Jiřı́ Matas

Computer Science · Physical Sciences

86h-index50.9kcitations514works2.72yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Image and Video Retrieval Techniques(164), Advanced Vision and Imaging(106), Video Surveillance and Tracking Methods(94), Robotics and Sensor-Based Localization(85), Image Retrieval and Classification Techniques(76)

Publications515 total

Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant Analysis
ArXiv.org·2026Open Access
Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant Analysis
arXiv (Cornell University)·2026Open Access
SAM-pose2seg: Pose-Guided Human Instance Segmentation in Crowds
arXiv (Cornell University)·2026Open Access
SAM-pose2seg: Pose-Guided Human Instance Segmentation in Crowds
ArXiv.org·2026Open Access
Auto-calibration of Camera Intrinsics and Extrinsics using Lidar and Motion
2025
The Third Visual Object Tracking Segmentation VOTS2025 Challenge Results
2025
Overview of LifeCLEF 2025: Challenges on Species Presence Prediction and Identification, and Individual Animal Identification
Lecture notes in computer science·2025· 2 cited
Deepfake Detection that Generalizes Across Benchmarks
arXiv (Cornell University)·2025Open Access
FungiTastic: A Multi-Modal Dataset and Benchmark for Image Categorization
2025
A Dataset for Semantic Segmentation in the Presence of Unknowns
2025
ILIAS: Instance-Level Image retrieval At Scale
2025· 2 cited
LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation
2025· 1 cited
ProbPose: A Probabilistic Approach to 2D Human Pose Estimation
2025· 3 cited
Antenna Q-Factor Topology Optimization with Auxiliary Edge Resistivities
arXiv (Cornell University)·2025Open Access
Q-Factor Evaluation Accelerated by a Deep Neural Network
2025· 1 cited
Unlocking the Hidden Potential of CLIP in Generalizable Deepfake Detection
arXiv (Cornell University)·2025Open Access
Breaking the Frame: Visual Place Recognition by Overlap Prediction
2025
MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation
2025· 1 cited
EEPPR: event-based estimation of periodic phenomena rate using correlation in 3D
2025
ILIAS: Instance-Level Image retrieval At Scale
arXiv (Cornell University)·2025Open Access
page 1 of 26Next →

Frequent Co-authors

Ondřej Chum(11), Luka Čehovin Zajc(10), Matej Kristan(10), Roman Pflugfelder(9), Gustavo J. Fernández(9), Josef Kittler(8), Alan Lukežič(8), Aleš Leonardis(8), Michael Felsberg(8), Lukáš Neumann(7), Tomáš Vojíř(7), Alfredo Petrosino(6), Krystian Mikolajczyk(5), Alireza Memarmoghadam(5), Álvaro García‐Martín(5), Fahad Shahbaz Khan(5), Huchuan Lu(5), Martin Danelljan(5), G Hager(4), Rama Krishna Gorthi(4)