Ismail Elezi
17 papers · 2020–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Academic Marathon (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (7) π Cross-Pollinator (12)
π
Interdisciplinary Bridge
π
Conference Polyglot
(7)
π
Grand Slam
π
Century Club
(16)
π₯
Unstoppable
(6)
ποΈ
Keyword Collector
(80)
Conferences
CVPR (6)
ICCV (3)
NIPS (3)
AAAI (2)
ECCV (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
object detection
(4)
active learning
(3)
uncertainty estimation
(2)
knowledge distillation
(2)
image generation
(2)
class imbalance
(2)
semi-supervised learning
(1)
principal component analysis
(1)
semantic segmentation
(1)
feature extraction
(1)
transfer learning
(1)
computer vision
(1)
embedding space
(1)
image retrieval
(1)
3d reconstruction
(1)
video generation
(1)
probabilistic modeling
(1)
epistemic uncertainty
(1)
attention mechanism
(1)
visual similarity
(1)
Papers
ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs
AAAI 2026
Region-based Cluster Discrimination for Visual Representation Learning
ICCV 2025
"Principal Components" Enable A New Language of Images
ICCV 2025
Fractal Calibration for Long-tailed Object Detection
CVPR 2025
From Attention to Activation: Unraveling the Enigmas of Large Language Models
ICLR 2025
VkD: Improving Knowledge Distillation using Orthogonal Projections
CVPR 2024
VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
NIPS 2024
Three Heads Are Better than One: Complementary Experts for Long-Tailed Semi-supervised Learning
AAAI 2024
G3DR: Generative 3D Reconstruction in ImageNet
CVPR 2024
Simple Cues Lead to a Strong Multi-Object Tracker
CVPR 2023
Learning to Discover and Detect Objects
NIPS 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
NIPS 2022
Learning Intra-Batch Connections for Deep Metric Learning
ICML 2021
Active Learning for Deep Object Detection via Probabilistic Modeling
ICCV 2021
CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks
CVPR 2020
The Group Loss for Deep Metric Learning
ECCV 2020