Yunhao Ge

papers

301

total citations

papers (12)

Improving Zero-Shot Generalization and Robustness of Multi-Modal Models

CVPR 2023arXiv

citations

Describe Anything: Detailed Localized Image and Video Captioning

ICCV 2025arXiv

citations

A Peek Into the Reasoning of Neural Networks: Interpreting With Structural Visual Concepts

CVPR 2021arXiv

citations

DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation

ICLR 2025arXiv

citations

Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition

ECCV 2020arXiv

citations

ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary

CVPR 2025arXiv

citations

"Contributions of Shape, Texture, and Color in Visual Recognition"

ECCV 2022

citations

Yunhao Ge

papers (12)

Improving Zero-Shot Generalization and Robustness of Multi-Modal Models

Describe Anything: Detailed Localized Image and Video Captioning

A Peek Into the Reasoning of Neural Networks: Interpreting With Structural Visual Concepts

Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation

Neural-Sim: Learning to Generate Training Data with NeRF

CLR: Channel-wise Lightweight Reprogramming for Continual Learning

3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation

Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition

ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary

"Contributions of Shape, Texture, and Color in Visual Recognition"

papers (12)

Improving Zero-Shot Generalization and Robustness of Multi-Modal Models

Describe Anything: Detailed Localized Image and Video Captioning

A Peek Into the Reasoning of Neural Networks: Interpreting With Structural Visual Concepts

Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation

Neural-Sim: Learning to Generate Training Data with NeRF

CLR: Channel-wise Lightweight Reprogramming for Continual Learning

3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation

Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition

ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary

"Contributions of Shape, Texture, and Color in Visual Recognition"