Fanyue Wei
4 papers · 2022–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
visual saliency
(1)
video synthesis
(1)
video understanding
(1)
image editing
(1)
video highlight detection
(1)
diffusion model
(1)
spurious correlation
(1)
moment retrieval
(1)
positional embedding
(1)
temporal context
(1)
temporal localization
(1)
attention sharing
(1)
3d convolutional network
(1)
text-video alignment
(1)
pixel-level distinction
(1)
Papers
The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergy
CVPR 2026
The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning
ICCV 2025
Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning
ECCV 2024
Learning Pixel-Level Distinctions for Video Highlight Detection
CVPR 2022