activity
20202024
most cited3DMNDT:3D multi-view registration method based on the normal distributions transform

3 citations · 3 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG2024

Watch Your Head: Assembling Projection Heads to Save the Reliability of Federated Models

Jinqian Chen, Jihua Zhu, Qinghai Zheng +2

Federated learning encounters substantial challenges with heterogeneous data, leading to performance degradation and convergence issues. While considerable progress has been achiev…

cs.LG2023

Contrastive Label Enhancement

Yifei Wang, Yiyang Zhou, Jihua Zhu +3

Label distribution learning (LDL) is a new machine learning paradigm for solving label ambiguity. Since it is difficult to directly obtain label distributions, many studies are foc…

cs.CV2023

HD2Reg: Hierarchical Descriptors and Detectors for Point Cloud Registration

Canhui Tang, Yiheng Li, Shaoyi Du +2

Feature Descriptors and Detectors are two main components of feature-based point cloud registration. However, little attention has been drawn to the explicit representation of loca…

cs.CV2021★ 3 cited

3DMNDT:3D multi-view registration method based on the normal distributions transform

Jihua Zhu, Di Wang, Jiaxi Mu +3

The normal distributions transform (NDT) is an effective paradigm for the point set registration. This method is originally designed for pair-wise registration and it will suffer f…

cs.CV2020

Effective multi-view registration of point sets based on student's t mixture model

Yanlin Ma, Jihua Zhu, Zhongyu Li +2

Recently, Expectation-maximization (EM) algorithm has been introduced as an effective means to solve multi-view registration problem. Most of the previous methods assume that each…

cs.LG2020

Multi-view Subspace Clustering Networks with Local and Global Graph Information

Qinghai Zheng, Jihua Zhu, Yuanyuan Ma +2

This study investigates the problem of multi-view subspace clustering, the goal of which is to explore the underlying grouping structure of data collected from different fields or…