|
Selected(0)Clear
Items/Page: Sort: |
| ZBS：Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection 会议论文
, 加拿大温哥华, 2023-6-18到2023-6-22
Authors: 安永琪; 赵旭 ; 于涛; 郭海云; 赵朝阳; 唐明; 王金桥
 Adobe PDF(4738Kb) |  Favorite | View/Download：35/9 | Submit date：2023/04/25 |
| 基于图像和点云融合的3D目标检测方法研究 学位论文
, 2023
Authors: 张永昌
Adobe PDF(6879Kb) | Favorite | View/Download：26/1 | Submit date：2023/05/29
3D目标检测 图像和点云 注意力融合 时空数据关联 目标追踪 |
| 联合显著性检测技术及其应用研究 学位论文
, 2023
Authors: 王煜
Adobe PDF(12172Kb) | Favorite | View/Download：5/0 | Submit date：2023/06/07
联合显著性检测 特征空间调制 组内一致性 组间可分性 协同感知 |
| 多模态超声时空特征互作融合智能分析算法及其辅助临床诊断研究 学位论文
, 2023
Authors: 孟哲令
Adobe PDF(10969Kb) | Favorite | View/Download：28/1 | Submit date：2023/05/18
多模态超声影像 互作融合 人工智能辅助临床诊断 多步模态融合网络 层次化诊断网络 |
| 基于运动想象的脑电信号分类算法研究 学位论文
, 2023
Authors: 曲宗福
Adobe PDF(11117Kb) | Favorite | View/Download：9/0 | Submit date：2023/05/29
运动想象，Transformer，图卷积神经网络，OpenBCI |
| Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation 期刊论文
IEEE Transactions on Multimedia, 2023, 页码: 1 - 13
Authors: Liu, Jiawei; Wang, Weining; Chen, Sihan; Zhu, Xinxin; Liu, Jing
Adobe PDF(7741Kb) | Favorite | View/Download：15/0 | Submit date：2023/05/03
Text-guided sounding-video generation Videoaudio representation Contrastive learning Transformer |
| The Human Continuity Activity Semi-Supervised Recognizing Model for Multi-View IoT Network 期刊论文
IEEE Internet of Things Journal, 2023, 卷号: 17, 期号: 4, 页码: 2031-2046
Authors: Ruiwen Yuan; Wang JP(王军平)
Adobe PDF(1265Kb) | Favorite | View/Download：13/4 | Submit date：2023/05/05 |
| Temporal sparse adversarial attack on sequence-based gait recognition 期刊论文
PATTERN RECOGNITION, 2023, 卷号: 133, 页码: 11
Authors: He, Ziwen; Wang, Wei; Dong, Jing; Tan, Tieniu
Adobe PDF(1435Kb) | Favorite | View/Download：96/4 | Submit date：2022/11/21
Adversarial attack Gait recognition Temporal sparsity |
| STGSA: A Novel Spatial-Temporal Graph Synchronous Aggregation Model for Traffic Prediction 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 1, 页码: 226-238
Authors: Zebing Wei; Hongxia Zhao; Zhishuai Li; Xiaojie Bu; Yuanyuan Chen; Xiqiao Zhang; Yisheng Lv; Fei-Yue Wang
 Adobe PDF(7068Kb) | Favorite | View/Download：75/14 | Submit date：2023/01/03
Deep learning graph neural network (GNN) multi-stream spatial-temporal feature extraction temporal graph traffic prediction |
| Coarse-to-Fine Video Instance Segmentation With Factorized Conditional Appearance Flows 期刊论文
IEEE/CAA Journal of Automatica Sinica, 2023, 卷号: 10, 期号: 5, 页码: 1192-1208
Authors: Zheyun Qin; Xiankai Lu; Xiushan Nie; Dongfang Liu; Yilong Yin; Wenguan Wang
Adobe PDF(42794Kb) | Favorite | View/Download：7/0 | Submit date：2023/04/26
Embedding learning generative model normalizing flows video instance segmentation (VIS) |
