53 citations · 112 across the 19 of their papers we have counts for
20 papers
HOT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers
Wenhao Li, Mengyuan Liu, Hong Liu +3
Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make…
Refine Medical Diagnosis Using Generation Augmented Retrieval and Clinical Practice Guidelines
Wenhao Li, Hongkuan Zhang, Hongwei Zhang +5
Current medical language models, adapted from large language models (LLMs), typically predict ICD code-based diagnosis from electronic health records (EHRs) because these labels ar…
TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation
Jiajie Liu, Mengyuan Liu, Hong Liu +1
Recent multi-frame lifting methods have dominated the 3D human pose estimation. However, previous methods ignore the intricate dependence within the 2D pose sequence and learn sing…
NanoHTNet: Nano Human Topology Network for Efficient 3D Human Pose Estimation
Jialun Cai, Mengyuan Liu, Hong Liu +2
The widespread application of 3D human pose estimation (HPE) is limited by resource-constrained edge devices, requiring more efficient models. A key approach to enhancing efficienc…
Dual-Branch Graph Transformer Network for 3D Human Mesh Reconstruction from Video
Tao Tang, Hong Liu, Yingxuan You +2
Human Mesh Reconstruction (HMR) from monocular video plays an important role in human-robot interaction and collaboration. However, existing video-based human mesh reconstruction m…
Depth: Self-Supervised Depth Estimation with Dynamic Mask in Dynamic Scenes
Siyu Chen, Hong Liu, Wenhao Li +3
Depth estimation is a crucial technology in robotics. Recently, self-supervised depth estimation methods have demonstrated great potential as they can efficiently leverage large am…
ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos
Tao Tang, Hong Liu, Yingxuan You +2
Although existing video-based 3D human mesh recovery methods have made significant progress, simultaneously estimating human pose and shape from low-resolution image features limit…
PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection
Yidi Li, Jiahao Wen, Bin Ren +5
The integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. However, this combination often struggles with capturing semantic inf…
Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation
Ti Wang, Mengyuan Liu, Hong Liu +5
Although data-driven methods have achieved success in 3D human pose estimation, they often suffer from domain gaps and exhibit limited generalization. In contrast, optimization-bas…
Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
Wenhao Li, Mengyuan Liu, Hong Liu +3
Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make…
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video
Yingxuan You, Hong Liu, Ti Wang +3
Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging. Existing video-based…
Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
Mengyuan Liu, Hong Liu, Tianyu Guo
Considering the instance-level discriminative ability, contrastive learning methods, including MoCo and SimCLR, have been adapted from the original image representation learning ta…
Interweaved Graph and Attention Network for 3D Human Pose Estimation
Ti Wang, Hong Liu, Runwei Ding +3
Despite substantial progress in 3D human pose estimation from a single-view image, prior works rarely explore global and local correlations, leading to insufficient learning of hum…
GATOR: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Pose
Yingxuan You, Hong Liu, Xia Li +3
3D human mesh recovery from a 2D pose plays an important role in various applications. However, it is hard for existing methods to simultaneously capture the multiple relations dur…
Feature Completion Transformer for Occluded Person Re-identification
Tao Wang, Mengyuan Liu, Hong Liu +4
Occluded person re-identification (Re-ID) is a challenging problem due to the destruction of occluders. Most existing methods focus on visible human body parts through some prior i…
HTNet: Human Topology Aware Network for 3D Human Pose Estimation
Jialun Cai, Hong Liu, Runwei Ding +3
3D human pose estimation errors would propagate along the human body topology and accumulate at the end joints of limbs. Inspired by the backtracking mechanism in automatic control…
GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation
Wenhao Li, Mengyuan Liu, Hong Liu +4
Modern multi-layer perceptron (MLP) models have shown competitive results in learning visual representations without self-attention. However, existing MLP models are not good at ca…
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
Wenhao Li, Hong Liu, Hao Tang +2
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spat…
Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network
Guoliang Hua, Hong Liu, Wenhao Li +3
Although monocular 3D human pose estimation methods have made significant progress, it is far from being solved due to the inherent depth ambiguity. Instead, exploiting multi-view…
Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
Wenhao Li, Hong Liu, Runwei Ding +3
Despite the great progress in 3D human pose estimation from videos, it is still an open problem to take full advantage of a redundant 2D pose sequence to learn representative repre…