Oriane Siméoni

Research Scientist, Meta FAIR

Joined

December 2019

Names

Oriane Siméoni

Emails

****@gmail.com (Confirmed)

****@valeo.com (Confirmed)

****@meta.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Research Scientist

Meta FAIR (meta.com)

2024 – Present

Research Scientist

Valeo.ai (valeo.com)

2020 – 2024

Intern

Google (google.com)

2020 – 2020

PhD student

INRIA (inria.fr)

2016 – 2020

Intern

Twitter (twitter.com)

2018 – 2019

Intern

Czech Technical Univeresity in Prague, Czech Technical University of Prague (fel.cvut.cz)

2018 – 2018

Advisors, Relations & Conflicts

Coworker

Jean Ponce

2021 – 2021

PhD Advisor

Ioannis Avrithis

2016 – 2020

PhD Advisor

Guillaume gravier

2016 – 2020

Coworker

Ahmet Iscen

2016 – 2019

Coworker

Giorgos Tolias

2016 – 2019

Expertise

computer vision

image representation

unsupervised object discovery

active learning

unsupervised segmentation

2016 – Present

Publications

DINOv3
Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seung Eun Yi, Michael Ramamonjisoa, Francisco Massa, Daniel HAZIZA, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan et al. (6 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
Revisiting [CLS] and Patch Token Interaction in Vision Transformers
Alexis Marouani, Oriane Siméoni, Herve Jegou, Piotr Bojanowski, Huy V. Vo
- ICLR 2026 Poster
- Readers: Everyone
Test-time Contrastive Concepts for Open-world Semantic Segmentation with Vision-Language Models
Monika Wysoczańska, Antonin Vobecky, Amaia Cardiel, Tomasz Trzcinski, Renaud Marlet, Andrei Bursuc, Oriane Siméoni
- Accepted by TMLR
- Readers: Everyone
CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation
Monika Wysoczańska, Oriane Siméoni, Michael Ramamonjisoa, Andrei Bursuc, Tomasz Trzcinski, Patrick Perez
- ECCV 2024
- Readers: Everyone
LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension
Amaia Cardiel, Eloi Zablocki, Elias Ramzi, Oriane Siméoni, Matthieu Cord
- ICLR 2025 Poster
- Readers: Everyone
Test-time Contrastive Concepts for Open-World Semantic Segmentation
Monika Wysoczańska, Antonin Vobecky, Amaia Cardiel, Tomasz Trzcinski, Renaud Marlet, Andrei Bursuc, Oriane Siméoni
- Submitted to ICLR 2025
- Readers: Everyone
MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments
Spyros Gidaris, Andrei Bursuc, Oriane Siméoni, Antonín Vobecký, Nikos Komodakis, Matthieu Cord, Patrick Perez
- Accepted by TMLR
- Readers: Everyone
POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
Antonín Vobecký, Oriane Siméoni, David Hurych, Spyros Gidaris, Andrei Bursuc, Patrick Perez, Josef Sivic
- NeurIPS 2023 poster
- Readers: Everyone
You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation
Nermin Samet, Oriane Siméoni, Gilles Puy, Georgy Ponimatkin, Renaud Marlet, Vincent Lepetit
- Published: 01 Jan 2023, Last Modified: 13 Aug 2023
- CoRR 2023
- Readers: Everyone
Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey
Oriane Siméoni, Éloi Zablocki, Spyros Gidaris, Gilles Puy, Patrick Pérez
- Published: 01 Jan 2023, Last Modified: 30 Oct 2023
- CoRR 2023
- Readers: Everyone

View all 28 publications

Co-Authors

View all 58 co-authors