Picture for Xiaoguang Ma

Xiaoguang Ma

Constrained Behavior Cloning for Robotic Learning

Add code
Aug 20, 2024
Viaarxiv icon

Low-Cost and Real-Time Industrial Human Action Recognitions Based on Large-Scale Foundation Models

Add code
Mar 13, 2024
Viaarxiv icon

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification

Add code
Mar 11, 2024
Viaarxiv icon

Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics

Add code
Feb 05, 2024
Viaarxiv icon

DynPL-SVO: A New Method Using Point and Line Features for Stereo Visual Odometry in Dynamic Scenes

Add code
May 17, 2022
Figure 1 for DynPL-SVO: A New Method Using Point and Line Features for Stereo Visual Odometry in Dynamic Scenes
Figure 2 for DynPL-SVO: A New Method Using Point and Line Features for Stereo Visual Odometry in Dynamic Scenes
Figure 3 for DynPL-SVO: A New Method Using Point and Line Features for Stereo Visual Odometry in Dynamic Scenes
Figure 4 for DynPL-SVO: A New Method Using Point and Line Features for Stereo Visual Odometry in Dynamic Scenes
Viaarxiv icon