Mi Luo
8 papers · 2021–2025 · 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (21) 🐣 Hot Topic Early Bird 👥 Mega-Team · Civilization
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Computer Vision
(4)
Machine Learning
(4)
Core AI · Computer Vision
(4)
Artificial Intelligence
(3)
Deep Learning
(3)
Application Areas
(2)
Core AI · Artificial Intelligence
(2)
Learning Types
(2)
Models
(2)
Optimization & Theory
(2)
Processing
(2)
Analysis
(1)
Architectures
(1)
Domain-Specific
(1)
Generation
(1)
Keywords
egocentric video
(2)
diffusion model
(2)
representation learning
(2)
vision transformer
(1)
model selection
(1)
pose estimation
(1)
video generation
(1)
self-supervised learning
(1)
multimodal learning
(1)
model architecture
(1)
egocentric vision
(1)
video understanding
(1)
hand pose estimation
(1)
unsupervised domain adaptation
(1)
model aggregation
(1)
activity recognition
(1)
3d pose estimation
(1)
hyperparameter tuning
(1)
ensemble method
(1)
video editing
(1)
Papers
Viewpoint Rosetta Stone: Unlocking Unpaired Ego-Exo Videos for View-invariant Representation Learning
CVPR 2025
4Diff: 3D-Aware Diffusion Model for Third-to-First Viewpoint Translation
ECCV 2024
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
CVPR 2024
HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness
NeurIPS 2024
Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos
ECCV 2024
Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline
NeurIPS 2024
MetaFormer Is Actually What You Need for Vision
CVPR 2022
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
NeurIPS 2021