Mengyuan Liu

17

Papers

81

Total Citations

Papers (17)

Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning

GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction

Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking

Expressive Forecasting of 3D Whole-Body Human Motions

Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment

SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation

UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking

Recognizing Human Actions as the Evolution of Pose Estimation Maps

PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation

RenderIH: A Large-Scale Synthetic Dataset for 3D Interacting Hand Pose Estimation

TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation

FlexPose: Pose Distribution Adaptation with Limited Guidance

Recognizing Actions from Robotic View for Natural Human-Robot Interaction

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

Explore In-Context Learning for 3D Point Cloud Understanding