刘智慧｜中国地质大学(武汉)｜学者主页

期刊论文

2026

基于特征增强与上下文融合的ALS点云分类

肖根，刘智慧，马双喜，王智晓

《应用激光》

DOI

2026

VeloEdit: Training-Free Consistent and Continuous Instruction-Based Image Editing via Velocity Field Decomposition

Zongqing Li, Zhihui Liu, Yujie Xie, Shan Wu, Hongshen Lv, Songzhi Su

arXiv.org

DOI

2026

Three Creates All: You Only Sample 3 Steps

Yuren Cai, Guang-Yi Wang, Zongqing Li, Li Li, Zhihui Liu, Songzhi Su

arXiv.org

DOI

2026

PITH-FORMER: A Hierarchical Motion Prediction Framework Guided by Latent Goals and Driving Habits

Jia-Shu Lin, Ganjun Zheng, Zhihui Liu, Wenhao Wang, Zongqing Li, Songzhi Su

IEEE International Conference on Acoustics, Speech, and Signal Processing

DOI

2026

Coarse-to-fine Trajectory Prediction via Time-Aware Interaction Predictor and Conditional Diffusion-based Refiner

Ganjun Zheng, Jia-Shu Lin, Zhihui Liu, Zongqing Li, Feipeng Rong, Songzhi Su

IEEE International Conference on Acoustics, Speech, and Signal Processing

DOI

2026

ARDiff: Anisotropic Residual Diffusion for Heterogeneous Graph Learning

Yong Chen, Li Li, N. Zong, Zhihui Liu, Songzhi Su

AAAI Conference on Artificial Intelligence

DOI

2026

GPS-GS: Geometry-Aware Progressive Optimization with Synergistic Pseudo-Views for Sparse-View Gaussian Splatting

Pei Liu, Hongru Sun, Zhihui Liu, Songzhi Su

IEEE International Conference on Acoustics, Speech, and Signal Processing

DOI

2025

LRMM: Low rank multi-scale multi-modal fusion for person re-identification based on RGB-NI-TI

Di Wu, Zhihui Liu, Zihan Chen, Shenglong Gan, Kaiwen Tan, Qin Wan, Yaonan Wang

Expert Systems With Applications，Vol. 263

DOI

2025

LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation

Chang Liu, Henghui Ding, Kaining Ying, Ling-Yi Hong, Ning Xu, Linjie Yang, Yuchen Fan, Ming-Qi Gao, Jing-Kun Chen, Yunqi Miao, Wu, Zhijin Qin, Jungong Han, Zhixiong Zhang, Shuangrui Ding, Xiao-Wen Dong, Yuhang Zang, Yuhang Cao, Jiaqi Wang, Changwon Lim, Joonyoung Moon, Donghyeon Cho, Tingmin Li, Yixuan Li, Yang Yang, An Yan, Lei-Lei Cao, Feng Lu, Ran Hong, Youhai Jiang, Feng-Jie Zhu, Yujie Xie, Hongyang Zhang, Zhihui Liu, Shihai Ruan, Quan-Zhu Niu, Dengxian Gong, Shihao Chen, Tao Zhang, Yi-Kang Zhou, Haobo Yuan, Lu Qi, Xiang-Tai Li, Shun-Ping Ji, Alexey Nekrasov, Ali Athar, Daan de Geus, Alexander Hermans, Bastian Leibe

arXiv.org

DOI

2025

SAMSON: 3rd Place Solution of LSVOS 2025 VOS Challenge

Yujie Xie, Hongyang Zhang, Zhihui Liu, Shihai Ruan

arXiv.org

DOI

2023

增强特征融合的动态图卷积的机载LiDAR点云分类

余锦，刘智慧，方琮淇，赖祖龙

《应用激光》

2021

基于稀疏迭代协方差矩阵的谐波参数快速估计方法

熊丹丹，刘剑锋，赵红景天，刘智慧

《信号处理》

DOI

2019

一种基于修正动量的RBM算法

沈卉卉，刘国武，付丽华，刘智慧，李宏伟

《电子学报》

2012

乘性和加性噪声中二维谐波频率估计

刘智慧，李宏伟，边家文

《信号处理》

2012

基于留一准则的多尺度径向基函数网络

张猛，付丽华，刘智慧，何婷婷，魏志成

《计算机工程》

2012

基于矩阵旋转不变性的二维谐波免配对方法

刘智慧，李宏伟，彭惠明

《计算机工程与应用》

预印本

2025

Known Meets Unknown: Mitigating Overconfidence in Open Set Recognition

Dongdong Zhao, Ranxin Fang, Changtian Song, Zhihui Liu, Jianwen Xiang

arXiv preprint

刘智慧

精选作品

期刊论文

基于特征增强与上下文融合的ALS点云分类

VeloEdit: Training-Free Consistent and Continuous Instruction-Based Image Editing via Velocity Field Decomposition

Three Creates All: You Only Sample 3 Steps

PITH-FORMER: A Hierarchical Motion Prediction Framework Guided by Latent Goals and Driving Habits

Coarse-to-fine Trajectory Prediction via Time-Aware Interaction Predictor and Conditional Diffusion-based Refiner

ARDiff: Anisotropic Residual Diffusion for Heterogeneous Graph Learning

GPS-GS: Geometry-Aware Progressive Optimization with Synergistic Pseudo-Views for Sparse-View Gaussian Splatting

LRMM: Low rank multi-scale multi-modal fusion for person re-identification based on RGB-NI-TI

LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation

SAMSON: 3rd Place Solution of LSVOS 2025 VOS Challenge

增强特征融合的动态图卷积的机载LiDAR点云分类

基于稀疏迭代协方差矩阵的谐波参数快速估计方法

一种基于修正动量的RBM算法

乘性和加性噪声中二维谐波频率估计

基于留一准则的多尺度径向基函数网络

基于矩阵旋转不变性的二维谐波免配对方法

预印本

Known Meets Unknown: Mitigating Overconfidence in Open Set Recognition

研究方向