Qihao Liu

Affiliations

Johns Hopkins UniversityShanghai Jiao Tong University

papers

379

total citations

papers (10)

Learning Part Segmentation Through Unsupervised Domain Adaptation From Synthetic Vehicles

CVPR 2022arXiv

citations

Explicit Occlusion Reasoning for Multi-Person 3D Human Pose Estimation

ECCV 2022arXiv

citations

FlowTok: Flowing Seamlessly Across Text and Image Tokens

ICCV 2025arXiv

citations

DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data

CVPR 2024arXiv

citations

PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation

CVPR 2023arXiv

citations

Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution

CVPR 2025arXiv

citations

InstMove: Instance Motion for Object-Centric Video Segmentation

CVPR 2023arXiv

citations

Qihao Liu

Affiliations

papers (10)

In Defense of Online Models for Video Instance Segmentation

General Object Foundation Model for Images and Videos at Scale

Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape

Learning Part Segmentation Through Unsupervised Domain Adaptation From Synthetic Vehicles

Explicit Occlusion Reasoning for Multi-Person 3D Human Pose Estimation

FlowTok: Flowing Seamlessly Across Text and Image Tokens

DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data

PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation

Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution

InstMove: Instance Motion for Object-Centric Video Segmentation

papers (10)

In Defense of Online Models for Video Instance Segmentation

General Object Foundation Model for Images and Videos at Scale

Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape

Learning Part Segmentation Through Unsupervised Domain Adaptation From Synthetic Vehicles

Explicit Occlusion Reasoning for Multi-Person 3D Human Pose Estimation

FlowTok: Flowing Seamlessly Across Text and Image Tokens

DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data

PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation

Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution

InstMove: Instance Motion for Object-Centric Video Segmentation