Mateusz Kozinski
11 papers · 2015–2024 · 4 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 ↓+2 more ↓ Show less ↑
🗺️ Taxonomy Completionist (19) 🐣 Hot Topic Early Bird 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze
⚡
Prolific Year · Productive
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Keywords
distribution shift
(3)
test-time training
(2)
vision-language model
(2)
image segmentation
(2)
video recognition
(2)
online adaptation
(2)
multiple instance learning
(1)
neural network optimization
(1)
density estimation
(1)
deep learning
(1)
video anomaly detection
(1)
iterative refinement
(1)
domain adaptation
(1)
test-time adaptation
(1)
occlusion handling
(1)
likelihood estimation
(1)
markov random field
(1)
gaussian mixture model
(1)
loss function
(1)
point cloud
(1)
Papers
Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs
ECCV 2024
MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection
CVPR 2024
ActMAD: Activation Matching To Align Distributions for Test-Time-Training
CVPR 2023
LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections
NeurIPS 2023
MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
ICCV 2023
MATE: Masked Autoencoders are Online 3D Test-Time Learners
ICCV 2023
Video Test-Time Adaptation for Action Recognition
CVPR 2023
TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation
ECCV 2020
Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial Images
ECCV 2020
Beyond the Pixel-Wise Loss for Topology-Aware Delineation
CVPR 2018
A MRF Shape Prior for Facade Parsing With Occlusions
CVPR 2015