Yun Liu

papers

862

total citations

papers (23)

HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction

CVPR 2022arXiv

279

citations

UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-Aware Curriculum and Iterative Generalist-Specialist Learning

ICCV 2023arXiv

149

citations

CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis

CVPR 2023arXiv

citations

CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement

CVPR 2025arXiv

citations

Indiscernible Object Counting in Underwater Scenes

CVPR 2023arXiv

citations

Rethinking Few-shot 3D Point Cloud Semantic Segmentation

CVPR 2024arXiv

citations

Feature Modulation Transformer: Cross-Refinement of Global Representation via High-Frequency Prior for Image Super-Resolution

ICCV 2023arXiv

citations

SensorLM: Learning the Language of Wearable Sensors

NEURIPS 2025arXiv

citations

Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model

CVPR 2025arXiv

citations

ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping

CVPR 2025arXiv

citations

SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis

ICCV 2025arXiv

citations

Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network

AAAI 2025

citations

Exploiting Temporal State Space Sharing for Video Semantic Segmentation

CVPR 2025arXiv

citations

SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization

CVPR 2025

citations

RADAR: Benchmarking Language Models on Imperfect Tabular Data

NEURIPS 2025arXiv

citations

Perceiving and Modeling Density for Image Dehazing

ECCV 2022

citations

Rethinking Computer-Aided Tuberculosis Diagnosis

CVPR 2020

citations

Adverse Weather Removal with Codebook Priors

ICCV 2023

citations

Yun Liu

papers (23)

HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction

UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-Aware Curriculum and Iterative Generalist-Specialist Learning

CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis

TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding

DOTS: Decoupling Operation and Topology in Differentiable Architecture Search

Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation

Coarse-To-Fine Feature Mining for Video Semantic Segmentation

Scaling Wearable Foundation Models

CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement

Indiscernible Object Counting in Underwater Scenes

Rethinking Few-shot 3D Point Cloud Semantic Segmentation

Feature Modulation Transformer: Cross-Refinement of Global Representation via High-Frequency Prior for Image Super-Resolution

SensorLM: Learning the Language of Wearable Sensors

Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model

ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping

SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis

Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network

Exploiting Temporal State Space Sharing for Video Semantic Segmentation

SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization

RADAR: Benchmarking Language Models on Imperfect Tabular Data

Perceiving and Modeling Density for Image Dehazing

Rethinking Computer-Aided Tuberculosis Diagnosis

Adverse Weather Removal with Codebook Priors

papers (23)

HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction

UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-Aware Curriculum and Iterative Generalist-Specialist Learning

CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis

TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding

DOTS: Decoupling Operation and Topology in Differentiable Architecture Search

Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation

Coarse-To-Fine Feature Mining for Video Semantic Segmentation

Scaling Wearable Foundation Models

CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement

Indiscernible Object Counting in Underwater Scenes

Rethinking Few-shot 3D Point Cloud Semantic Segmentation

Feature Modulation Transformer: Cross-Refinement of Global Representation via High-Frequency Prior for Image Super-Resolution

SensorLM: Learning the Language of Wearable Sensors

Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model

ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping

SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis

Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network

Exploiting Temporal State Space Sharing for Video Semantic Segmentation

SnowMaster: Comprehensive Real-world Image Desnowing via MLLM with Multi-Model Feedback Optimization

RADAR: Benchmarking Language Models on Imperfect Tabular Data

Perceiving and Modeling Density for Image Dehazing

Rethinking Computer-Aided Tuberculosis Diagnosis

Adverse Weather Removal with Codebook Priors