Ajmal Mian

8

Papers

5

Total Citations

Papers (8)

Efficient Hyperparameter Optimization with Adaptive Fidelity Identification

Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level

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

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

Occlusion-aware Text-Image-Point Cloud Pretraining for Open-World 3D Object Recognition

CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation

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

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