更多论文请访问： Google Scholar

2026

Figure 1: DSVTformer: Dual-Stream Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation

Wanruo Zhang, Mengyuan Liu*, Wenhao Li, Hong Liu. DSVTformer: Dual-Stream Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation. PR, 2026. (通讯作者, 模式识别期刊)

[论文][代码]
Figure 1: Pose2Point: Bridging human poses and point clouds for unified action recognition

Jiaying Lin, Jiajun Wen, Weiwei Wan, Mengyuan Liu*. Pose2Point: Bridging human poses and point clouds for unified action recognition. PR, 2026. (通讯作者, 模式识别期刊)

[论文][代码]
Figure 1: DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition

Jiaying Lin, Shiman Wu, Jinfu Liu, Can Wang, Mengyuan Liu* . DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition. ECCV, 2026. (通讯作者, 计算机视觉顶会)

[论文] [代码]
Figure 1: UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation

Ziyi Wang, Xinshun Wang, Chen Shuang, Cong Yang, Mengyuan Liu* . UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation. ECCV, 2026. (通讯作者, 计算机视觉顶会)

[论文] [代码]
Figure 1: Universal Skeleton Understanding via Differentiable Rendering and MLLMs

Ziyi Wang, Peiming Li, Xinshun Wang, Yang Tang, Kai-Kuang Ma, Mengyuan Liu* . Universal Skeleton Understanding via Differentiable Rendering and MLLMs. ICML, 2026. (通讯作者, 机器学习顶会)

[论文] [代码]
Figure 1: Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation

Xinshun Wang, Peiming Li, Ziyi Wang, Zhongbin Fang, Zhichao Deng, Songtao Wu, Xiangtai Li, Mengyuan Liu* . Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation. CVPR, 2026. (通讯作者, 计算机视觉顶会)

[论文] [代码]
Figure 1: Find Anything Like Humans: Online Semantic Mapping and Coarse-to-Fine Navigation in Dynamic Environments

Yutian Zhang, Jianyu Zhang, Mengyuan Liu* . Find Anything Like Humans: Online Semantic Mapping and Coarse-to-Fine Navigation in Dynamic Environments. ICRA, 2026. (通讯作者, 机器人顶会)

[论文] [代码]
Figure 1: MP1: MeanFlow Tames Policy Learning in 1-step for Robotic Manipulation

Juyi Sheng, Ziyi Wang, Peiming Li, Mengyuan Liu* . MP1: MeanFlow Tames Policy Learning in 1-step for Robotic Manipulation. AAAI, 2026. (通讯作者, 人工智能顶会)

[论文] [代码]
Figure 1: Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation

Ti Wang, Mengyuan Liu*, Hong Liu, Bin Ren, Yingxuan You, Wenhao Li, Nicu Sebe, Xia Li. Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation. TMM, 2026. (通讯作者, 多媒体期刊)

[论文][代码]

2025

Figure 1: Heatmap Pooling Network for Action Recognition From RGB Videos

Mengyuan Liu, Jinfu Liu, Yongkang Jiang, Bin He. Heatmap Pooling Network for Action Recognition From RGB Videos. TPAMI, 2025. (第一作者, 计算机视觉顶刊)

[论文][代码]
Figure 1: H2OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers

Wenhao Li, Mengyuan Liu*, Hong Liu, Pichao Wang, Shijian Lu, Nicu Sebe. H2OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers. TPAMI, 2025. (共同通讯作者, 计算机视觉顶刊)

[论文][代码]
Figure 1: Recognizing Actions from Robotic View for Natural Human-Robot Interaction

Ziyi Wang, Peiming Li, Hong Liu, Zhichao Deng, Can Wang, Jun Liu, Junsong Yuan, Mengyuan Liu* . Recognizing Actions from Robotic View for Natural Human-Robot Interaction. ICCV, 2025. (通讯作者, 计算机视觉顶会)

[论文] [代码]
Figure 1: Ust-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling

Peiming Li, Ziyi Wang, Yulin Yuan, Hong Liu, Xiangming Meng, Junsong Yuan, Mengyuan Liu* . Ust-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling. ICCV, 2025. (通讯作者, 计算机视觉顶会)

[论文] [代码]
Figure 1: Recognizing Skeleton-Based Actions As Points

BaiqiaoYin, Jiaying Lin, Jiajun Wen, Yue Li, Jinfu Liu, Yanfei Wang, Mengyuan Liu*. Recognizing Skeleton-Based Actions As Points. IROS, 2025. (通讯作者, 机器人顶会)

[论文][代码]
Figure 1: Frequency-Aware Self-Supervised Group Activity Recognition with Skeleton Sequences

Guoquan Wang, Mengyuan Liu*, Hong Liu, Jinyan Zhang, Peini Guo, Ruijia Fan, Siyu Chen. Frequency-Aware Self-Supervised Group Activity Recognition with Skeleton Sequences. PR, 2025. (通讯作者, 模式识别期刊)

[论文][代码]
Figure 1: NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation

Jialun Cai, Mengyuan Liu*, Hong Liu, Wenhao Li, Shuheng Zhou. NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation. TIP, 2025. (通讯作者, 图像处理顶刊)

[论文][代码]
Figure 1: TcpFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation

Jiajie Liu, Mengyuan Liu* , Hong Liu, Wenhao Li. TcpFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation. AAAI, 2025. (通讯作者, 人工智能顶会)

[论文] [代码]
Figure 1: SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation

Wanruo Zhang, Mengyuan Liu*, Hong Liu, Wenhao Li. SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation. AAAI, 2025. (通讯作者, 人工智能顶会)

[论文][代码]

2024

Figure 1: GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation

Wenhao Li, Mengyuan Liu*, Hong Liu, Tianyu Guo, Ti Wang, Hao Tang, Nicu Sebe. GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation. PR, 2024. (通讯作者, 模式识别期刊)

[论文][代码]
Figure 1: Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition

Jinfu Liu, Chen Chen, Mengyuan Liu*. Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition. ACM MM, 2024. (通讯作者, 多媒体顶会)

[论文][代码]
Figure 1: ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models

Peiming Li, Ziyi Wang, Mengyuan Liu* , Hong Liu, Chen Chen. ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models. ACM MM, 2024. (通讯作者, 多媒体顶会)

[论文] [代码]
Figure 1: APP: Adaptive Pose Pooling for 3D Human Pose Estimation from Videos

Jinyan Zhang, Mengyuan Liu* , Hong Liu, Guoquan Wang, Wenhao Li. APP: Adaptive Pose Pooling for 3D Human Pose Estimation from Videos. ACM MM, 2024. (通讯作者, 多媒体顶会)

[论文] [代码]
Figure 1: CHAMP: a large-scale dataset for skeleton-based composite human motion prediction

Wanying Zhang, Mengyuan Liu*, Xinshun Wang, Shen Zhao, Can Wang. CHAMP: a large-scale dataset for skeleton-based composite human motion prediction. TCSVT, 2024. (通讯作者, 视频技术期刊)

[论文][代码]
Figure 1: Improving Self-Supervised Action Recognition from Extremely Augmented Skeleton Sequences

Tianyu Guo, Mengyuan Liu*, Hong Liu, Guoquan Wang, Wenhao Li. Improving Self-Supervised Action Recognition from Extremely Augmented Skeleton Sequences. PR, 2024. (通讯作者, 模式识别期刊)

[论文][代码]
Figure 1: Augmented Skeleton Sequences with Hypergraph Network for Self-Supervised Group Activity Recognition

Guoquan Wang, Mengyuan Liu*, Hong Liu, Peini Guo, Ti Wang, Jingwen Guo, Ruijia Fan. Augmented Skeleton Sequences with Hypergraph Network for Self-Supervised Group Activity Recognition. PR, 2024. (通讯作者, 模式识别期刊)

[论文][代码]
Figure 1: Facial Prior Guided Micro-Expression Generation

Yi Zhang, Xinhua Xu, Youjun Zhao, Yuhang Wen, Zixuan Tang, Mengyuan Liu*. Facial Prior Guided Micro-Expression Generation. TIP, 2024. (通讯作者, 图像处理顶刊)

[论文][代码]
Figure 1: Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

Wenhao Li, Mengyuan Liu*, Hong Liu, Pichao Wang, Jialun Cai, Nicu Sebe. Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation. CVPR, 2024. (通讯作者, 计算机视觉顶会)

[论文][代码]

地址

北京大学深圳研究生院
广东省深圳市西丽大学城北大校区 518055

邮箱

liumengyuan@pku.edu.cn