Automated Organization Profile北京邮电大学
北京邮电大学
Current S-Index
Sum of Dataset Indices for all datasets
Average Dataset Index per Dataset
Average Dataset Index per dataset
Total Datasets
Total datasets in this organization
Average FAIR Score
Average FAIR Score per dataset
Total Citations
Total citations to the organization's datasets
Total Mentions
Total mentions of the organization's datasets
S-Index Interpretation
The S-Index (Sharing Index) is a comprehensive metric that represents the cumulative impact of all your datasets. It is calculated as the sum of Dataset Index scores across all your claimed datasets.
What it means:
- A higher S-index indicates greater overall impact of your datasets relative to typical datasets in their fields of research
- The S-Index grows as you add more datasets or as existing datasets gain more citations and mentions
- It provides a single number to track your research data impact over time
Current S-Index: 1.6 (sum of 2 datasets Dataset Index scores)
More information here.
S-Index Over Time
Cumulative Citations Over Time
Cumulative Mentions Over Time
Datasets
现有的多视图 3D 人体姿态估计 方法在很大程度上依赖于精确的外在校准,而 显著限制了它们在不受控制的情况下的实际部署 环境。为了解决这一限制,我们提出了一种无外在参数的多视图 3D 人体姿态估计 (EFMP) 框架,其中包含三个技术贡献。第一 提出了一种局部全局姿态嵌入 (LGPE) 方案 同时捕获细粒度的关节依赖关系 同时建立交叉视图对应关系。其次,开发了 SpatialView Joint Transformer (SVJFormer) 架构 具有三个专用组件:(1) 特征转换 调制 (FTM) 为 不同的标记来模拟异构关系模式;(2) 先验知识增强 (PKE) 系统地整合 人类运动学约束和多视图几何先验 通过结构拓扑编码进行注意力计算; (3) 空间视图联合注意力 (SVJA) 实现解耦 空间视图注意力计算,然后进行联合分布建模,以捕获分层空间视图依赖关系。 第三种是基于骨骼重投影的 Multi-view Aggregation 引入 (BPMA) 机制以整合多个 3D 输出为单个更高质量的 3D 姿势,用于实际应用。对 3 个基准测试的广泛实验表明 我们的方法实现了最先进的性能,同时 保持紧凑的模型大小。代码和结果可用 在 https://github.com/Z-Z-J/EFMP。
Authors
- zhang, zijian