Mingtao Feng

8

Papers

2

Total Citations

Papers (8)

Semantic Ambiguity Modeling and Propagation for Fine-Grained Visual Cross View Geo-Localization

Mono3DVLT: Monocular-Video-Based 3D Visual Language Tracking

Hierarchical Gaussian Mixture Model Splatting for Efficient and Part Controllable 3D Generation

Feature Information Driven Position Gaussian Distribution Estimation for Tiny Object Detection

Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes

Partially Matching Submap Helps: Uncetainty Modeling and Propagation for Text to Point Cloud Localization

Beyond Human Perception: Understanding Multi-Object World from Monocular View

L4D-Track: Language-to-4D Modeling Towards 6-DoF Tracking and Shape Reconstruction in 3D Point Cloud Stream