Hehe Fan
- Papers
- 10
Cite
Notes
Only stored in your browser.
Authored papers
10WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild
arXiv 2026
Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models
arXiv 2026
DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization
arXiv 2025
VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing
arXiv 2025
HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting
arXiv 2024
MMAD: Multi-label Micro-Action Detection in Videos
ICCV 2025
Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition
arXiv 2024
Continual Learning with Strong Experience Replay
arXiv 2023
Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos
ICCV 2023 1
DocMSU: A Comprehensive Benchmark for Document-level Multimodal Sarcasm Understanding
arXiv 2023
Affiliations
Frequent co-authors
10from 10 papers