CASIA OpenIR

浏览/检索结果: 共218条,第1-10条 帮助

  只显示已认领条目
已选(0)清除 条数/页:   排序方式:
Attribute-Guided Cross-Modal Interaction and Enhancement for Audio-Visual Matching 期刊论文
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2024, 卷号: 19, 页码: 4986-4998
作者:  Wang, Jiaxiang;  Zheng, Aihua;  Yan, Yan;  He, Ran;  Tang, Jin
收藏  |  浏览/下载:2/0  |  提交时间:2024/07/03
Audio-visual cross-modal matching  attribute-guided cross-modal interaction  attribute-guided cross-modal enhancement  
Recognizing Predictive Substructures With Subgraph Information Bottleneck 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 卷号: 46, 期号: 3, 页码: 1650-1663
作者:  Yu, Junchi;  Xu, Tingyang;  Rong, Yu;  Bian, Yatao;  Huang, Junzhou;  He, Ran
收藏  |  浏览/下载:1/0  |  提交时间:2024/07/03
Three-dimensional displays  Mutual information  Task analysis  Optimization  Training  Redundancy  Computer vision  Graph convolutional network  subgraph information bottleneck  graph classification  
Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning 会议论文
, Torino, Italia, 2024-5
作者:  Zhitao He;  Pengfei Cao;  Zhuoran Jin;  Yubo Chen;  Kang Liu;  Jun Zhao
Adobe PDF(794Kb)  |  收藏  |  浏览/下载:16/8  |  提交时间:2024/06/25
Bi-Directional and Early Interaction Transformers for Bird’s Eye View Semantic Segmentation 会议论文
, Vancouver Convention Center, 2023 年 6 月 18 日 – 2023 年 6 月 22 日
作者:  Pan Cong;  He Yonghao;  Peng Junran;  Zhang Qian;  Sui Wei;  Zhang Zhaoxiang
Adobe PDF(2215Kb)  |  收藏  |  浏览/下载:40/20  |  提交时间:2024/06/12
Improving Subgraph Recognition with Variational Graph Information Bottleneck 会议论文
, 美国路易斯安那新奥尔良, 2022
作者:  Yu, Junchi;  Cao, Jie;  He, Ran
Adobe PDF(2212Kb)  |  收藏  |  浏览/下载:22/7  |  提交时间:2024/06/03
基于边缘特征增强的任意形状文本检测网络 期刊论文
自动化学报, 2023, 卷号: 49, 期号: 5, 页码: 1019-1030
作者:  白鹤翔;  王浩然
Adobe PDF(3157Kb)  |  收藏  |  浏览/下载:44/15  |  提交时间:2024/05/09
场景文本检测  任意形状  边缘区域  浅层特征  渐进尺度扩张网络  
A General Framework for Deep Supervised Discrete Hashing 期刊论文
International Journal of Computer Vision, 2020, 页码: 2204-2222
作者:  Li, Qi;  Sun, Zhenan;  He, Ran;  Tan, Tieniu
Adobe PDF(1007Kb)  |  收藏  |  浏览/下载:142/47  |  提交时间:2024/02/23
ScoreMix: A Scalable Augmentation Strategy for Training GANs With Limited Data 期刊论文
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 7, 页码: 8920-8935
作者:  Cao, Jie;  Luo, Mandi;  Yu, Junchi;  Yang, Ming-Hsuan;  He, Ran
Adobe PDF(1823Kb)  |  收藏  |  浏览/下载:125/7  |  提交时间:2023/11/17
Generative adversarial networks  image synthesis  data augmentation  few-shot image-to-image translation  
ProxyMix: Proxy-based Mixup training with label refinery for source-free domain adaptation 期刊论文
NEURAL NETWORKS, 2023, 卷号: 167, 页码: 92-103
作者:  Ding, Yuhe;  Sheng, Lijun;  Liang, Jian;  Zheng, Aihua;  He, Ran
收藏  |  浏览/下载:85/0  |  提交时间:2023/11/16
Source-free unsupervised domain  adaptation  Pseudo labeling  
MEAD: A Large-scale Audio-visual Dataset for Emotional Talking Face Generation 会议论文
, Glasgow, 2020-08-23
作者:  王凯思源;  Song LS(宋林森);  Wu QY(吴潜溢);  Yang ZQ(杨卓谦);  Wu WY(吴文岩);  Qian C(钱晨);  He R(赫然);  Qiao Y(乔宇);  Loy, Chen Change
Adobe PDF(8588Kb)  |  收藏  |  浏览/下载:109/25  |  提交时间:2023/06/29