Ismail Elezi
18 papers · 2020–2026 · 7 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 ↓+5 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (37) 🏃 Academic Marathon · Sprint 🏆 Grand Slam
🤝
Dynamic Duo
(10)
🗃️
Keyword Collector
(89)
🔥
Unstoppable · Bronze
❓
The Questioner
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(13)
Computer Vision
(8)
Deep Learning
(8)
Analysis
(6)
Application Areas
(6)
Core Methods
(6)
Architectures
(5)
Learning Types · Machine Learning
(5)
Learning Types · Deep Learning
(4)
Artificial Intelligence
(3)
Core AI
(3)
Optimization & Theory
(3)
Generation
(2)
Models
(2)
Applications
(1)
Keywords
object detection
(4)
active learning
(3)
image generation
(2)
class imbalance
(2)
knowledge distillation
(2)
uncertainty estimation
(2)
semantic segmentation
(1)
feature extraction
(1)
3d reconstruction
(1)
transfer learning
(1)
probabilistic modeling
(1)
principal component analysis
(1)
computer vision
(1)
embedding space
(1)
image classification
(1)
epistemic uncertainty
(1)
visual similarity
(1)
image retrieval
(1)
video generation
(1)
semi-supervised learning
(1)
Papers
Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering
CVPR 2026
ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs
AAAI 2026
Fractal Calibration for Long-tailed Object Detection
CVPR 2025
From Attention to Activation: Unraveling the Enigmas of Large Language Models
ICLR 2025
"Principal Components" Enable A New Language of Images
ICCV 2025
Region-based Cluster Discrimination for Visual Representation Learning
ICCV 2025
G3DR: Generative 3D Reconstruction in ImageNet
CVPR 2024
Three Heads Are Better than One: Complementary Experts for Long-Tailed Semi-supervised Learning
AAAI 2024
VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
NeurIPS 2024
VkD: Improving Knowledge Distillation using Orthogonal Projections
CVPR 2024
Simple Cues Lead to a Strong Multi-Object Tracker
CVPR 2023
Learning to Discover and Detect Objects
NeurIPS 2022
Not All Labels Are Equal: Rationalizing the Labeling Costs for Training Object Detection
CVPR 2022
The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes
NeurIPS 2022
Active Learning for Deep Object Detection via Probabilistic Modeling
ICCV 2021
Learning Intra-Batch Connections for Deep Metric Learning
ICML 2021
CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks
CVPR 2020
The Group Loss for Deep Metric Learning
ECCV 2020