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 Junjie Yan

Junjie Yan

Inter-class Discrepancy Alignment for Face Recognition


Mar 02, 2021
Jiaheng Liu, Yudong Wu, Yichao Wu, Zhenmao Li, Chen Ken, Ding Liang, Junjie Yan


  Access Paper or Ask Questions

Inception Convolution with Efficient Dilation Search


Dec 25, 2020
Jie Liu, Chuming Li, Feng Liang, Chen Lin, Ming Sun, Junjie Yan, Wanli Ouyang, Dong Xu

Figure 1 for Inception Convolution with Efficient Dilation Search
Figure 2 for Inception Convolution with Efficient Dilation Search
Figure 3 for Inception Convolution with Efficient Dilation Search
Figure 4 for Inception Convolution with Efficient Dilation Search

  Access Paper or Ask Questions

DETR for Pedestrian Detection


Dec 12, 2020
Matthieu Lin, Chuming Li, Xingyuan Bu, Ming Sun, Chen Lin, Junjie Yan, Wanli Ouyang, Zhidong Deng

Figure 1 for DETR for Pedestrian Detection
Figure 2 for DETR for Pedestrian Detection
Figure 3 for DETR for Pedestrian Detection
Figure 4 for DETR for Pedestrian Detection

  Access Paper or Ask Questions

Context-Aware Graph Convolution Network for Target Re-identification


Dec 09, 2020
Deyi Ji, Haoran Wang, Hanzhe Hu, Weihao Gan, Wei Wu, Junjie Yan

Figure 1 for Context-Aware Graph Convolution Network for Target Re-identification
Figure 2 for Context-Aware Graph Convolution Network for Target Re-identification
Figure 3 for Context-Aware Graph Convolution Network for Target Re-identification
Figure 4 for Context-Aware Graph Convolution Network for Target Re-identification
* Accepted by AAAI2021 
  Access Paper or Ask Questions

PV-NAS: Practical Neural Architecture Search for Video Recognition


Nov 03, 2020
Zihao Wang, Chen Lin, Lu Sheng, Junjie Yan, Jing Shao

Figure 1 for PV-NAS: Practical Neural Architecture Search for Video Recognition
Figure 2 for PV-NAS: Practical Neural Architecture Search for Video Recognition
Figure 3 for PV-NAS: Practical Neural Architecture Search for Video Recognition
Figure 4 for PV-NAS: Practical Neural Architecture Search for Video Recognition

  Access Paper or Ask Questions

Improving Auto-Augment via Augmentation-Wise Weight Sharing


Oct 22, 2020
Keyu Tian, Chen Lin, Ming Sun, Luping Zhou, Junjie Yan, Wanli Ouyang

Figure 1 for Improving Auto-Augment via Augmentation-Wise Weight Sharing
Figure 2 for Improving Auto-Augment via Augmentation-Wise Weight Sharing
Figure 3 for Improving Auto-Augment via Augmentation-Wise Weight Sharing
Figure 4 for Improving Auto-Augment via Augmentation-Wise Weight Sharing
* Accepted to NeurIPS 2020 (Poster) 
  Access Paper or Ask Questions

Adaptive Gradient Method with Resilience and Momentum


Oct 21, 2020
Jie Liu, Chen Lin, Chuming Li, Lu Sheng, Ming Sun, Junjie Yan, Wanli Ouyang

Figure 1 for Adaptive Gradient Method with Resilience and Momentum
Figure 2 for Adaptive Gradient Method with Resilience and Momentum
Figure 3 for Adaptive Gradient Method with Resilience and Momentum
Figure 4 for Adaptive Gradient Method with Resilience and Momentum

  Access Paper or Ask Questions

Once Quantized for All: Progressively Searching for Quantized Efficient Models


Oct 09, 2020
Mingzhu Shen, Feng Liang, Chuming Li, Chen Lin, Ming Sun, Junjie Yan, Wanli Ouyang

Figure 1 for Once Quantized for All: Progressively Searching for Quantized Efficient Models
Figure 2 for Once Quantized for All: Progressively Searching for Quantized Efficient Models
Figure 3 for Once Quantized for All: Progressively Searching for Quantized Efficient Models
Figure 4 for Once Quantized for All: Progressively Searching for Quantized Efficient Models
* The first two authors contributed equally 
  Access Paper or Ask Questions

Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks


Oct 02, 2020
Kun Yuan, Quanquan Li, Dapeng Chen, Aojun Zhou, Junjie Yan

Figure 1 for Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
Figure 2 for Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
Figure 3 for Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
Figure 4 for Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
* 13 pages, 3 figures, 6 tables 
  Access Paper or Ask Questions

MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection


Sep 24, 2020
Xin Lu, Quanquan Li, Buyu Li, Junjie Yan

Figure 1 for MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection
Figure 2 for MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection
Figure 3 for MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection
Figure 4 for MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection
* ECCV 2020 
  Access Paper or Ask Questions

Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition


Sep 15, 2020
Haisheng Su, Jing Su, Dongliang Wang, Weihao Gan, Wei Wu, Mengmeng Wang, Junjie Yan, Yu Qiao

Figure 1 for Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition
Figure 2 for Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition
Figure 3 for Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition
Figure 4 for Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition
* Submmited to AAAI21 
  Access Paper or Ask Questions

BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation


Sep 15, 2020
Haisheng Su, Weihao Gan, Wei Wu, Junjie Yan, Yu Qiao

Figure 1 for BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
Figure 2 for BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
Figure 3 for BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
Figure 4 for BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
* Submitted to AAAI21. arXiv admin note: substantial text overlap with arXiv:2007.09883 
  Access Paper or Ask Questions

Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020


Aug 26, 2020
Haisheng Su, Jinyuan Feng, Hao Shao, Zhenyu Jiang, Manyuan Zhang, Wei Wu, Yu Liu, Hongsheng Li, Junjie Yan

Figure 1 for Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020
Figure 2 for Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020
Figure 3 for Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020
Figure 4 for Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020
* Submitted to CVPR workshop of ActivityNet Challenge 2020 
  Access Paper or Ask Questions

Learning Connectivity of Neural Networks from a Topological Perspective


Aug 19, 2020
Kun Yuan, Quanquan Li, Jing Shao, Junjie Yan

Figure 1 for Learning Connectivity of Neural Networks from a Topological Perspective
Figure 2 for Learning Connectivity of Neural Networks from a Topological Perspective
Figure 3 for Learning Connectivity of Neural Networks from a Topological Perspective
Figure 4 for Learning Connectivity of Neural Networks from a Topological Perspective
* 17 pages, 5 figures, to be published in ECCV2020 
  Access Paper or Ask Questions

CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations


Aug 01, 2020
Yuanhan Zhang, Zhenfei Yin, Yidong Li, Guojun Yin, Junjie Yan, Jing Shao, Ziwei Liu

Figure 1 for CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations
Figure 2 for CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations
Figure 3 for CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations
Figure 4 for CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations
* To appear in ECCV 2020. Dataset is available at: https://github.com/Davidzhangyuanhan/CelebA-Spoof 
  Access Paper or Ask Questions

Class-wise Dynamic Graph Convolution for Semantic Segmentation


Jul 19, 2020
Hanzhe Hu, Deyi Ji, Weihao Gan, Shuai Bai, Wei Wu, Junjie Yan

Figure 1 for Class-wise Dynamic Graph Convolution for Semantic Segmentation
Figure 2 for Class-wise Dynamic Graph Convolution for Semantic Segmentation
Figure 3 for Class-wise Dynamic Graph Convolution for Semantic Segmentation
Figure 4 for Class-wise Dynamic Graph Convolution for Semantic Segmentation
* Accepted by ECCV2020 
  Access Paper or Ask Questions

Powering One-shot Topological NAS with Stabilized Share-parameter Proxy


May 21, 2020
Ronghao Guo, Chen Lin, Chuming Li, Keyu Tian, Ming Sun, Lu Sheng, Junjie Yan

Figure 1 for Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
Figure 2 for Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
Figure 3 for Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
Figure 4 for Powering One-shot Topological NAS with Stabilized Share-parameter Proxy

  Access Paper or Ask Questions

Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels


May 18, 2020
Junran Peng, Xingyuan Bu, Ming Sun, Zhaoxiang Zhang, Tieniu Tan, Junjie Yan

Figure 1 for Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels
Figure 2 for Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels
Figure 3 for Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels
Figure 4 for Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels
* CVPR2020 oral. The first two authors contribute equally 
  Access Paper or Ask Questions

COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification


May 16, 2020
Shijie Yu, Shihua Li, Dapeng Chen, Rui Zhao, Junjie Yan, Yu Qiao

Figure 1 for COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
Figure 2 for COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
Figure 3 for COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
Figure 4 for COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
* Accepted by CVPR2020 
  Access Paper or Ask Questions

DMCP: Differentiable Markov Channel Pruning for Neural Networks


May 08, 2020
Shaopeng Guo, Yujie Wang, Quanquan Li, Junjie Yan

Figure 1 for DMCP: Differentiable Markov Channel Pruning for Neural Networks
Figure 2 for DMCP: Differentiable Markov Channel Pruning for Neural Networks
Figure 3 for DMCP: Differentiable Markov Channel Pruning for Neural Networks
Figure 4 for DMCP: Differentiable Markov Channel Pruning for Neural Networks
* CVPR2020 Oral. Code has been released at https://github.com/zx55/dmcp 
  Access Paper or Ask Questions

Equalization Loss for Long-Tailed Object Recognition


Apr 14, 2020
Jingru Tan, Changbao Wang, Buyu Li, Quanquan Li, Wanli Ouyang, Changqing Yin, Junjie Yan

Figure 1 for Equalization Loss for Long-Tailed Object Recognition
Figure 2 for Equalization Loss for Long-Tailed Object Recognition
Figure 3 for Equalization Loss for Long-Tailed Object Recognition
Figure 4 for Equalization Loss for Long-Tailed Object Recognition
* CVPR 2020. Winner of LVIS Challenge 2019. Code has been available at https: //github.com/tztztztztz/eql.detectron2 
  Access Paper or Ask Questions

1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation


Mar 17, 2020
Yu Liu, Guanglu Song, Yuhang Zang, Yan Gao, Enze Xie, Junjie Yan, Chen Change Loy, Xiaogang Wang

Figure 1 for 1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
Figure 2 for 1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
Figure 3 for 1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
Figure 4 for 1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation

  Access Paper or Ask Questions

Top-1 Solution of Multi-Moments in Time Challenge 2019


Mar 13, 2020
Manyuan Zhang, Hao Shao, Guanglu Song, Yu Liu, Junjie Yan

Figure 1 for Top-1 Solution of Multi-Moments in Time Challenge 2019
Figure 2 for Top-1 Solution of Multi-Moments in Time Challenge 2019
Figure 3 for Top-1 Solution of Multi-Moments in Time Challenge 2019
Figure 4 for Top-1 Solution of Multi-Moments in Time Challenge 2019

  Access Paper or Ask Questions

Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization


Jan 19, 2020
Junjie Yan, Ruosi Wan, Xiangyu Zhang, Wei Zhang, Yichen Wei, Jian Sun

Figure 1 for Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
Figure 2 for Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
Figure 3 for Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
Figure 4 for Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
* Published in ICLR2020; code: https://github.com/megvii-model/MABN 
  Access Paper or Ask Questions