Mateusz Kozinski

About Mateusz Kozinski

Mateusz Kozinski, With an exceptional h-index of 12 and a recent h-index of 10 (since 2020), a distinguished researcher at École Polytechnique Fédérale de Lausanne,

His recent articles reflect a diverse array of research interests and contributions to the field:

MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection

Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs

Lafter: Label-free tuning of zero-shot classifier using language and unlabeled image collections

Harnessing Deep Learning to Detect Bronchiolitis Obliterans Syndrome from Chest CT

Mate: Masked autoencoders are online 3d test-time learners

Actmad: Activation matching to align distributions for test-time-training

State-Aware Configuration Detection for Augmented Reality Step-by-Step Tutorials

Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions

Mateusz Kozinski Information

University

Position

Scientist

Citations(all)

581

Citations(since 2020)

522

Cited By

184

hIndex(all)

12

hIndex(since 2020)

10

i10Index(all)

14

i10Index(since 2020)

10

Email

University Profile Page

Google Scholar

Top articles of Mateusz Kozinski

MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection

arXiv preprint arXiv:2403.14497

2024/3/21

Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs

arXiv preprint arXiv:2403.11755

2024/3/18

Lafter: Label-free tuning of zero-shot classifier using language and unlabeled image collections

NeurIPS 2023; arXiv preprint arXiv:2305.18287

2023/5/29

Mate: Masked autoencoders are online 3d test-time learners

2023

Actmad: Activation matching to align distributions for test-time-training

CVPR 2023; arXiv preprint arXiv:2211.12870

2022/11/23

State-Aware Configuration Detection for Augmented Reality Step-by-Step Tutorials

2023/10/16

Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions

2023/6/4

Persistent homology with improved locality information for more effective delineation

IEEE Transactions on Pattern Analysis and Machine Intelligence

2023/3/1

Match, expand and improve: Unsupervised finetuning for zero-shot action recognition with language knowledge

ICCV 2023; arXiv preprint arXiv:2303.08914

2023/3/15

Video test-time adaptation for action recognition

CVPR 2023; arXiv preprint arXiv:2211.15393

2022/11/24

Enforcing connectivity of 3D linear structures using their 2D projections

2022/9/16

Generating LOD3 building models from structure-from-motion and semantic segmentation

Automation in Construction

2022/9/1

TOPO-Loss for continuity-preserving crack detection using deep learning

Construction and Building Materials

2022/8/15

Adjusting the ground truth annotations for connectivity-based learning to delineate

IEEE Transactions on Medical Imaging

2022/7/21

Localized Persistent Homologies for more Effective Deep Learning

2021/10/6

Mateusz Kozinski
Mateusz Kozinski

H-Index: 6

Pascal Fua
Pascal Fua

H-Index: 67

Drainage canals in Southeast Asian peatlands increase carbon emissions

Agu Advances

2021/3

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

IEEE Transactions on Pattern Analysis and Machine Intelligence

2021/4/21

A convolutional neural network segments yeast microscopy images with high accuracy

Nature communications

2020/11/12

YeaZ: A convolutional neural network for highly accurate, label-free segmentation of yeast microscopy images

bioRxiv

2020/5/12

See List of Professors in Mateusz Kozinski University(École Polytechnique Fédérale de Lausanne)