Junfei Xiao
10 papers · 2022–2026 · 5 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 ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (28) ποΈ Keyword Collector (52)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
β
The Questioner
Top co-authors
Research topics
Computer Vision
(6)
Deep Learning
(6)
Artificial Intelligence
(5)
Machine Learning
(5)
Core AI
(5)
Architectures
(3)
Generation
(3)
Learning Types Β· Machine Learning
(3)
Learning Types Β· Deep Learning
(3)
Models
(3)
Analysis
(2)
Application Areas
(2)
Domain-Specific
(2)
Healthcare & Medicine
(1)
Clinical
(1)
Keywords
medical imaging
(2)
masked autoencoder
(2)
vision transformer
(2)
video generation
(2)
deep learning
(1)
visual representation learning
(1)
semantic alignment
(1)
video understanding
(1)
transfer learning
(1)
medical image segmentation
(1)
multi-label classification
(1)
synthetic data
(1)
knowledge distillation
(1)
diffusion model
(1)
action recognition
(1)
consistency regularization
(1)
vision-language model
(1)
self-supervised pretraining
(1)
embedding alignment
(1)
semi-supervised learning
(1)
Papers
Captain Safari: A World Engine with Pose-Aligned 3D Memory
CVPR 2026
VideoAuteur: Towards Long Narrative Video Generation
ICCV 2025
What If We Recaption Billions of Web Images with LLaMA-3?
ICML 2025
A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties
ECCV 2024
Rejuvenating image-GPT as Strong Visual Representation Learners
ICML 2024
CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection
ICCV 2023
Delving Into Masked Autoencoders for Multi-Label Thorax Disease Classification
WACV 2023
Label-Free Liver Tumor Segmentation
CVPR 2023
Masked Autoencoders Enable Efficient Knowledge Distillers
CVPR 2023
Learning From Temporal Gradient for Semi-Supervised Action Recognition
CVPR 2022