Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Xiangyu Zhang

Xiangyu Zhang

MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception

Nov 19, 2022
Hongyu Zhou, Zheng Ge, Zeming Li, Xiangyu Zhang

Figure 1 for MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception

Figure 2 for MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception

Figure 3 for MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception

Figure 4 for MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception

Access Paper or Ask Questions

MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

Nov 17, 2022
Yuang Zhang, Tiancai Wang, Xiangyu Zhang

Figure 1 for MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

Figure 2 for MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

Figure 3 for MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

Figure 4 for MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

* Tech report

Access Paper or Ask Questions

Q-LSTM Language Model -- Decentralized Quantum Multilingual Pre-Trained Language Model for Privacy Protection

Oct 06, 2022
Shuyue Stella Li, Xiangyu Zhang, Shu Zhou, Hongchao Shu, Ruixing Liang, Hexin Liu, Leibny Paola Garcia

Figure 1 for Q-LSTM Language Model -- Decentralized Quantum Multilingual Pre-Trained Language Model for Privacy Protection

Figure 2 for Q-LSTM Language Model -- Decentralized Quantum Multilingual Pre-Trained Language Model for Privacy Protection

Figure 3 for Q-LSTM Language Model -- Decentralized Quantum Multilingual Pre-Trained Language Model for Privacy Protection

Figure 4 for Q-LSTM Language Model -- Decentralized Quantum Multilingual Pre-Trained Language Model for Privacy Protection

* 5 pages, 3 figures, 3 tables

Access Paper or Ask Questions

Differentiable Architecture Search with Random Features

Aug 18, 2022
Xuanyang Zhang, Yonggang Li, Xiangyu Zhang, Yongtao Wang, Jian Sun

Figure 1 for Differentiable Architecture Search with Random Features

Figure 2 for Differentiable Architecture Search with Random Features

Figure 3 for Differentiable Architecture Search with Random Features

Figure 4 for Differentiable Architecture Search with Random Features

* Tech Report

Access Paper or Ask Questions

Understanding Masked Image Modeling via Learning Occlusion Invariant Feature

Aug 08, 2022
Xiangwen Kong, Xiangyu Zhang

Figure 1 for Understanding Masked Image Modeling via Learning Occlusion Invariant Feature

Figure 2 for Understanding Masked Image Modeling via Learning Occlusion Invariant Feature

Figure 3 for Understanding Masked Image Modeling via Learning Occlusion Invariant Feature

Figure 4 for Understanding Masked Image Modeling via Learning Occlusion Invariant Feature

Access Paper or Ask Questions

Revisiting the Critical Factors of Augmentation-Invariant Representation Learning

Jul 30, 2022
Junqiang Huang, Xiangwen Kong, Xiangyu Zhang

Figure 1 for Revisiting the Critical Factors of Augmentation-Invariant Representation Learning

Figure 2 for Revisiting the Critical Factors of Augmentation-Invariant Representation Learning

Figure 3 for Revisiting the Critical Factors of Augmentation-Invariant Representation Learning

Figure 4 for Revisiting the Critical Factors of Augmentation-Invariant Representation Learning

* Accepted by ECCV 2022

Access Paper or Ask Questions