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 Xinshuo Weng

Wide-Baseline Multi-Camera Calibration using Person Re-Identification


Apr 17, 2021
Yan Xu, Yu-Jhe Li, Xinshuo Weng, Kris Kitani


  Access Paper or Ask Questions

AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting


Mar 25, 2021
Ye Yuan, Xinshuo Weng, Yanglan Ou, Kris Kitani

* Project page: https://www.ye-yuan.com/agentformer 

  Access Paper or Ask Questions

Supervision by Registration and Triangulation for Landmark Detection


Jan 25, 2021
Xuanyi Dong, Yi Yang, Shih-En Wei, Xinshuo Weng, Yaser Sheikh, Shoou-I Yu

* Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2020 

  Access Paper or Ask Questions

AutoSelect: Automatic and Dynamic Detection Selection for 3D Multi-Object Tracking


Dec 10, 2020
Xinshuo Weng, Kris Kitani


  Access Paper or Ask Questions

End-to-End 3D Multi-Object Tracking and Trajectory Forecasting


Aug 25, 2020
Xinshuo Weng, Ye Yuan, Kris Kitani

* Extended abstract. The first two authors contributed equally. Project website: http://www.xinshuoweng.com/projects/GNNTrkForecast. arXiv admin note: substantial text overlap with arXiv:2003.07847 

  Access Paper or Ask Questions

Graph Neural Networks for 3D Multi-Object Tracking


Aug 20, 2020
Xinshuo Weng, Yongxin Wang, Yunze Man, Kris Kitani

* ECCV 2020 workshop paper. Project website: http://www.xinshuoweng.com/projects/GNN3DMOT. arXiv admin note: substantial text overlap with arXiv:2006.07327 

  Access Paper or Ask Questions

AB3DMOT: A Baseline for 3D Multi-Object Tracking and New Evaluation Metrics


Aug 18, 2020
Xinshuo Weng, Jianren Wang, David Held, Kris Kitani

* Extended abstract that will be presented at ECCV 2020 Workshops. Project website: http://www.xinshuoweng.com/projects/AB3DMOT 

  Access Paper or Ask Questions

Joint Detection and Multi-Object Tracking with Graph Neural Networks


Jun 23, 2020
Yongxin Wang, Xinshuo Weng, Kris Kitani


  Access Paper or Ask Questions

When We First Met: Visual-Inertial Person Localization for Co-Robot Rendezvous


Jun 17, 2020
Xi Sun, Xinshuo Weng, Kris Kitani


  Access Paper or Ask Questions

GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning


Jun 12, 2020
Xinshuo Weng, Yongxin Wang, Yunze Man, Kris Kitani

* CVPR 2020. My website for all my research works: http://www.xinshuoweng.com/ 

  Access Paper or Ask Questions

Unsupervised Sequence Forecasting of 100,000 Points for Unsupervised Trajectory Forecasting


Mar 29, 2020
Xinshuo Weng, Jianren Wang, Sergey Levine, Kris Kitani, Nicholas Rhinehart

* Code will be available at https://github.com/xinshuoweng/SPCSF 

  Access Paper or Ask Questions

Sequential Forecasting of 100,000 Points


Mar 18, 2020
Xinshuo Weng, Jianren Wang, Sergey Levine, Kris Kitani, Nicholas Rhinehart

* Code will be available at https://github.com/xinshuoweng/SPCSF 

  Access Paper or Ask Questions

Joint 3D Tracking and Forecasting with Graph Neural Network and Diversity Sampling


Mar 17, 2020
Xinshuo Weng, Ye Yuan, Kris Kitani

* Code will be made available at https://github.com/xinshuoweng/GNNTrkForecast. The first two authors contributed equally to this work 

  Access Paper or Ask Questions

Learning Shape Representations for Clothing Variations in Person Re-Identification


Mar 16, 2020
Yu-Jhe Li, Zhengyi Luo, Xinshuo Weng, Kris M. Kitani

* 11 pages, 8 figures. In submission 

  Access Paper or Ask Questions

A Baseline for 3D Multi-Object Tracking


Aug 05, 2019
Xinshuo Weng, Kris Kitani

* fix typo 

  Access Paper or Ask Questions

Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading


May 04, 2019
Xinshuo Weng, Kris Kitani

* arXiv admin note: text overlap with arXiv:1903.09616 

  Access Paper or Ask Questions

Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud


Mar 31, 2019
Xinshuo Weng, Kris Kitani


  Access Paper or Ask Questions

On the Importance of Video Action Recognition for Visual Lipreading


Mar 22, 2019
Xinshuo Weng


  Access Paper or Ask Questions

Future Near-Collision Prediction from Monocular Video: Feasibility, Dataset, and Challenges


Mar 21, 2019
Aashi Manglik, Xinshuo Weng, Eshed Ohn-Bar, Kris M. Kitani

* 7 pages, 5 figures 

  Access Paper or Ask Questions

Deep Reinforcement Learning for Autonomous Driving


Mar 19, 2019
Sen Wang, Daoyuan Jia, Xinshuo Weng

* no time for further improvement 

  Access Paper or Ask Questions

CyLKs: Unsupervised Cycle Lucas-Kanade Network for Landmark Tracking


Nov 28, 2018
Xinshuo Weng, Wentao Han


  Access Paper or Ask Questions

Image Labeling with Markov Random Fields and Conditional Random Fields


Nov 28, 2018
Shangxuan Wu, Xinshuo Weng


  Access Paper or Ask Questions

GroundNet: Segmentation-Aware Monocular Ground Plane Estimation with Geometric Consistency


Nov 17, 2018
Yunze Man, Xinshuo Weng, Kris Kitani


  Access Paper or Ask Questions

Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors


Jul 04, 2018
Xuanyi Dong, Shoou-I Yu, Xinshuo Weng, Shih-En Wei, Yi Yang, Yaser Sheikh

* Minor modifications to the CVPR 2018 version (add missing references) 

  Access Paper or Ask Questions

Rotational Rectification Network: Enabling Pedestrian Detection for Mobile Vision


Sep 12, 2017
Xinshuo Weng, Shangxuan Wu, Fares Beainy, Kris Kitani


  Access Paper or Ask Questions

Visual Compiler: Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator


Dec 15, 2016
Namhoon Lee, Xinshuo Weng, Vishnu Naresh Boddeti, Yu Zhang, Fares Beainy, Kris Kitani, Takeo Kanade

* submitted to CVPR 2017 

  Access Paper or Ask Questions