏  |  浏览/下载：71/0  |  提交时间：2023/12/04
Contrastive learning  mutual learning  online knowledge distillation  visual recognition  
Plant Disease Recognition: A Large-Scale Benchmark Dataset and a Visual Region and Loss Reweighting Approach 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 卷号: 30, 页码: 2003-2015
作者:  Liu, Xinda;  Min, Weiqing;  Mei, Shuhuan;  Wang, Lili;  Jiang, Shuqiang
收藏  |  浏览/下载：101/0  |  提交时间：2021/12/01
Diseases  Agriculture  Plants (biology)  Visualization  Image recognition  Feature extraction  Medical diagnosis  Plant disease recognition  fine-grained visual classification  reweighting approach  feature aggregation  
Few-shot Food Recognition via Multi-view Representation Learning 期刊论文
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2020, 卷号: 16, 期号: 3, 页码: 20
作者:  Jiang, Shuqiang;  Min, Weiqing;  Lyu, Yongqiang;  Liu, Linhu
收藏  |  浏览/下载：105/0  |  提交时间：2020/12/10
Food recognition  few-shot learning  visual recognition  deep learning  
Learning to Recognize Visual Concepts for Visual Question Answering With Structural Label Space 期刊论文
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2020, 卷号: 14, 期号: 3, 页码: 494-505
作者:  Gao, Difei;  Wang, Ruiping;  Shan, Shiguang;  Chen, Xilin
收藏  |  浏览/下载：113/0  |  提交时间：2020/12/10
Visualization  Semantics  Grounding  Knowledge discovery  Sports  Task analysis  Image recognition  Visual question answering  visual concept recognition  structural label space  
A Hierarchical CNN-RNN Approach for Visual Emotion Classification 期刊论文
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2019, 卷号: 15, 期号: 3, 页码: 17
作者:  Li, Liang;  Zhu, Xinge;  Hao, Yiming;  Wang, Shuhui;  Gao, Xingyu;  Huang, Qingming
收藏  |  浏览/下载：95/0  |  提交时间：2020/12/10
Visual emotion recognition  multi-task learning  feature fusing  hierarchical CNN-RNN  stacked bi-directional RNN  
A survey on context-aware mobile visual recognition 期刊论文
MULTIMEDIA SYSTEMS, 2017, 卷号: 23, 期号: 6, 页码: 647-665
作者:  Min, Weiqing;  Jiang, Shuqiang;  Wang, Shuhui;  Xu, Ruihan;  Cao, Yushan;  Herranz, Luis;  He, Zhiqiang
收藏  |  浏览/下载：111/0  |  提交时间：2019/12/12
Mobile visual recognition  Context  Survey  
Fine-Grained Image Classification via Low-Rank Sparse Coding With General and Class-Specific Codebooks 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2017, 卷号: 28, 期号: 7, 页码: 1550-1559
作者:  Zhang, Chunjie;  Liang, Chao;  Li, Liang;  Liu, Jing;  Huang, Qingming;  Tian, Qi
收藏  |  浏览/下载：108/0  |  提交时间：2019/12/12
Fine grained  image representation  semantic space  visual recognition  
Boosted random contextual semantic space based representation for visual recognition 期刊论文
INFORMATION SCIENCES, 2016, 卷号: 369, 页码: 160-170
作者:  Zhang, Chunjie;  Xue, Zhe;  Zhu, Xiaobin;  Wang, Huanian;  Huang, Qingming;  Tian, Qi
收藏  |  浏览/下载：107/0  |  提交时间：2019/12/13
Pattern recognition  Image processing  Visual representation  
Socio-mobile landmark recognition using local features with adaptive region selection 期刊论文
NEUROCOMPUTING, 2016, 卷号: 172, 页码: 100-113
作者:  Zhang, Chunjie;  Zhang, Yifan;  Zhu, Xiaobin;  Xue, Zhe;  Qin, Lei;  Huang, Qingming;  Tian, Qi
收藏  |  浏览/下载：108/0  |  提交时间：2019/12/13
Mobile  Social relationship  Adaptive region selection  Local feature  Geo-codebook  Visual recognition