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 Jian Sun

Jian Sun

NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results


Jun 07, 2021
Goutam Bhat, Martin Danelljan, Radu Timofte, Kazutoshi Akita, Wooyeong Cho, Haoqiang Fan, Lanpeng Jia, Daeshik Kim, Bruno Lecouat, Youwei Li, Shuaicheng Liu, Ziluan Liu, Ziwei Luo, Takahiro Maeda, Julien Mairal, Christian Micheloni, Xuan Mo, Takeru Oba, Pavel Ostyakov, Jean Ponce, Sanghyeok Son, Jian Sun, Norimichi Ukita, Rao Muhammad Umer, Youliang Yan, Lei Yu, Magauiya Zhussip, Xueyi Zou

Figure 1 for NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
Figure 2 for NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
Figure 3 for NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
Figure 4 for NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
* NTIRE 2021 Burst Super-Resolution challenge report 
  Access Paper or Ask Questions

Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking


Jun 01, 2021
Yinpei Dai, Hangyu Li, Yongbin Li, Jian Sun, Fei Huang, Luo Si, Xiaodan Zhu

Figure 1 for Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking
Figure 2 for Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking
Figure 3 for Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking
Figure 4 for Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking
* 7 pages, 2 figures, accepted to ACL21 
  Access Paper or Ask Questions

ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging


May 22, 2021
Zhen Liu, Wenjie Lin, Xinpeng Li, Qing Rao, Ting Jiang, Mingyan Han, Haoqiang Fan, Jian Sun, Shuaicheng Liu

Figure 1 for ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging
Figure 2 for ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging
Figure 3 for ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging
Figure 4 for ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging
* Accepted by CVPRW 2021 
  Access Paper or Ask Questions

Generalized Few-Shot Object Detection without Forgetting


May 20, 2021
Zhibo Fan, Yuchen Ma, Zeming Li, Jian Sun

Figure 1 for Generalized Few-Shot Object Detection without Forgetting
Figure 2 for Generalized Few-Shot Object Detection without Forgetting
Figure 3 for Generalized Few-Shot Object Detection without Forgetting
Figure 4 for Generalized Few-Shot Object Detection without Forgetting
* Accepted by CVPR 2021 
  Access Paper or Ask Questions

Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report


May 17, 2021
Andrey Ignatov, Kim Byeoung-su, Radu Timofte, Angeline Pouget, Fenglong Song, Cheng Li, Shuai Xiao, Zhongqian Fu, Matteo Maggioni, Yibin Huang, Shen Cheng, Xin Lu, Yifeng Zhou, Liangyu Chen, Donghao Liu, Xiangyu Zhang, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Minsu Kwon, Myungje Lee, Jaeyoon Yoo, Changbeom Kang, Shinjo Wang, Bin Huang, Tianbao Zhou, Shuai Liu, Lei Lei, Chaoyu Feng, Liguang Huang, Zhikun Lei, Feifei Chen

Figure 1 for Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
Figure 2 for Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
Figure 3 for Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
Figure 4 for Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
* Mobile AI 2021 Workshop and Challenges: https://ai-benchmark.com/workshops/mai/2021/. arXiv admin note: substantial text overlap with arXiv:2105.07809, arXiv:2105.07825 
  Access Paper or Ask Questions

Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion


Apr 27, 2021
Guanglin Niu, Yang Li, Chengguang Tang, Ruiying Geng, Jian Dai, Qiao Liu, Hao Wang, Jian Sun, Fei Huang, Luo Si

Figure 1 for Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
Figure 2 for Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
Figure 3 for Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
Figure 4 for Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
* The full version of a paper accepted to SIGIR 2021 
  Access Paper or Ask Questions

Points as Queries: Weakly Semi-supervised Object Detection by Points


Apr 15, 2021
Liangyu Chen, Tong Yang, Xiangyu Zhang, Wei Zhang, Jian Sun

Figure 1 for Points as Queries: Weakly Semi-supervised Object Detection by Points
Figure 2 for Points as Queries: Weakly Semi-supervised Object Detection by Points
Figure 3 for Points as Queries: Weakly Semi-supervised Object Detection by Points
Figure 4 for Points as Queries: Weakly Semi-supervised Object Detection by Points

  Access Paper or Ask Questions

IQDet: Instance-wise Quality Distribution Sampling for Object Detection


Apr 14, 2021
Yuchen Ma, Songtao Liu, Zeming Li, Jian Sun

Figure 1 for IQDet: Instance-wise Quality Distribution Sampling for Object Detection
Figure 2 for IQDet: Instance-wise Quality Distribution Sampling for Object Detection
Figure 3 for IQDet: Instance-wise Quality Distribution Sampling for Object Detection
Figure 4 for IQDet: Instance-wise Quality Distribution Sampling for Object Detection
* Accepted by CVPR 2021 
  Access Paper or Ask Questions

Learning to Jointly Deblur, Demosaick and Denoise Raw Images


Apr 13, 2021
Thomas Eboli, Jian Sun, Jean Ponce

Figure 1 for Learning to Jointly Deblur, Demosaick and Denoise Raw Images
Figure 2 for Learning to Jointly Deblur, Demosaick and Denoise Raw Images
Figure 3 for Learning to Jointly Deblur, Demosaick and Denoise Raw Images
Figure 4 for Learning to Jointly Deblur, Demosaick and Denoise Raw Images

  Access Paper or Ask Questions

Distribution Alignment: A Unified Framework for Long-tail Visual Recognition


Mar 30, 2021
Songyang Zhang, Zeming Li, Shipeng Yan, Xuming He, Jian Sun

Figure 1 for Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
Figure 2 for Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
Figure 3 for Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
Figure 4 for Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
* Accepted by CVPR 2021 
  Access Paper or Ask Questions

OTA: Optimal Transport Assignment for Object Detection


Mar 26, 2021
Zheng Ge, Songtao Liu, Zeming Li, Osamu Yoshie, Jian Sun

Figure 1 for OTA: Optimal Transport Assignment for Object Detection
Figure 2 for OTA: Optimal Transport Assignment for Object Detection
Figure 3 for OTA: Optimal Transport Assignment for Object Detection
Figure 4 for OTA: Optimal Transport Assignment for Object Detection
* CVPR2021 
  Access Paper or Ask Questions

Training Networks in Null Space of Feature Covariance for Continual Learning


Mar 17, 2021
Shipeng Wang, Xiaorong Li, Jian Sun, Zongben Xu

Figure 1 for Training Networks in Null Space of Feature Covariance for Continual Learning
Figure 2 for Training Networks in Null Space of Feature Covariance for Continual Learning
Figure 3 for Training Networks in Null Space of Feature Covariance for Continual Learning
Figure 4 for Training Networks in Null Space of Feature Covariance for Continual Learning
* Accepted as an oral of CVPR2021 
  Access Paper or Ask Questions

You Only Look One-level Feature


Mar 17, 2021
Qiang Chen, Yingming Wang, Tong Yang, Xiangyu Zhang, Jian Cheng, Jian Sun

Figure 1 for You Only Look One-level Feature
Figure 2 for You Only Look One-level Feature
Figure 3 for You Only Look One-level Feature
Figure 4 for You Only Look One-level Feature
* Accepted by CVPR2021. We provide more details and add additional comparison with YOLOv4 in this version 
  Access Paper or Ask Questions

Training Networks in Null Space of Covariance for Continual Learning


Mar 12, 2021
Shipeng Wang, Xiaorong Li, Jian Sun, Zongben Xu

Figure 1 for Training Networks in Null Space of Covariance for Continual Learning
Figure 2 for Training Networks in Null Space of Covariance for Continual Learning
Figure 3 for Training Networks in Null Space of Covariance for Continual Learning
Figure 4 for Training Networks in Null Space of Covariance for Continual Learning

  Access Paper or Ask Questions

End-to-End Human Object Interaction Detection with HOI Transformer


Mar 08, 2021
Cheng Zou, Bohan Wang, Yue Hu, Junqi Liu, Qian Wu, Yu Zhao, Boxun Li, Chenguang Zhang, Chi Zhang, Yichen Wei, Jian Sun

Figure 1 for End-to-End Human Object Interaction Detection with HOI Transformer
Figure 2 for End-to-End Human Object Interaction Detection with HOI Transformer
Figure 3 for End-to-End Human Object Interaction Detection with HOI Transformer
Figure 4 for End-to-End Human Object Interaction Detection with HOI Transformer
* Accepted to CVPR2021 
  Access Paper or Ask Questions

Improving Text-to-SQL with Schema Dependency Learning


Mar 07, 2021
Binyuan Hui, Xiang Shi, Ruiying Geng, Binhua Li, Yongbin Li, Jian Sun, Xiaodan Zhu

Figure 1 for Improving Text-to-SQL with Schema Dependency Learning
Figure 2 for Improving Text-to-SQL with Schema Dependency Learning
Figure 3 for Improving Text-to-SQL with Schema Dependency Learning
Figure 4 for Improving Text-to-SQL with Schema Dependency Learning

  Access Paper or Ask Questions

FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation


Mar 03, 2021
Yisheng He, Haibin Huang, Haoqiang Fan, Qifeng Chen, Jian Sun

Figure 1 for FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation
Figure 2 for FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation
Figure 3 for FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation
Figure 4 for FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation
* Accepted to CVPR2021 
  Access Paper or Ask Questions

Using Long Short-Term Memory (LSTM) and Internet of Things (IoT) for localized surface temperature forecasting in an urban environment


Feb 04, 2021
Manzhu Yu, Fangcao Xu, Weiming Hu, Jian Sun, Guido Cervone

Figure 1 for Using Long Short-Term Memory (LSTM) and Internet of Things (IoT) for localized surface temperature forecasting in an urban environment
Figure 2 for Using Long Short-Term Memory (LSTM) and Internet of Things (IoT) for localized surface temperature forecasting in an urban environment
Figure 3 for Using Long Short-Term Memory (LSTM) and Internet of Things (IoT) for localized surface temperature forecasting in an urban environment
Figure 4 for Using Long Short-Term Memory (LSTM) and Internet of Things (IoT) for localized surface temperature forecasting in an urban environment

  Access Paper or Ask Questions

Neural Architecture Search with Random Labels


Jan 28, 2021
Xuanyang Zhang, Pengfei Hou, Xiangyu Zhang, Jian Sun

Figure 1 for Neural Architecture Search with Random Labels
Figure 2 for Neural Architecture Search with Random Labels
Figure 3 for Neural Architecture Search with Random Labels
Figure 4 for Neural Architecture Search with Random Labels
* Tech report 
  Access Paper or Ask Questions

Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning


Jan 19, 2021
Zeming Li, Songtao Liu, Jian Sun

Figure 1 for Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning
Figure 2 for Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning
Figure 3 for Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning
Figure 4 for Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning
* 11 pages, Tech report 
  Access Paper or Ask Questions

RepVGG: Making VGG-style ConvNets Great Again


Jan 11, 2021
Xiaohan Ding, Xiangyu Zhang, Ningning Ma, Jungong Han, Guiguang Ding, Jian Sun

Figure 1 for RepVGG: Making VGG-style ConvNets Great Again
Figure 2 for RepVGG: Making VGG-style ConvNets Great Again
Figure 3 for RepVGG: Making VGG-style ConvNets Great Again
Figure 4 for RepVGG: Making VGG-style ConvNets Great Again
* The code and trained models are available at https://github.com/megvii-model/RepVGG 
  Access Paper or Ask Questions

Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing


Jan 05, 2021
Binyuan Hui, Ruiying Geng, Qiyu Ren, Binhua Li, Yongbin Li, Jian Sun, Fei Huang, Luo Si, Pengfei Zhu, Xiaodan Zhu

Figure 1 for Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
Figure 2 for Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
Figure 3 for Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
Figure 4 for Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
* Accepted by AAAI 2021 
  Access Paper or Ask Questions

Implicit Feature Pyramid Network for Object Detection


Dec 25, 2020
Tiancai Wang, Xiangyu Zhang, Jian Sun

Figure 1 for Implicit Feature Pyramid Network for Object Detection
Figure 2 for Implicit Feature Pyramid Network for Object Detection
Figure 3 for Implicit Feature Pyramid Network for Object Detection
Figure 4 for Implicit Feature Pyramid Network for Object Detection
* Tech report 
  Access Paper or Ask Questions

Efficient Human Pose Estimation by Learning Deeply Aggregated Representations


Dec 15, 2020
Zhengxiong Luo, Zhicheng Wang, Yuanhao Cai, Guanan Wang, Yan Huang, Liang Wang, Erjin Zhou, Tieniu Tan, Jian Sun

Figure 1 for Efficient Human Pose Estimation by Learning Deeply Aggregated Representations
Figure 2 for Efficient Human Pose Estimation by Learning Deeply Aggregated Representations
Figure 3 for Efficient Human Pose Estimation by Learning Deeply Aggregated Representations
Figure 4 for Efficient Human Pose Estimation by Learning Deeply Aggregated Representations

  Access Paper or Ask Questions

Self-EMD: Self-Supervised Object Detection without ImageNet


Dec 08, 2020
Songtao Liu, Zeming Li, Jian Sun

Figure 1 for Self-EMD: Self-Supervised Object Detection without ImageNet
Figure 2 for Self-EMD: Self-Supervised Object Detection without ImageNet
Figure 3 for Self-EMD: Self-Supervised Object Detection without ImageNet
Figure 4 for Self-EMD: Self-Supervised Object Detection without ImageNet

  Access Paper or Ask Questions

End-to-End Object Detection with Fully Convolutional Network


Dec 07, 2020
Jianfeng Wang, Lin Song, Zeming Li, Hongbin Sun, Jian Sun, Nanning Zheng

Figure 1 for End-to-End Object Detection with Fully Convolutional Network
Figure 2 for End-to-End Object Detection with Fully Convolutional Network
Figure 3 for End-to-End Object Detection with Fully Convolutional Network
Figure 4 for End-to-End Object Detection with Fully Convolutional Network

  Access Paper or Ask Questions

Fine-Grained Dynamic Head for Object Detection


Dec 07, 2020
Lin Song, Yanwei Li, Zhengkai Jiang, Zeming Li, Hongbin Sun, Jian Sun, Nanning Zheng

Figure 1 for Fine-Grained Dynamic Head for Object Detection
Figure 2 for Fine-Grained Dynamic Head for Object Detection
Figure 3 for Fine-Grained Dynamic Head for Object Detection
Figure 4 for Fine-Grained Dynamic Head for Object Detection
* Accepted by NeurIPS-2020 
  Access Paper or Ask Questions

Rethinking Learnable Tree Filter for Generic Feature Transform


Dec 07, 2020
Lin Song, Yanwei Li, Zhengkai Jiang, Zeming Li, Xiangyu Zhang, Hongbin Sun, Jian Sun, Nanning Zheng

Figure 1 for Rethinking Learnable Tree Filter for Generic Feature Transform
Figure 2 for Rethinking Learnable Tree Filter for Generic Feature Transform
Figure 3 for Rethinking Learnable Tree Filter for Generic Feature Transform
Figure 4 for Rethinking Learnable Tree Filter for Generic Feature Transform
* Accepted by NeurIPS-2020 
  Access Paper or Ask Questions