Picture for Yu-Kai Huang

Yu-Kai Huang

BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction

Add code
May 27, 2024
Viaarxiv icon

QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Prediction

Add code
Jun 18, 2023
Figure 1 for QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Prediction
Figure 2 for QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Prediction
Figure 3 for QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Prediction
Figure 4 for QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Prediction
Viaarxiv icon

Multi-Stream Attention Learning for Monocular Vehicle Velocity and Inter-Vehicle Distance Estimation

Add code
Oct 22, 2021
Figure 1 for Multi-Stream Attention Learning for Monocular Vehicle Velocity and Inter-Vehicle Distance Estimation
Figure 2 for Multi-Stream Attention Learning for Monocular Vehicle Velocity and Inter-Vehicle Distance Estimation
Figure 3 for Multi-Stream Attention Learning for Monocular Vehicle Velocity and Inter-Vehicle Distance Estimation
Figure 4 for Multi-Stream Attention Learning for Monocular Vehicle Velocity and Inter-Vehicle Distance Estimation
Viaarxiv icon

ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation

Add code
Aug 07, 2021
Figure 1 for ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
Figure 2 for ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
Figure 3 for ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
Figure 4 for ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
Viaarxiv icon

Learning from 2D: Pixel-to-Point Knowledge Transfer for 3D Pretraining

Add code
Apr 10, 2021
Figure 1 for Learning from 2D: Pixel-to-Point Knowledge Transfer for 3D Pretraining
Figure 2 for Learning from 2D: Pixel-to-Point Knowledge Transfer for 3D Pretraining
Figure 3 for Learning from 2D: Pixel-to-Point Knowledge Transfer for 3D Pretraining
Figure 4 for Learning from 2D: Pixel-to-Point Knowledge Transfer for 3D Pretraining
Viaarxiv icon

Unsupervised Disentanglement of Linear-Encoded Facial Semantics

Add code
Mar 30, 2021
Figure 1 for Unsupervised Disentanglement of Linear-Encoded Facial Semantics
Figure 2 for Unsupervised Disentanglement of Linear-Encoded Facial Semantics
Figure 3 for Unsupervised Disentanglement of Linear-Encoded Facial Semantics
Figure 4 for Unsupervised Disentanglement of Linear-Encoded Facial Semantics
Viaarxiv icon

$S^3$: Learnable Sparse Signal Superdensity for Guided Depth Estimation

Add code
Mar 22, 2021
Figure 1 for $S^3$: Learnable Sparse Signal Superdensity for Guided Depth Estimation
Figure 2 for $S^3$: Learnable Sparse Signal Superdensity for Guided Depth Estimation
Figure 3 for $S^3$: Learnable Sparse Signal Superdensity for Guided Depth Estimation
Figure 4 for $S^3$: Learnable Sparse Signal Superdensity for Guided Depth Estimation
Viaarxiv icon

Expanding Sparse Guidance for Stereo Matching

Add code
Apr 24, 2020
Figure 1 for Expanding Sparse Guidance for Stereo Matching
Figure 2 for Expanding Sparse Guidance for Stereo Matching
Figure 3 for Expanding Sparse Guidance for Stereo Matching
Figure 4 for Expanding Sparse Guidance for Stereo Matching
Viaarxiv icon

Indoor Depth Completion with Boundary Consistency and Self-Attention

Add code
Aug 22, 2019
Figure 1 for Indoor Depth Completion with Boundary Consistency and Self-Attention
Figure 2 for Indoor Depth Completion with Boundary Consistency and Self-Attention
Figure 3 for Indoor Depth Completion with Boundary Consistency and Self-Attention
Figure 4 for Indoor Depth Completion with Boundary Consistency and Self-Attention
Viaarxiv icon

Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder

Add code
Oct 31, 2018
Figure 1 for Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder
Figure 2 for Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder
Figure 3 for Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder
Figure 4 for Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder
Viaarxiv icon