Deng Cai

12

Papers

55

Total Citations

Papers (12)

3426 Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

Retrieval is Accurate Generation

Semi-supervised 3D Object Detection with PatchTeacher and PillarMix

Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection

STraj: Self-training for Bridging the Cross-Geography Gap in Trajectory Prediction

TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training

MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization

Empowering Self-Learning of LLMs: Inner Knowledge Explicitation as a Catalyst

PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation

Towards Fine-Grained HBOE with Rendered Orientation Set and Laplace Smoothing

Learning Occupancy for Monocular 3D Object Detection