Jian-Fang Hu

25 papers · 2013–2026 · 6 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (6) 🏃 Academic Marathon (12) 🌈 Renaissance Researcher (6) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (56) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🧬 Topic Evolution 🤝 Dynamic Duo (19) 🚀 Conference Pioneer 💎 Century Club (24) 📈 Trend Setter 🔥 Unstoppable (5) 🗃️ Keyword Collector (124) ⚡ Prolific Year (7)

Conferences

CVPR (10) AAAI (4) ICCV (4) NIPS (4) ECCV (2) IJCAI (1)

Top co-authors

Wei-Shi Zheng (19) Chaolei Tan (7) Jianhuang Lai (6) Tianming Liang (4) Zihang Lin (4) Jiangxin Sun (4) Jianguo Zhang (4) Kun-Yu Lin (3) Xiaotong Lin (3) Xionghui Wang (2)

Keywords

video understanding (7) diffusion model (4) video grounding (4) human motion prediction (3) representation learning (3) action recognition (2) video paragraph grounding (2) knowledge distillation (2) spatio-temporal reasoning (2) human-object interaction (2) video prediction (2) weakly-supervised learning (2) early action prediction (2) subspace learning (1) pose estimation (1) multi-task learning (1) image restoration (1) transfer learning (1) semantic segmentation (1) image classification (1)

Papers

TubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding AAAI 2026

Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic CVPR 2025

ViSpeak: Visual Instruction Feedback in Streaming Videos ICCV 2025

ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations ICCV 2025

CLIP-RestoreX: Restore Image Structure and Perception in Exposure Correction AAAI 2025

SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection AAAI 2025

Panorama Generation From NFoV Image Done Right CVPR 2025

Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks CVPR 2025

Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model CVPR 2024

AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks NIPS 2024

Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels CVPR 2024

Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding CVPR 2024

Progressive Pretext Task Learning for Human Trajectory Prediction ECCV 2024

Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding CVPR 2023

Hierarchical Semantic Correspondence Networks for Video Paragraph Grounding CVPR 2023

Temporal Continual Learning with Prior Compensation for Human Motion Prediction NIPS 2023

You Never Stop Dancing: Non-freezing Dance Generation via Bank-constrained Manifold Projection NIPS 2022

Predictive Feature Learning for Future Segmentation Prediction ICCV 2021

Action-guided 3D Human Motion Prediction NIPS 2021

DBDNet: Learning Bi-directional Dynamics for Early Action Prediction IJCAI 2019

Progressive Teacher-Student Learning for Early Action Prediction CVPR 2019

Action Knowledge Transfer for Action Prediction with Partial Videos AAAI 2019

Deep Bilinear Learning for RGB-D Action Recognition ECCV 2018

Jointly Learning Heterogeneous Features for RGB-D Activity Recognition CVPR 2015

Recognising Human-Object Interaction via Exemplar Based Modelling ICCV 2013