Wayne Zhang

Affiliations

SenseTime Research

papers

3,444

total citations

papers (19)

RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition

ECCV 2020arXiv

186

citations

Semantically Coherent Out-of-Distribution Detection

ICCV 2021arXiv

151

citations

Panoptic Scene Graph Generation

ECCV 2022arXiv

148

citations

Scale-Equalizing Pyramid Convolution for Object Detection

CVPR 2020arXiv

118

citations

Pseudo-Mask Matters in Weakly-Supervised Semantic Segmentation

ICCV 2021arXiv

104

citations

Vision Transformer With Progressive Sampling

ICCV 2021arXiv

103

citations

Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection

CVPR 2023arXiv

citations

Context-Aware RCNN: A Baseline for Action Detection in Videos

ECCV 2020arXiv

citations

Panoptic Video Scene Graph Generation

CVPR 2023arXiv

citations

Diverse Cotraining Makes Strong Semi-Supervised Segmentor

ICCV 2023arXiv

citations

Text4Seg: Reimagining Image Segmentation as Text Generation

ICLR 2025arXiv

citations

SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation

NEURIPS 2023arXiv

citations

Webly Supervised Image Classification with Self-Contained Confidence

ECCV 2020arXiv

citations

Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation

ICCV 2023arXiv

citations

Wayne Zhang

Affiliations

papers (19)

BiFormer: Vision Transformer With Bi-Level Routing Attention

ViM: Out-of-Distribution With Virtual-Logit Matching

Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation

OpenOOD: Benchmarking Generalized Out-of-Distribution Detection

Fourier Contour Embedding for Arbitrary-Shaped Text Detection

RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition

Semantically Coherent Out-of-Distribution Detection

Panoptic Scene Graph Generation

Scale-Equalizing Pyramid Convolution for Object Detection

Pseudo-Mask Matters in Weakly-Supervised Semantic Segmentation

Vision Transformer With Progressive Sampling

Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection

Context-Aware RCNN: A Baseline for Action Detection in Videos

Panoptic Video Scene Graph Generation

Diverse Cotraining Makes Strong Semi-Supervised Segmentor

Text4Seg: Reimagining Image Segmentation as Text Generation

SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation

Webly Supervised Image Classification with Self-Contained Confidence

Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation

papers (19)

BiFormer: Vision Transformer With Bi-Level Routing Attention

ViM: Out-of-Distribution With Virtual-Logit Matching

Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation

OpenOOD: Benchmarking Generalized Out-of-Distribution Detection

Fourier Contour Embedding for Arbitrary-Shaped Text Detection

RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition

Semantically Coherent Out-of-Distribution Detection

Panoptic Scene Graph Generation

Scale-Equalizing Pyramid Convolution for Object Detection

Pseudo-Mask Matters in Weakly-Supervised Semantic Segmentation

Vision Transformer With Progressive Sampling

Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection

Context-Aware RCNN: A Baseline for Action Detection in Videos

Panoptic Video Scene Graph Generation

Diverse Cotraining Makes Strong Semi-Supervised Segmentor

Text4Seg: Reimagining Image Segmentation as Text Generation

SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation

Webly Supervised Image Classification with Self-Contained Confidence

Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation