Shuai Yi

papers

2,621

total citations

papers (15)

GroupFormer: Group Activity Recognition With Clustered Spatial-Temporal Transformer

ICCV 2021arXiv

137

citations

Unsupervised 3D Shape Completion Through GAN Inversion

CVPR 2021arXiv

135

citations

EcoNAS: Finding Proxies for Economical Neural Architecture Search

CVPR 2020arXiv

125

citations

Collaborative Unsupervised Visual Representation Learning From Decentralized Data

ICCV 2021arXiv

117

citations

Encoder-Decoder With Multi-Level Attention for 3D Human Shape and Pose Estimation

ICCV 2021arXiv

citations

Unsupervised Domain Adaptive 3D Detection With Multi-Level Consistency

ICCV 2021arXiv

citations

CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

ICCV 2021arXiv

citations

MessyTable: Instance Association in Multiple Camera Views

ECCV 2020arXiv

citations

Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection

ECCV 2020arXiv

citations

Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators

AAAI 2024arXiv

citations

Random Registers for Cross-Domain Few-Shot Learning

ICML 2025arXiv

citations

Shuai Yi

papers (15)

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

Delving Into Localization Errors for Monocular 3D Object Detection

Variational Relational Point Completion Network

GroupFormer: Group Activity Recognition With Clustered Spatial-Temporal Transformer

Unsupervised 3D Shape Completion Through GAN Inversion

EcoNAS: Finding Proxies for Economical Neural Architecture Search

Collaborative Unsupervised Visual Representation Learning From Decentralized Data

Encoder-Decoder With Multi-Level Attention for 3D Human Shape and Pose Estimation

Unsupervised Domain Adaptive 3D Detection With Multi-Level Consistency

CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

MessyTable: Instance Association in Multiple Camera Views

Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection

Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators

Random Registers for Cross-Domain Few-Shot Learning

papers (15)

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

Delving Into Localization Errors for Monocular 3D Object Detection

Variational Relational Point Completion Network

GroupFormer: Group Activity Recognition With Clustered Spatial-Temporal Transformer

Unsupervised 3D Shape Completion Through GAN Inversion

EcoNAS: Finding Proxies for Economical Neural Architecture Search

Collaborative Unsupervised Visual Representation Learning From Decentralized Data

Encoder-Decoder With Multi-Level Attention for 3D Human Shape and Pose Estimation

Unsupervised Domain Adaptive 3D Detection With Multi-Level Consistency

CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

MessyTable: Instance Association in Multiple Camera Views

Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection

Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators

Random Registers for Cross-Domain Few-Shot Learning