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 Xiangyu Chen

Modeling and Measurements for Multi-path Mitigation with Reconfigurable Intelligent Surfaces


Sep 24, 2021
Ruya Zhou, Xiangyu Chen, Wankai Tang, Xiao Li, Shi Jin, Ertugrul Basar, Qiang Cheng, Tie Jun Cui

* An RIS has been utilized in modeling and measurements for multi-path mitigation 

  Access Paper or Ask Questions

Audio-Visual Transformer Based Crowd Counting


Sep 04, 2021
Usman Sajid, Xiangyu Chen, Hasan Sajid, Taejoon Kim, Guanghui Wang


  Access Paper or Ask Questions

A New Journey from SDRTV to HDRTV


Aug 18, 2021
Xiangyu Chen, Zhengwen Zhang, Jimmy S. Ren, Lynhoo Tian, Yu Qiao, Chao Dong

* Accepted to ICCV 

  Access Paper or Ask Questions

Design and Implementation of MIMO Transmission Based on Dual-Polarized Reconfigurable Intelligent Surface


Jul 02, 2021
Xiangyu Chen, Jun Chen Ke, Wankai Tang, Ming Zheng Chen, Jun Yan Dai, Ertugrul Basar, Shi Jin, Qiang Cheng, Tie Jun Cui

* This work has been accepted by IEEE WCL 

  Access Paper or Ask Questions

HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization


Jun 19, 2021
Xiangyu Chen, Yihao Liu, Zhengwen Zhang, Yu Qiao, Chao Dong


  Access Paper or Ask Questions

Improving the List Decoding Version of the Cyclically Equivariant Neural Decoder


Jun 15, 2021
Xiangyu Chen, Min Ye

* Code available at https://github.com/improvedlistdecoder/code 

  Access Paper or Ask Questions

Cyclically Equivariant Neural Decoders for Cyclic Codes


May 12, 2021
Xiangyu Chen, Min Ye

* Accepted for long presentation at ICML 2021. Code available at https://github.com/cyclicallyneuraldecoder/CyclicallyEquivariantNeuralDecoders 

  Access Paper or Ask Questions

Few-Shot Learning by Integrating Spatial and Frequency Representation


May 11, 2021
Xiangyu Chen, Guanghui Wang


  Access Paper or Ask Questions

Very Lightweight Photo Retouching Network with Conditional Sequential Modulation


Apr 13, 2021
Yihao Liu, Jingwen He, Xiangyu Chen, Zhengwen Zhang, Hengyuan Zhao, Chao Dong, Yu Qiao

* Extended version of CSRNet (ECCV2020). arXiv admin note: substantial text overlap with arXiv:2009.10390 

  Access Paper or Ask Questions

Low-Precision Reinforcement Learning


Feb 26, 2021
Johan Bjorck, Xiangyu Chen, Christopher De Sa, Carla P. Gomes, Kilian Q. Weinberger


  Access Paper or Ask Questions

Path Loss Modeling and Measurements for Reconfigurable Intelligent Surfaces in the Millimeter-Wave Frequency Band


Jan 21, 2021
Wankai Tang, Xiangyu Chen, Ming Zheng Chen, Jun Yan Dai, Yu Han, Marco Di Renzo, Shi Jin, Qiang Cheng, Tie Jun Cui

* We introduce model refinements to our previously proposed free-space path loss model for RISs in order to make it simpler, more applicable, and easier to use. We report the world's first measurement campaign to characterize the path loss for RIS-assisted mmWave wireless communications 

  Access Paper or Ask Questions

Robotic grasp detection using a novel two-stage approach


Nov 28, 2020
Zhe Chu, Mengkai Hu, Xiangyu Chen


  Access Paper or Ask Questions

Train in Germany, Test in The USA: Making 3D Object Detectors Generalize


May 17, 2020
Yan Wang, Xiangyu Chen, Yurong You, Li Erran, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger, Wei-Lun Chao

* Accepted to 2020 Conference on Computer Vision and Pattern Recognition (CVPR 2020) 

  Access Paper or Ask Questions

Transferable Active Grasping and Real Embodied Dataset


Apr 28, 2020
Xiangyu Chen, Zelin Ye, Jiankai Sun, Yuda Fan, Fang Hu, Chenxi Wang, Cewu Lu


  Access Paper or Ask Questions

Combating noisy labels by agreement: A joint training method with co-regularization


Mar 06, 2020
Hongxin Wei, Lei Feng, Xiangyu Chen, Bo An

* Accepted by CVPR 2020; Code is available at: https://github.com/hongxin001/JoCoR. arXiv admin note: text overlap with arXiv:1901.04215 by other authors 

  Access Paper or Ask Questions

The Cross-Modality Disparity Problem in Multispectral Pedestrian Detection


Jan 09, 2019
Lu Zhang, Zhiyong Liu, Xiangyu Chen, Xu Yang

* 10 pages, 8 figures, 4 tables 

  Access Paper or Ask Questions