Search Results for author: Hsu-kuang Chiu

Found 8 papers, 4 papers with code

Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter

2 code implementations26 Sep 2023 Hsu-kuang Chiu, Chien-Yi Wang, Min-Hung Chen, Stephen F. Smith

However, their proposed methods mainly use cooperative detection results as input to a standard single-sensor Kalman Filter-based tracking algorithm.

3D Multi-Object Tracking Autonomous Driving

Collision Avoidance Detour for Multi-Agent Trajectory Forecasting

no code implementations20 Jun 2023 Hsu-kuang Chiu, Stephen F. Smith

We present our approach, Collision Avoidance Detour (CAD), which won the 3rd place award in the 2023 Waymo Open Dataset Challenge - Sim Agents, held at the 2023 CVPR Workshop on Autonomous Driving.

Autonomous Driving Collision Avoidance +3

Selective Communication for Cooperative Perception in End-to-End Autonomous Driving

no code implementations26 May 2023 Hsu-kuang Chiu, Stephen F. Smith

The reliability of current autonomous driving systems is often jeopardized in situations when the vehicle's field-of-view is limited by nearby occluding objects.

Autonomous Driving Multi-Agent Path Finding

Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Driving

1 code implementation26 Dec 2020 Hsu-kuang Chiu, Jie Li, Rares Ambrus, Jeannette Bohg

Second, we propose to learn a metric that combines the Mahalanobis and feature distances when comparing a track and a new detection in data association.

Autonomous Driving Management +5

Imitation Learning for Human Pose Prediction

no code implementations ICCV 2019 Borui Wang, Ehsan Adeli, Hsu-kuang Chiu, De-An Huang, Juan Carlos Niebles

Modeling and prediction of human motion dynamics has long been a challenging problem in computer vision, and most existing methods rely on the end-to-end supervised training of various architectures of recurrent neural networks.

Ranked #2 on Human Pose Forecasting on Human3.6M (MAR, walking, 1,000ms metric)

Human Pose Forecasting Imitation Learning +3

Segmenting the Future

no code implementations24 Apr 2019 Hsu-kuang Chiu, Ehsan Adeli, Juan Carlos Niebles

While prior work attempts to predict future video pixels, anticipate activities or forecast future scene semantic segments from segmentation of the preceding frames, methods that predict future semantic segmentation solely from the previous frame RGB data in a single end-to-end trainable model do not exist.

Autonomous Driving Decision Making +4

Action-Agnostic Human Pose Forecasting

1 code implementation23 Oct 2018 Hsu-kuang Chiu, Ehsan Adeli, Borui Wang, De-An Huang, Juan Carlos Niebles

In this paper, we propose a new action-agnostic method for short- and long-term human pose forecasting.

Ranked #5 on Human Pose Forecasting on Human3.6M (MAR, walking, 1,000ms metric)

Human Dynamics Human Pose Forecasting

Cannot find the paper you are looking for? You can Submit a new open access paper.