Thomas Mensink
17 papers · 2014–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π§ Keyword Pioneer π Cross-Pollinator (10) π Conference Polyglot (8) π Academic Marathon (11) π Renaissance Researcher (5)
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(28)
π₯
Mega-Team
(42)
π§¬
Topic Evolution
π
Century Club
(17)
β
The Questioner
ποΈ
Keyword Collector
(63)
π₯
Unstoppable
(6)
Conferences
CVPR (4)
ECCV (3)
ICCV (3)
ICML (2)
WACV (2)
CORL (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
semantic segmentation
(4)
transfer learning
(3)
zero-shot learning
(2)
image classification
(2)
image generation
(2)
diffusion model
(2)
depth estimation
(2)
semi-supervised learning
(1)
active learning
(1)
action recognition
(1)
feature matching
(1)
few-shot learning
(1)
domain adaptation
(1)
visual question answering
(1)
model distillation
(1)
multi-task learning
(1)
knowledge distillation
(1)
multimodal learning
(1)
knowledge transfer
(1)
vision transformer
(1)
Papers
Simpler Diffusion: 1.5 FID on ImageNet512 with Pixel-space Diffusion
CVPR 2025
Multistep Distillation of Diffusion Models via Moment Matching
NIPS 2024
Encyclopedic VQA: Visual Questions About Detailed Properties of Fine-Grained Categories
ICCV 2023
Scaling Vision Transformers to 22 Billion Parameters
ICML 2023
How Stable Are Transferability Metrics Evaluations?
ECCV 2022
Transferability Estimation Using Bhattacharyya Class Separability
CVPR 2022
Transferability Metrics for Selecting Source Model Ensembles
CVPR 2022
The Missing Link: Finding Label Relations across Datasets
ECCV 2022
EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes
WACV 2021
Calibration of Neural Networks using Splines
ICLR 2021
Neural Feature Matching in Implicit 3D Representations
ICML 2021
Multi-Loss Weighting With Coefficient of Variations
WACV 2021
Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection
CORL 2020
PointMixup: Augmentation for Point Clouds
ECCV 2020
Active Transfer Learning With Zero-Shot Priors: Reusing Past Datasets for Future Tasks
ICCV 2015
Objects2action: Classifying and Localizing Actions Without Any Video Example
ICCV 2015
COSTA: Co-Occurrence Statistics for Zero-Shot Classification
CVPR 2014