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 Cunjun Yu

Balanced Activation for Long-tailed Visual Recognition

Aug 24, 2020
Jiawei Ren, Cunjun Yu, Zhongang Cai, Haiyu Zhao

* LVIS Challenge Workshop at ECCV 2020 Spotlight. arXiv admin note: substantial text overlap with arXiv:2007.10740 

  Access Paper or Ask Questions

Leveraging Localization for Multi-camera Association

Aug 07, 2020
Zhongang Cai, Cunjun Yu, Junzhe Zhang, Jiawei Ren, Haiyu Zhao

  Access Paper or Ask Questions

MessyTable: Instance Association in Multiple Camera Views

Jul 29, 2020
Zhongang Cai, Junzhe Zhang, Daxuan Ren, Cunjun Yu, Haiyu Zhao, Shuai Yi, Chai Kiat Yeo, Chen Change Loy

* Accepted in ECCV 2020 

  Access Paper or Ask Questions

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Jul 21, 2020
Jiawei Ren, Cunjun Yu, Shunan Sheng, Xiao Ma, Haiyu Zhao, Shuai Yi, Hongsheng Li

  Access Paper or Ask Questions

Leveraging Temporal Information for 3D Detection and Domain Adaptation

Jun 30, 2020
Cunjun Yu, Zhongang Cai, Daxuan Ren, Haiyu Zhao

  Access Paper or Ask Questions

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

May 18, 2020
Cunjun Yu, Xiao Ma, Jiawei Ren, Haiyu Zhao, Shuai Yi

* 19 pages, 8 figures, 2 tables 

  Access Paper or Ask Questions

Learning an Efficient Network for Large-Scale Hierarchical Object Detection with Data Imbalance: 3rd Place Solution to Open Images Challenge 2019

Oct 26, 2019
Xingyuan Bu, Junran Peng, Changbao Wang, Cunjun Yu, Guoliang Cao

* 6 pages, 3 figures, ICCV 2019 Open Images Workshop 

  Access Paper or Ask Questions

Siamese Convolutional Neural Network for Sub-millimeter-accurate Camera Pose Estimation and Visual Servoing

Mar 12, 2019
Cunjun Yu, Zhongang Cai, Hung Pham, Quang-Cuong Pham

  Access Paper or Ask Questions

3D Convolution on RGB-D Point Clouds for Accurate Model-free Object Pose Estimation

Dec 29, 2018
Zhongang Cai, Cunjun Yu, Quang-Cuong Pham

  Access Paper or Ask Questions