Huimin Ma

23

Papers

46

Total Citations

Papers (23)

RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement

Unlocking Attributes' Contribution to Successful Camouflage: A Combined Textual and Visual Analysis Strategy

SAM2Object: Consolidating View Consistency via SAM2 for Zero-Shot 3D Instance Segmentation

ProtoCar: Learning 3D Vehicle Prototypes from Single-View and Unconstrained Driving Scene Images

AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios

MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network

A²RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image Fusion

Improving Object Proposals With Multi-Thresholding Straddling Expansion

Monocular 3D Object Detection for Autonomous Driving

Multi-View 3D Object Detection Network for Autonomous Driving

Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features

Single Image Action Recognition Using Semantic Body Part Actions

Defending Against Universal Adversarial Patches by Clipping Feature Norms

3D Object Proposals for Accurate Object Class Detection

Step Vulnerability Guided Mean Fluctuation Adversarial Attack against Conditional Diffusion Models

DADet: Safeguarding Image Conditional Diffusion Models against Adversarial and Backdoor Attacks via Diffusion Anomaly Detection

Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Textures

RRT-MVS: Recurrent Regularization Transformer for Multi-View Stereo

Image-to-video Adaptation with Outlier Modeling and Robust Self-learning

Transferable Adversarial Attacks for Object Detection Using Object

Unveiling the Dynamics of Information Interplay in Supervised Learning

Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems

FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning