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

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Lei Zhang

Lei Zhang

Peking University, Beijing, China, Visiting student, Department of Mechanical Engineering, Northwestern University

Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth


Jul 28, 2021
Chenhang He, Jianqiang Huang, Xian-Sheng Hua, Lei Zhang

Figure 1 for Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
Figure 2 for Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
Figure 3 for Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
Figure 4 for Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
* 10 pages, 8 figures 
  Access Paper or Ask Questions

Image Scene Graph Generation (SGG) Benchmark


Jul 27, 2021
Xiaotian Han, Jianwei Yang, Houdong Hu, Lei Zhang, Jianfeng Gao, Pengchuan Zhang

Figure 1 for Image Scene Graph Generation (SGG) Benchmark
Figure 2 for Image Scene Graph Generation (SGG) Benchmark
Figure 3 for Image Scene Graph Generation (SGG) Benchmark
Figure 4 for Image Scene Graph Generation (SGG) Benchmark

  Access Paper or Ask Questions

Improve Unsupervised Pretraining for Few-label Transfer


Jul 26, 2021
Suichan Li, Dongdong Chen, Yinpeng Chen, Lu Yuan, Lei Zhang, Qi Chu, Bin Liu, Nenghai Yu

Figure 1 for Improve Unsupervised Pretraining for Few-label Transfer
Figure 2 for Improve Unsupervised Pretraining for Few-label Transfer
Figure 3 for Improve Unsupervised Pretraining for Few-label Transfer
Figure 4 for Improve Unsupervised Pretraining for Few-label Transfer
* ICCV 2021. arXiv admin note: substantial text overlap with arXiv:2012.05899 
  Access Paper or Ask Questions

Query2Label: A Simple Transformer Way to Multi-Label Classification


Jul 22, 2021
Shilong Liu, Lei Zhang, Xiao Yang, Hang Su, Jun Zhu

Figure 1 for Query2Label: A Simple Transformer Way to Multi-Label Classification
Figure 2 for Query2Label: A Simple Transformer Way to Multi-Label Classification
Figure 3 for Query2Label: A Simple Transformer Way to Multi-Label Classification
Figure 4 for Query2Label: A Simple Transformer Way to Multi-Label Classification

  Access Paper or Ask Questions

Bridging the Gap between Spatial and Spectral Domains: A Theoretical Framework for Graph Neural Networks


Jul 21, 2021
Zhiqian Chen, Fanglan Chen, Lei Zhang, Taoran Ji, Kaiqun Fu, Liang Zhao, Feng Chen, Lingfei Wu, Charu Aggarwal, Chang-Tien Lu

Figure 1 for Bridging the Gap between Spatial and Spectral Domains: A Theoretical Framework for Graph Neural Networks
Figure 2 for Bridging the Gap between Spatial and Spectral Domains: A Theoretical Framework for Graph Neural Networks
Figure 3 for Bridging the Gap between Spatial and Spectral Domains: A Theoretical Framework for Graph Neural Networks
Figure 4 for Bridging the Gap between Spatial and Spectral Domains: A Theoretical Framework for Graph Neural Networks

  Access Paper or Ask Questions

Conditional Directed Graph Convolution for 3D Human Pose Estimation


Jul 16, 2021
Wenbo Hu, Changgong Zhang, Fangneng Zhan, Lei Zhang, Tien-Tsin Wong

Figure 1 for Conditional Directed Graph Convolution for 3D Human Pose Estimation
Figure 2 for Conditional Directed Graph Convolution for 3D Human Pose Estimation
Figure 3 for Conditional Directed Graph Convolution for 3D Human Pose Estimation
Figure 4 for Conditional Directed Graph Convolution for 3D Human Pose Estimation
* ACM International Conference on Multimedia (ACM MM), 2021 
  Access Paper or Ask Questions

Sliding Spectrum Decomposition for Diversified Recommendation


Jul 12, 2021
Yanhua Huang, Weikun Wang, Lei Zhang, Ruiwen Xu

Figure 1 for Sliding Spectrum Decomposition for Diversified Recommendation
Figure 2 for Sliding Spectrum Decomposition for Diversified Recommendation
Figure 3 for Sliding Spectrum Decomposition for Diversified Recommendation
Figure 4 for Sliding Spectrum Decomposition for Diversified Recommendation
* In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '21), August 14--18, 2021, Virtual Event, Singapore 
  Access Paper or Ask Questions

NTIRE 2021 Multi-modal Aerial View Object Classification Challenge


Jul 02, 2021
Jerrick Liu, Nathan Inkawhich, Oliver Nina, Radu Timofte, Sahil Jain, Bob Lee, Yuru Duan, Wei Wei, Lei Zhang, Songzheng Xu, Yuxuan Sun, Jiaqi Tang, Xueli Geng, Mengru Ma, Gongzhe Li, Xueli Geng, Huanqia Cai, Chengxue Cai, Sol Cummings, Casian Miron, Alexandru Pasarica, Cheng-Yen Yang, Hung-Min Hsu, Jiarui Cai, Jie Mei, Chia-Ying Yeh, Jenq-Neng Hwang, Michael Xin, Zhongkai Shangguan, Zihe Zheng, Xu Yifei, Lehan Yang, Kele Xu, Min Feng

Figure 1 for NTIRE 2021 Multi-modal Aerial View Object Classification Challenge
Figure 2 for NTIRE 2021 Multi-modal Aerial View Object Classification Challenge
Figure 3 for NTIRE 2021 Multi-modal Aerial View Object Classification Challenge
Figure 4 for NTIRE 2021 Multi-modal Aerial View Object Classification Challenge
* Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, 588-595 
 * 10 pages, 1 figure. Conference on Computer Vision and Pattern Recognition 
  Access Paper or Ask Questions

Unsupervised Single Image Super-resolution Under Complex Noise


Jul 02, 2021
Zongsheng Yue, Qian Zhao, Jianwen Xie, Lei Zhang, Deyu Meng

Figure 1 for Unsupervised Single Image Super-resolution Under Complex Noise
Figure 2 for Unsupervised Single Image Super-resolution Under Complex Noise
Figure 3 for Unsupervised Single Image Super-resolution Under Complex Noise
Figure 4 for Unsupervised Single Image Super-resolution Under Complex Noise

  Access Paper or Ask Questions

Text Prior Guided Scene Text Image Super-resolution


Jun 30, 2021
Jianqi Ma, Shi Guo, Lei Zhang

Figure 1 for Text Prior Guided Scene Text Image Super-resolution
Figure 2 for Text Prior Guided Scene Text Image Super-resolution
Figure 3 for Text Prior Guided Scene Text Image Super-resolution
Figure 4 for Text Prior Guided Scene Text Image Super-resolution
* Code has been released on https://github.com/mjq11302010044/TPGSR 
  Access Paper or Ask Questions

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents


Jun 23, 2021
Rui Meng, Khushboo Thaker, Lei Zhang, Yue Dong, Xingdi Yuan, Tong Wang, Daqing He

Figure 1 for Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents
Figure 2 for Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents
Figure 3 for Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents
Figure 4 for Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents
* Accepted at ACL2021 
  Access Paper or Ask Questions

Gradual Domain Adaptation via Self-Training of Auxiliary Models


Jun 18, 2021
Yabin Zhang, Bin Deng, Kui Jia, Lei Zhang

Figure 1 for Gradual Domain Adaptation via Self-Training of Auxiliary Models
Figure 2 for Gradual Domain Adaptation via Self-Training of Auxiliary Models
Figure 3 for Gradual Domain Adaptation via Self-Training of Auxiliary Models
Figure 4 for Gradual Domain Adaptation via Self-Training of Auxiliary Models
* code will be released at: https://github.com/YBZh/AuxSelfTrain 
  Access Paper or Ask Questions

Dynamic Head: Unifying Object Detection Heads with Attentions


Jun 15, 2021
Xiyang Dai, Yinpeng Chen, Bin Xiao, Dongdong Chen, Mengchen Liu, Lu Yuan, Lei Zhang

Figure 1 for Dynamic Head: Unifying Object Detection Heads with Attentions
Figure 2 for Dynamic Head: Unifying Object Detection Heads with Attentions
Figure 3 for Dynamic Head: Unifying Object Detection Heads with Attentions
Figure 4 for Dynamic Head: Unifying Object Detection Heads with Attentions
* CVPR 2021 camera ready with extensions 
  Access Paper or Ask Questions

Domain Adaptive SiamRPN++ for Object Tracking in the Wild


Jun 15, 2021
Zhongzhou Zhang, Lei Zhang

Figure 1 for Domain Adaptive SiamRPN++ for Object Tracking in the Wild
Figure 2 for Domain Adaptive SiamRPN++ for Object Tracking in the Wild
Figure 3 for Domain Adaptive SiamRPN++ for Object Tracking in the Wild
Figure 4 for Domain Adaptive SiamRPN++ for Object Tracking in the Wild
* 10 pages,7 figures 
  Access Paper or Ask Questions

Chasing Sparsity in Vision Transformers: An End-to-End Exploration


Jun 09, 2021
Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

Figure 1 for Chasing Sparsity in Vision Transformers: An End-to-End Exploration
Figure 2 for Chasing Sparsity in Vision Transformers: An End-to-End Exploration
Figure 3 for Chasing Sparsity in Vision Transformers: An End-to-End Exploration
Figure 4 for Chasing Sparsity in Vision Transformers: An End-to-End Exploration

  Access Paper or Ask Questions

Chasing Sparsity in Vision Transformers:An End-to-End Exploration


Jun 08, 2021
Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

Figure 1 for Chasing Sparsity in Vision Transformers:An End-to-End Exploration
Figure 2 for Chasing Sparsity in Vision Transformers:An End-to-End Exploration
Figure 3 for Chasing Sparsity in Vision Transformers:An End-to-End Exploration
Figure 4 for Chasing Sparsity in Vision Transformers:An End-to-End Exploration

  Access Paper or Ask Questions

Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners


Jun 01, 2021
Yabin Zhang, Haojian Zhang, Bin Deng, Shuai Li, Kui Jia, Lei Zhang

Figure 1 for Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners
Figure 2 for Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners
Figure 3 for Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners
Figure 4 for Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners
* Codes are available at https://github.com/YBZh 
  Access Paper or Ask Questions

Unsupervised Part Segmentation through Disentangling Appearance and Shape


May 26, 2021
Shilong Liu, Lei Zhang, Xiao Yang, Hang Su, Jun Zhu

Figure 1 for Unsupervised Part Segmentation through Disentangling Appearance and Shape
Figure 2 for Unsupervised Part Segmentation through Disentangling Appearance and Shape
Figure 3 for Unsupervised Part Segmentation through Disentangling Appearance and Shape
Figure 4 for Unsupervised Part Segmentation through Disentangling Appearance and Shape
* Accepted in CVPR 2021 
  Access Paper or Ask Questions

High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network


May 19, 2021
Jie Liang, Hui Zeng, Lei Zhang

Figure 1 for High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network
Figure 2 for High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network
Figure 3 for High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network
Figure 4 for High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network
* To appear at CVPR 2021 
  Access Paper or Ask Questions

PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency


May 19, 2021
Jie Liang, Hui Zeng, Miaomiao Cui, Xuansong Xie, Lei Zhang

Figure 1 for PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency
Figure 2 for PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency
Figure 3 for PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency
Figure 4 for PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency
* To appear at CVPR 2021 
  Access Paper or Ask Questions

HiDeNN-PGD: reduced-order hierarchical deep learning neural networks


May 13, 2021
Lei Zhang, Ye Lu, Shaoqiang Tang, Wing Kam Liu

Figure 1 for HiDeNN-PGD: reduced-order hierarchical deep learning neural networks
Figure 2 for HiDeNN-PGD: reduced-order hierarchical deep learning neural networks
Figure 3 for HiDeNN-PGD: reduced-order hierarchical deep learning neural networks
Figure 4 for HiDeNN-PGD: reduced-order hierarchical deep learning neural networks
* 35 pages, 12 figures 
  Access Paper or Ask Questions

GAN Prior Embedded Network for Blind Face Restoration in the Wild


May 13, 2021
Tao Yang, Peiran Ren, Xuansong Xie, Lei Zhang

Figure 1 for GAN Prior Embedded Network for Blind Face Restoration in the Wild
Figure 2 for GAN Prior Embedded Network for Blind Face Restoration in the Wild
Figure 3 for GAN Prior Embedded Network for Blind Face Restoration in the Wild
Figure 4 for GAN Prior Embedded Network for Blind Face Restoration in the Wild

  Access Paper or Ask Questions

Estimation of 3D Human Pose Using Prior Knowledge


May 09, 2021
Shu Chen, Lei Zhang, Beiji Zou

Figure 1 for Estimation of 3D Human Pose Using Prior Knowledge
Figure 2 for Estimation of 3D Human Pose Using Prior Knowledge
Figure 3 for Estimation of 3D Human Pose Using Prior Knowledge
Figure 4 for Estimation of 3D Human Pose Using Prior Knowledge
* letter 
  Access Paper or Ask Questions

Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks


May 08, 2021
Jiapeng Tang, Jiabao Lei, Dan Xu, Feiying Ma, Kui Jia, Lei Zhang

Figure 1 for Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks
Figure 2 for Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks
Figure 3 for Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks
Figure 4 for Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks
* 18 pages; 14 figures; 5 tables 
  Access Paper or Ask Questions

CAT: Cross-Attention Transformer for One-Shot Object Detection


Apr 30, 2021
Weidong Lin, Yuyan Deng, Yang Gao, Ning Wang, Jinghao Zhou, Lingqiao Liu, Lei Zhang, Peng Wang

Figure 1 for CAT: Cross-Attention Transformer for One-Shot Object Detection
Figure 2 for CAT: Cross-Attention Transformer for One-Shot Object Detection
Figure 3 for CAT: Cross-Attention Transformer for One-Shot Object Detection
Figure 4 for CAT: Cross-Attention Transformer for One-Shot Object Detection
* 7 pages, 3 figures 
  Access Paper or Ask Questions

Discover the Hidden Attack Path in Multi-domain Cyberspace Based on Reinforcement Learning


Apr 15, 2021
Lei Zhang, Wei Bai, Wei Li, Shiming Xia, Qibin Zheng

Figure 1 for Discover the Hidden Attack Path in Multi-domain Cyberspace Based on Reinforcement Learning
Figure 2 for Discover the Hidden Attack Path in Multi-domain Cyberspace Based on Reinforcement Learning
Figure 3 for Discover the Hidden Attack Path in Multi-domain Cyberspace Based on Reinforcement Learning
Figure 4 for Discover the Hidden Attack Path in Multi-domain Cyberspace Based on Reinforcement Learning
* 12 pages, 2 figures, 3 tables. arXiv admin note: substantial text overlap with arXiv:2007.04614 
  Access Paper or Ask Questions

Lite-HRNet: A Lightweight High-Resolution Network


Apr 13, 2021
Changqian Yu, Bin Xiao, Changxin Gao, Lu Yuan, Lei Zhang, Nong Sang, Jingdong Wang

Figure 1 for Lite-HRNet: A Lightweight High-Resolution Network
Figure 2 for Lite-HRNet: A Lightweight High-Resolution Network
Figure 3 for Lite-HRNet: A Lightweight High-Resolution Network
Figure 4 for Lite-HRNet: A Lightweight High-Resolution Network
* Accepted to CVPR 2021 
  Access Paper or Ask Questions

CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning


Apr 13, 2021
Luowei Zhou, Jingjing Liu, Yu Cheng, Zhe Gan, Lei Zhang

Figure 1 for CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning
Figure 2 for CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning
Figure 3 for CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning
Figure 4 for CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning
* 12 pages, 4 figures 
  Access Paper or Ask Questions

Smart and Secure CAV Networks Empowered by AI-Enabled Blockchain: Next Frontier for Intelligent Safe-Driving Assessment


Apr 09, 2021
Le Xia, Yao Sun, Rafiq Swash, Lina Mohjazi, Lei Zhang, Muhammad Ali Imran

Figure 1 for Smart and Secure CAV Networks Empowered by AI-Enabled Blockchain: Next Frontier for Intelligent Safe-Driving Assessment
Figure 2 for Smart and Secure CAV Networks Empowered by AI-Enabled Blockchain: Next Frontier for Intelligent Safe-Driving Assessment
Figure 3 for Smart and Secure CAV Networks Empowered by AI-Enabled Blockchain: Next Frontier for Intelligent Safe-Driving Assessment
Figure 4 for Smart and Secure CAV Networks Empowered by AI-Enabled Blockchain: Next Frontier for Intelligent Safe-Driving Assessment
* 8 pages, 4 figures, 1 table, this paper has been submitted to IEEE Wireless Communications Magazine and is still awaiting the review result 
  Access Paper or Ask Questions