Junwei Liang

papers

466

total citations

papers (12)

The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction

CVPR 2020arXiv

181

citations

SimAug: Learning Robust Representations from Simulation for Trajectory Prediction

ECCV 2020arXiv

citations

Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation

CVPR 2025arXiv

citations

Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization

NEURIPS 2025arXiv

citations

STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition

CVPR 2023arXiv

citations

Multi-dataset Training of Transformers for Robust Action Recognition

NEURIPS 2022arXiv

citations

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

ECCV 2024arXiv

citations

GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs

ICCV 2025arXiv

citations

Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations

ICCV 2021

citations

Junwei Liang

papers (12)

The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction

SimAug: Learning Robust Representations from Simulation for Trajectory Prediction

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval

Prioritized Semantic Learning for Zero-shot Instance Navigation

Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation

Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization

STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition

Multi-dataset Training of Transformers for Robust Action Recognition

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs

Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations

papers (12)

The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction

SimAug: Learning Robust Representations from Simulation for Trajectory Prediction

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval

Prioritized Semantic Learning for Zero-shot Instance Navigation

Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation

Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization

STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition

Multi-dataset Training of Transformers for Robust Action Recognition

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs

Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations