Stephen Lin

papers

34,235

total citations

papers (28)

Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows

ICCV 2021arXiv

29,293

citations

Video Swin Transformer

CVPR 2022arXiv

1,909

citations

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

CVPR 2021arXiv

454

citations

Disentangled Non-local Neural Networks

ECCV 2020arXiv

368

citations

Neural Articulated Radiance Field

ICCV 2021arXiv

239

citations

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

ECCV 2020arXiv

214

citations

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

ECCV 2022arXiv

177

citations

Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation

ECCV 2020arXiv

150

citations

A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

CVPR 2022arXiv

139

citations

RepPoints v2: Verification Meets Regression for Object Detection

NEURIPS 2020arXiv

132

citations

A Transductive Approach for Video Object Segmentation

CVPR 2020arXiv

120

citations

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation

ECCV 2020arXiv

102

citations

Cross-Iteration Batch Normalization

CVPR 2021arXiv

citations

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations

ECCV 2022arXiv

citations

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

CVPR 2022arXiv

citations

Dense RepPoints: Representing Visual Objects with Dense Point Sets

ECCV 2020arXiv

citations

The Emergence of Objectness: Learning Zero-shot Segmentation from Videos

NEURIPS 2021arXiv

citations

Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance

ECCV 2022arXiv

citations

Object-based Illumination Estimation with Rendering-aware Neural Networks

ECCV 2020arXiv

citations

Bringing Rolling Shutter Images Alive with Dual Reversed Distortion

ECCV 2022arXiv

citations

You Only Need Less Attention at Each Stage in Vision Transformers

CVPR 2024arXiv

citations

Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning

ICCV 2023arXiv

citations

Bootstrap Your Object Detector via Mixed Training

NEURIPS 2021arXiv

citations

Associative Transformer

CVPR 2025arXiv

citations

Could Giant Pre-trained Image Models Extract Universal Representations?

NEURIPS 2022

citations

Stephen Lin

papers (28)

Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows

Video Swin Transformer

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

Disentangled Non-local Neural Networks

Neural Articulated Radiance Field

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

Aligning Pretraining for Detection via Object-Level Contrastive Learning

Instance Localization for Self-Supervised Detection Pretraining

Single Image Reflection Removal Through Cascaded Refinement

Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation

A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

RepPoints v2: Verification Meets Regression for Object Detection

A Transductive Approach for Video Object Segmentation

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation

Cross-Iteration Batch Normalization

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

Dense RepPoints: Representing Visual Objects with Dense Point Sets

The Emergence of Objectness: Learning Zero-shot Segmentation from Videos

Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance

Object-based Illumination Estimation with Rendering-aware Neural Networks

Bringing Rolling Shutter Images Alive with Dual Reversed Distortion

You Only Need Less Attention at Each Stage in Vision Transformers

Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning

Bootstrap Your Object Detector via Mixed Training

Associative Transformer

Could Giant Pre-trained Image Models Extract Universal Representations?

papers (28)

Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows

Video Swin Transformer

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

Disentangled Non-local Neural Networks

Neural Articulated Radiance Field

SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

Aligning Pretraining for Detection via Object-Level Contrastive Learning

Instance Localization for Self-Supervised Detection Pretraining

Single Image Reflection Removal Through Cascaded Refinement

Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation

A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

RepPoints v2: Verification Meets Regression for Object Detection

A Transductive Approach for Video Object Segmentation

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation

Cross-Iteration Batch Normalization

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

Dense RepPoints: Representing Visual Objects with Dense Point Sets

The Emergence of Objectness: Learning Zero-shot Segmentation from Videos

Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance

Object-based Illumination Estimation with Rendering-aware Neural Networks

Bringing Rolling Shutter Images Alive with Dual Reversed Distortion

You Only Need Less Attention at Each Stage in Vision Transformers

Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning

Bootstrap Your Object Detector via Mixed Training

Associative Transformer

Could Giant Pre-trained Image Models Extract Universal Representations?