Xinshuo Weng

Carnegie Mellon University
0000-0002-7894-4381
http://www.xinshuoweng.com/
Publications36
h-index11
Citations528
Highly Influential Citations63
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • K. Kitani
  • 53 Publications • 1,124 Citations
  • Kris M. Kitani
  • 123 Publications • 2,986 Citations
  • R. Urtasun
  • 272 Publications • 29,850 Citations
  • Andrew Zisserman
  • 795 Publications • 175,381 Citations
  • Publications
  • Influence
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
TLDR
In this paper, we present supervision-by-registration, an unsupervised approach to improve the precision of facial landmark detectors on both images and video. Expand
  • 126
  • 18
  • PDF
A Baseline for 3D Multi-Object Tracking
TLDR
We use an off-the-shelf 3D object detector to obtain oriented 3D bounding boxes from LiDAR point cloud. Expand
  • 48
  • 13
  • PDF
Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud
Monocular 3D scene understanding tasks, such as object size estimation, heading angle estimation and 3D localization, is challenging. Successful modern-day methods for 3D scene understanding require… Expand
  • 74
  • 8
  • PDF
3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
TLDR
We proposed an accurate, simple and real-time system for online 3D MOT. Expand
  • 42
  • 8
  • PDF
GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking With 2D-3D Multi-Feature Learning
TLDR
We propose two techniques to improve the discriminative feature learning for MOT: (1) instead of obtaining features for each object independently, we propose a novel feature interaction mechanism by introducing the Graph Neural Network. Expand
  • 25
  • 3
  • PDF
Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading
TLDR
We focus on the word-level visual lipreading, which requires recognizing the word being spoken, given only the video but not the audio. Expand
  • 17
  • 2
  • PDF
Joint Detection and Multi-Object Tracking with Graph Neural Networks
TLDR
We propose a new approach for joint MOT based on Graph Neural Networks (GNNs). Expand
  • 13
  • 2
  • PDF
GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning
TLDR
We propose two techniques to improve the discriminative feature learning for MOT: (1) instead of obtaining features for each object independently, we propose a novel feature interaction mechanism by introducing the Graph Neural Network. Expand
  • 8
  • 2
  • PDF
Deep Reinforcement Learning for Autonomous Driving
TLDR
Reinforcement learning has steadily improved and outperform human in lots of traditional games since the resurgence of deep neural network. Expand
  • 47
  • 1
  • PDF
Forecasting Time-to-Collision from Monocular Video: Feasibility, Dataset, and Challenges
TLDR
We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. Expand
  • 13
  • 1
  • PDF
...
1
2
3
4
...