Heng Fan

9

Papers

102

Total Citations

Papers (9)

Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance

ProMotion: Prototypes As Motion Learners

All You Need is One: Capsule Prompt Tuning with a Single Vector

GSOT3D: Towards Generic 3D Single Object Tracking in the Wild

PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization

Attention to Trajectory: Trajectory-Aware Open-Vocabulary Tracking

Kernel Adaptive Convolution for Scene Text Detection via Distance Map Prediction

Context-Guided Spatio-Temporal Video Grounding

CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes