Tsung-Yi Lin

papers

6,985

total citations

papers (22)

Magic3D: High-Resolution Text-to-3D Content Creation

CVPR 2023arXiv

1,461

citations

Simple Copy-Paste Is a Strong Data Augmentation Method for Instance Segmentation

CVPR 2021arXiv

1,178

citations

MnasFPN: Learning Latency-Aware Pyramid Architecture for Object Detection on Mobile Devices

CVPR 2020arXiv

citations

Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval From a Single Image

ICCV 2021arXiv

citations

Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation

CVPR 2024arXiv

citations

Efficient Part-level 3D Object Generation via Dual Volume Packing

NEURIPS 2025arXiv

citations

Dynamic Camera Poses and Where to Find Them

CVPR 2025arXiv

citations

HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation

CVPR 2025arXiv

citations

Articulated Kinematics Distillation from Video Diffusion Models

CVPR 2025arXiv

citations

Efficient Scale-Permuted Backbone with Learned Resource Distribution

ECCV 2020arXiv

citations

A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation

ECCV 2022

citations

Tsung-Yi Lin

papers (22)

Magic3D: High-Resolution Text-to-3D Content Creation

Simple Copy-Paste Is a Strong Data Augmentation Method for Instance Segmentation

Bottleneck Transformers for Visual Recognition

Rethinking Pre-training and Self-training

Learning Data Augmentation Strategies for Object Detection

Scaling Open-Vocabulary Image Segmentation with Image-Level Labels

Revisiting ResNets: Improved Training and Scaling Strategies

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

A Unified Sequence Interface for Vision Tasks

Multi-Task Self-Training for Learning General Representations

ATT3D: Amortized Text-to-3D Object Synthesis

Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve

MnasFPN: Learning Latency-Aware Pyramid Architecture for Object Detection on Mobile Devices

Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval From a Single Image

Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation

Efficient Part-level 3D Object Generation via Dual Volume Packing

Dynamic Camera Poses and Where to Find Them

HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation

Articulated Kinematics Distillation from Video Diffusion Models

Efficient Scale-Permuted Backbone with Learned Resource Distribution

A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation

papers (22)

Magic3D: High-Resolution Text-to-3D Content Creation

Simple Copy-Paste Is a Strong Data Augmentation Method for Instance Segmentation

Bottleneck Transformers for Visual Recognition

Rethinking Pre-training and Self-training

Learning Data Augmentation Strategies for Object Detection

Scaling Open-Vocabulary Image Segmentation with Image-Level Labels

Revisiting ResNets: Improved Training and Scaling Strategies

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

A Unified Sequence Interface for Vision Tasks

Multi-Task Self-Training for Learning General Representations

ATT3D: Amortized Text-to-3D Object Synthesis

Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve

MnasFPN: Learning Latency-Aware Pyramid Architecture for Object Detection on Mobile Devices

Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval From a Single Image

Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation

Efficient Part-level 3D Object Generation via Dual Volume Packing

Dynamic Camera Poses and Where to Find Them

HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation

Articulated Kinematics Distillation from Video Diffusion Models

Efficient Scale-Permuted Backbone with Learned Resource Distribution

A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation