Jian-Fang Hu

11

Papers

42

Total Citations

Papers (11)

Progressive Pretext Task Learning for Human Trajectory Prediction

ViSpeak: Visual Instruction Feedback in Streaming Videos

SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection

Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels

ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations

Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks

CLIP-RestoreX: Restore Image Structure and Perception in Exposure Correction

Panorama Generation From NFoV Image Done Right

Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model

Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding

Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic