Majid Mirmehdi
8 papers · 2021–2026 · 2 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(24)
👥
Mega-Team · Squad
Top co-authors
Research topics
Computer Vision
(7)
Analysis
(6)
Machine Learning
(5)
Application Areas
(4)
Learning Types
(4)
Deep Learning
(3)
Artificial Intelligence
(2)
Healthcare & Medicine
(1)
Architectures
(1)
Clinical
(1)
Core AI · Artificial Intelligence
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Domain-Specific
(1)
Generation
(1)
Keywords
few-shot learning
(2)
contrastive learning
(1)
pseudo labeling
(1)
action recognition
(1)
domain generalization
(1)
domain adaptation
(1)
curriculum learning
(1)
object detection
(1)
prototype learning
(1)
video recognition
(1)
self-supervised learning
(1)
data augmentation
(1)
source-free domain adaptation
(1)
video understanding
(1)
representation learning
(1)
text-to-image generation
(1)
model merging
(1)
parameter-efficient learning
(1)
class imbalance
(1)
unsupervised learning
(1)
Papers
Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation
WACV 2026
DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation
CVPR 2026
GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain
WACV 2026
The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification
CVPR 2026
The PanAf-FGBG Dataset: Understanding the Impact of Backgrounds in Wildlife Behaviour Recognition
CVPR 2025
PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessment
WACV 2024
Use Your Head: Improving Long-Tail Video Recognition
CVPR 2023
Temporal-Relational CrossTransformers for Few-Shot Action Recognition
CVPR 2021