Gabriela Csurka

Naver (South Korea) — South Korea

Computer Science · Physical Sciences

28h-index4.5kcitations138works0.92yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Advanced Image and Video Retrieval Techniques(67), Image Retrieval and Classification Techniques(49), Multimodal Machine Learning Applications(38), Domain Adaptation and Few-Shot Learning(36), Robotics and Sensor-Based Localization(17)

Publications139 total

Test-Time Vocabulary Adaptation for Language-Driven Object Detection
2025
PanSt3R: Multi-view Consistent Panoptic Segmentation
arXiv (Cornell University)·2025Open Access
MUSt3R: Multi-view Network for Stereo 3D Reconstruction
2025· 6 cited
Gaussian Splatting Feature Fields for (Privacy-Preserving) Visual Localization
2025
Test-time Vocabulary Adaptation for Language-driven Object Detection
arXiv (Cornell University)·2025Open Access
MUSt3R: Multi-view Network for Stereo 3D Reconstruction
arXiv (Cornell University)·2025Open Access
What Could Go Wrong? Discovering and Describing Failure Modes in Computer Vision
Lecture notes in computer science·2025
Spare Time Activity Sheets from Photo Albums
2024Open Access
What could go wrong? Discovering and describing failure modes in computer vision
arXiv (Cornell University)·2024Open Access
SHiNe: Semantic Hierarchy Nexus for Open-Vocabulary Object Detection
2024· 4 cited
Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinement
arXiv (Cornell University)·2024Open Access
SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection
arXiv (Cornell University)·2024Open Access
Self-Supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinement
2024· 2 cited
Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
arXiv (Cornell University)·2024Open Access
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow
2023· 73 cited
SegLoc: Learning Segmentation-Based Representations for Privacy-Preserving Visual Localization
2023· 15 cited
RaSP: Relation-aware Semantic Prior for Weakly Supervised Incremental Segmentation
arXiv (Cornell University)·2023· 1 citedOpen Access
Semantic Image Segmentation: Two Decades of Research
arXiv (Cornell University)·2023· 8 citedOpen Access
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow
arXiv (Cornell University)·2022· 2 citedOpen Access
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion
arXiv (Cornell University)·2022· 16 citedOpen Access
page 1 of 7Next →

Frequent Co-authors

Stéphane Clinchant(11), Florent Perronnin(9), Diane Larlus(8), Martin Humenberger(7), Boris Chidlovskii(7), Yohann Cabon(6), Philippe Weinzaepfel(5), Julien Ah-Pine(5), Jean-Michel Renders(5), Jérôme Revaud(4), Thomas Mensink(4), Jakob Verbeek(4), Luca Marchesotti(3), Noé Pion(3), Torsten Sattler(3), Vincent Leroy(3), Riccardo Volpi(3), Guillaume Jacquet(3), César Roberto de Souza(2), Christopher R. Dance(2)