| CARVIEW |
I am a research scientist and deputy scientific director at valeo.ai and research associate at the Astra Inria project team working on perception for assisted and autonomous driving. I'm teaching the Deep Learning DIY course at Ecole Polytechnique with Marc Lelarge since 2019. Previously I was research scientist at Safran Tech and prior to that postdoctoral researcher at Inria Paris, within the Willow project team working with Josef Sivic and Ivan Laptev on video crowd analysis. I did a postdoc with Hervé Jégou at Inria Bretagne in 2014 working on kernelized visual descriptors for image retrieval and fine-grained classification within the FIRE-ID project. I have completed my PhD in 2012 at Mines ParisTech and Telecom Sudparis under the supervision of Françoise Prêteux and Titus Zaharia. During my PhD I worked on content-based video retrieval and on multimedia video navigation systems in a close cooperation with Alcatel-Lucent Bell Labs France. I am a former student of the Polytechnic University of Bucharest (BSc 2009).
My research interests concern computer vision and machine learning applied to all sorts of challenging tasks.
News
Dec 2025: I will give a talk on Open & Repurposable Foundation Models for the Automotive Industry at ai-PULSE in Paris.
Nov 2025: 🏅Our paper IPA: An Information-Preserving Input Projection Framework for Efficient Foundation Model Adaptation led by Yuan Yin got the best paper award at the NeurIPS 2025 CCFM Workshop and was accepted for publication in the TMLR journal.
Nov 2025: I will be serving as Area Chair at CVPR 2026 and ICML 2026 .
Oct 2025: Our paper CLIP's Visual Embedding Projector is a Few-shot Cornucopia led by Mohammad Fahes is accepted at WACV 2026.
Sep 2025: I will give a keynote talk at the IGN LASTIG seminar - Uncertainty and risks on Reliability in the age of Foundation Models .
July 2025: New release from the team: Franca. Franca is a new fully open-sourced (data, code, weights, logs) vision foundation model that finally matches & sometimes outperforms DINOv2, SigLIPv2 & CLIP on ViT-G on various benchmarks setting a new standard for open-source research. We open-source code, model weights and intermediate checkpoints.
June 2025: 2 papers accepted to ICCV 2025: DIP led by Sophia Sirko-Galouchenko, and FLOSS led by Yasser Benigmim.
June 2025: Thrilled to join the Horizon EU project ELLIOT (European Large Open Multi-Modal Foundation Models for Robust Generalization on Arbitrary Data Streams) to advance multimodal generalist foundation models. What a top-notch consortium from the ELLIS community!
Apr 2025: We have a new PR[AI]RIE PhD position opening with the Inria Astra team co-advised with Raoul de Charette and Tuan-Hung Vu on Physics-Grounded Vision Foundation Models. Check it out and contact us as soon as possible (before May 20th 2025) if you're interested.
Apr 2025: I will be serving as Area Chair at NeurIPS 2025.
Mar 2025: We are organizing the fourth edition of the Workshop on Uncertainty Quantification for Computer Vision at CVPR 2025 with an amazing line-up of speakers and papers.
Mar 2025: We are organizing the Embodied Intelligence for Autonomous Systems on the Horizon workshop at CVPR 2025 with a crazy program of talks and speakers.
Feb 2025: New release from the team: VaViM & VaVAM. VaViM is a 1.2B parameter video generative model trained on 1,800+ hours of raw Youtube videos. Its derived video-action model, VaVAM, achieves state-of-the-art results on NeuroNCAP driving benchmark. We open-source code, model weights, training recipes and scaling laws.
Jan 2025: Our paper MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments led Spyros Gidaris and published in TMLR, was shortlisted to be presented at ICLR 2025.
Jan 2025: Honored to give a keynote talk on Multi-modal foundation models in the automotive industry at the Multimedia Modeling Conference in Nara, Japan.
Oct 2024: Check out our technical report The BRAVO Semantic Segmentation Challenge Results in UNCV2024.
Sep 2024: Our paper No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations with Walter Simoncini, Spyros Gidaris, and Yuki M. Asano is accepted at NeurIPS 2024. Go 🍄!
Sep 2024: I will be serving as Area Chair at CVPR 2025.
Selected papers and pre-prints
Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
Shashanka Venkataramanan, Valentinos Pariza, Mohammadreza Salehi, Lukas Knobel, Spyros Gidaris, Elias Ramzi, Andrei Bursuc, Yuki M. Asano
Preprint, 2025
bibtex / code
@article{venkataramanan2025franca,
title={Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning},
author={Venkataramanan, Shashanka and Pariza, Valentinos and Salehi, Mohammadreza and Knobel, Lukas and Gidaris, Spyros and Ramzi, Elias and Bursuc, Andrei and Asano, Yuki M},
journal={arXiv preprint arXiv:2507.14137},
year={2025}
}
IPA: An Information-Preserving Input Projection Framework for Efficient Foundation Model Adaptation
Yuan Yin, Shashanka Venkataramanan, Tuan-Hung Vu, Andrei Bursuc, Matthieu Cord
NeurIPS 2025 CCFM Workshop , 2025 and TMLR, 2026
bibtex
@article{yin2026ipa,
title={IPA: An Information-Preserving Input Projection Framework for Efficient Foundation Model Adaptation},
author={Yin, Yuan and Venkataramanan, Shashanka and Vu, Tuan-Hung and Bursuc, Andrei and Cord, Matthieu},
journal={TMLR},
year={2026}
}
CLIP's Visual Embedding Projector is a Few-shot Cornucopia
Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
WACV, 2026
bibtex / code
@inproceedings{fahes2024prolip,
title={Fine-Tuning CLIP's Last Visual Projector: A Few-Shot Cornucopia},
author={Fahes, Mohammad and Vu, Tuan-Hung and Bursuc, Andrei and P{\'e}rez, Patrick and de Charette, Raoul},
booktitle={WACV},
year={2026}
}
DIP: Unsupervised Dense In-Context Post-training of Visual Representations
Sophia Sirko-Galouchenko, Antonin Vobecky, Nicolas Thome, Andrei Bursuc, Spyros Gidaris,
ICCV, 2025
bibtex / code
@inproceedings{sirko2025dip,
title={DIP: Unsupervised Dense In-Context Post-training of Visual Representations},
author={Sirko-Galouchenko, Sophia and Gidaris, Spyros and Vobecky, Antonin and Bursuc, Andrei and Thome, Nicolas},
booktitle={ICCV},
year={2025}
}
FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation
Yasser Benigmim, Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Raoul de Charette
ICCV, 2025
bibtex / code / project page
@inproceedings{benigmim2025floss,
title={FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation},
author={Benigmim, Yasser and Fahes, Mohammad and Vu, Tuan-Hung and Bursuc, Andrei and de Charette, Raoul},
booktitle={ICCV},
year={2025}
}
VaViM and VaVAM: Autonomous Driving through Video Generative Modeling
Florent Bartoccioni, Elias Ramzi, Victor Besnier, Shashanka Venkataramanan, Tuan-Hung Vu, Yihong Xu, Spyros Gidaris, Serkan Odabas, David Hurych, Renaud Marlet, Alexandre Boulch, Mickaël Chen, Eloi Zablocki, Andrei Bursuc, Eduardo Valle, Matthieu Cord
Preprint, 2025
bibtex / code / project page
@article{bartoccioni2025vavim,
title={VaViM and VaVAM: Autonomous Driving through Video Generative Modeling},
author={Bartoccioni, Florent and Ramzi, Elias and Besnier, Victor and Venkataramanan, Shashanka and Vu, Tuan-Hung and Xu, Yihong and Chambon, Loick and Gidaris, Spyros and Odabas, Serkan and Hurych, David and others},
journal={arXiv preprint arXiv:2502.15672},
year={2025}
}
Test-time Contrastive Concepts for Open-world Semantic Segmentation
Monika Wysoczańska , Antonin Vobecky, Amaia Cardiel, Tomasz Trzciński, Renaud Marlet, Andrei Bursuc, Oriane Siméoni
TMLR, 2025
bibtex
@article{wysoczanska2024contrastiveconcepts,
title={A study of test-time contrastive concepts for open-world, open-vocabulary semantic segmentation},
author={Wysocza{\'n}ska, Monika and Vobecky, Antonin and Cardiel, Amaia and Trzci{\'n}ski, Tomasz and Marlet, Renaud and Bursuc, Andrei and Sim{\'e}oni, Oriane},
journal={TMLR},
year={2025}
}
LED: Light Enhanced Depth Estimation at Night
Simon De Moreau, Yasser Almehio, Andrei Bursuc, Hafid El-Idrissi, Bogdan Stanciulescu, Fabien Moutarde
BMVC, 2025
bibtex / code
@inproceedings{deMoreau2025led,
title = {LED: Light Enhanced Depth Estimation at Night},
author = {De Moreau, Simon and Almehio, Yasser and Bursuc, Andrei and El-Idrissi, Hafid and Stanciulescu, Bogdan and Moutarde, Fabien},
booktitle = {BMVC},
year = {2025},
}
DOC-Depth: A novel approach for dense depth ground truth generation
Simon De Moreau, Mathias Corsia, Hassan Bouchiba, and Yasser Almehio, Andrei Bursuc, Hafid El-Idrissi, Fabien Moutarde
Intelligent Vehicles Symposium, 2025
bibtex / code / dataset / project page
@inproceedings{deMoreau2024doc,
title = {DOC-Depth: A novel approach for dense depth ground truth generation},
author = {De Moreau, Simon and Corsia, Mathias and Bouchiba, Hassan and Almehio, Yasser and Bursuc, Andrei and El-Idrissi, Hafid and Moutarde, Fabien},
booktitle = {IV},
year = {2025},
}
Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation
Antonin Vobecky, David Hurych, Oriane Siméoni, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Josef Sivic
IJCV, 2025
bibtex
@article{vobecky2025das,
title={Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation},
author={Vobecky, Antonin and Hurych, David and Sim{\'e}oni, Oriane and Gidaris, Spyros and Bursuc, Andrei and P{\'e}rez, Patrick and Sivic, Josef},
journal={IJCV},
year={2025}
}
No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations
Walter Simoncini, Spyros Gidaris, Andrei Bursuc, Yuki M. Asano
NeurIPS, 2024
bibtex / code / project page
@inproceedings{simoncini2024fungi,
title={No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations},
author={Walter Simoncini and Spyros Gidaris and Andrei Bursuc and Yuki M. Asano},
booktitle={NeurIPS},
year={2024}
}
CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation
Monika Wysoczańska , Oriane Siméoni, Michaël Ramamonjisoa, Andrei Bursuc, Tomasz Trzciński, Patrick Pérez
ECCV, 2024
bibtex / code / project page
@inproceedings{wysoczanska2024dinoiser,
title={CLIP-DINOiser: Teaching CLIP a few DINO tricks},
author={Wysocza{\'n}ska, Monika and Sim{\'e}oni, Oriane and Ramamonjisoa, Micha{\"e}l and Bursuc, Andrei and Trzci{\'n}ski, Tomasz and P{\'e}rez, Patrick},
booktitle={ECCV},
year={2024}
}
The BRAVO Semantic Segmentation Challenge Results in UNCV2024
Tuan-Hung Vu, Eduardo Valle, Andrei Bursuc, Tommie Kerssies, Daan de Geus, Gijs Dubbelman, Long Qian, Bingke Zhu, Yingying Chen, Ming Tang, Jinqiao Wang, Tomáš Vojíř, Jan Šochman, Jiří Matas, Michael Smith, Frank Ferrie, Shamik Basu, Christos Sakaridis, Luc Van Gool
ECCV Workshops, 2024
bibtex / code / project page
@inproceedings{vu2024bravo,
title={The BRAVO Semantic Segmentation Challenge Results in UNCV2024},
author={Vu, Tuan-Hung and Valle, Eduardo and Bursuc, Andrei and Kerssies, Tommie and de Geus, Daan and Dubbelman, Gijs and Qian, Long and Zhu, Bingke and Chen, Yingying and Tang, Ming and others},
booktitle={ECCV Workshops},
year={2024}
}
Valeo4Cast: A Modular Approach to End-to-End Forecasting
Yihong Xu, Eloi Zablocki, Alexandre Boulch, Gilles Puy, Mickaël Chen, Florent Bartoccioni, Nermin Samet, Oriane Siméoni, Spyros Gidaris, Corentin Sautier, Tuan-Hung Vu, Andrei Bursuc, Eduardo Valle, Renaud Marlet, Matthieu Cord
Winning solution to the "Unified Detection, Tracking and Forecasting" Argoverse 2 challenge @CVPR Worshop on Autonomous Driving (WAD), 2024
bibtex / project page
@inproceedings{xu2024valeo4cast,
title={Valeo4Cast: A Modular Approach to End-to-End Forecasting},
author={Xu, Yihong and Zablocki, {\'E}loi and Boulch, Alexandre and Puy, Gilles and Chen, Mickael and Bartoccioni, Florent and Samet, Nermin and Sim{\'e}oni, Oriane and Gidaris, Spyros and Vu, Tuan-Hung and others},
booktitle={ECCV Workshops},
year={2024}
}
Three Pillars improving Vision Foundation Model Distillation for Lidar
Gilles Puy, Spyros Gidaris, Alexandre Boulch, Oriane Siméoni, Corentin Sautier, Patrick Pérez, Andrei Bursuc, Renaud Marlet
CVPR, 2024
bibtex / code / project page
@inproceedings{puy24scalr,
title={Three Pillars improving Vision Foundation Model Distillation for Lidar},
author={Puy, Gilles and Gidaris, Spyros and Boulch, Alexandre and Sim\'eoni, Oriane and Sautier, Corentin and P\'erez, Patrick and Bursuc, Andrei and Marlet, Renaud},
booktitle={CVPR},
year={2024}
}
A Simple Recipe for Language-guided Domain Generalized Segmentation
Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
CVPR, 2024
bibtex / code / project page
@inproceedings{fahes2024simple,
title={A Simple Recipe for Language-guided Domain Generalized Segmentation},
author={Fahes, Mohammad and Vu, Tuan-Hung and Bursuc, Andrei and P{\'e}rez, Patrick and de Charette, Raoul},
booktitle={CVPR},
year={2024}
}
Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models
Gianni Franchi, Olivier Laurent, Maxence Leguéry, Andrei Bursuc, Andrea Pilzer, Angela Yao
CVPR, 2024
bibtex / project page
@inproceedings{franchi2024make,
title={Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models},
author={Franchi, Gianni and Laurent, Olivier and Legu{\'e}ry, Maxence and Bursuc, Andrei and Pilzer, Andrea and Yao, Angela},
booktitle={CVPR},
year={2024}
}
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
Sophia Sirko-Galouchenko, Alexandre Boulch, Spyros Gidaris, Andrei Bursuc, Antonin Vobecky, Patrick Pérez, Renaud Marlet
CVPR Workshop on Autonomous Driving, 2024
bibtex
@inproceedings{sirko2024occfeat,
title={OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks},
author={Sirko-Galouchenko, Sophia and Boulch, Alexandre and Gidaris, Spyros and Bursuc, Andrei and Vobecky, Antonin and P{\'e}rez, Patrick and Marlet, Renaud},
journal={CVPR Workshops},
year={2024}
}
MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments
Spyros Gidaris, Andrei Bursuc, Oriane Siméoni, Nikos Komodakis, Matthieu Cord, Patrick Pérez
TMLR, 2024
bibtex
@article{gidaris2024moca,
title={MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments},
author={Gidaris, Spyros and Bursuc, Andrei and Simeoni, Oriane and Vobecky, Antonin and Komodakis, Nikos and Cord, Matthieu and P{\'e}rez, Patrick},
journal={TMLR},
year={2024}
}
Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification
Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch
TPAMI, 2024
bibtex / code
@article{franchi2024lpbnn,
title={Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification},
author={Franchi, Gianni and Bursuc, Andrei and Aldea, Emanuel and Dubuisson, S{\'e}verine and Bloch, Isabelle},
journal={TPAMI},
year={2024}
}
Learning to Generate Training Datasets for Robust Semantic Segmentation
Marwane Hariat, Olivier Laurent, Remi Kazmierczak, Shihao Zhang, Andrei Bursuc, Angela Yao, Gianni Franchi
WACV, 2024
bibtex / project page
@inproceedings{hariat2024learning,
title={Learning to generate training datasets for robust semantic segmentation},
author={Hariat, Marwane and Laurent, Olivier and Kazmierczak, R{\'e}mi and Zhang, Shihao and Bursuc, Andrei and Yao, Angela and Franchi, Gianni},
booktitle={WACV},
year={2024}
}
POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
Antonin Vobecky, Oriane Siméoni, David Hurych, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Josef Sivic
NeurIPS, 2023
bibtex / code / project page
@inproceedings{vobecky2023pop,
title={Pop-3d: Open-vocabulary 3d occupancy prediction from images},
author={Vobecky, Antonin and Sim{\'e}oni, Oriane and Hurych, David and Gidaris, Spyridon and Bursuc, Andrei and P{\'e}rez, Patrick and Sivic, Josef},
booktitle={NeurIPS},
year={2023}
}
PØDA: Prompt-driven Zero-shot Domain Adaptation
Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
ICCV, 2023
bibtex / code / project page
@inproceedings{fahes2023poda,
title={P{\O}DA: Prompt-driven Zero-shot Domain Adaptation},
author={Fahes, Mohammad and Vu, Tuan-Hung and Bursuc, Andrei and P{\'e}rez, Patrick and de Charette, Raoul},
booktitle={ICCV},
year={2023}
}
RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving
Angelika Ando, Spyros Gidaris, Andrei Bursuc, Gilles Puy, Alexandre Boulch, Renaud Marlet
CVPR, 2023
bibtex / code / project page
@inproceedings{ando2023rangevit,
title={RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving},
author={Ando, Angelika and Gidaris, Spyros and Bursuc, Andrei and Puy, Gilles and Boulch, Alexandre and Marlet, Renaud},
booktitle={CVPR},
year={2023}
}
Packed Ensembles for efficient uncertainty estimation
Olivier Laurent, Adrien Lafage, Enzo Tartaglione, Geoffrey Daniel, Jean-Marc Martinez, Andrei Bursuc, Gianni Franchi
ICLR (spotlight), 2023
bibtex / code / project page
@inproceedings{laurent2022packed,
title={Packed-Ensembles for Efficient Uncertainty Estimation},
author={Laurent, Olivier and Lafage, Adrien and Tartaglione, Enzo and Daniel, Geoffrey and Martinez, Jean-Marc and Bursuc, Andrei and Franchi, Gianni},
booktitle={ICLR},
year={2023}
}
LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation
Florent Bartoccioni, Éloi Zablocki, Andrei Bursuc, Patrick Pérez, Matthieu Cord, Karteek Alahari
CoRL, 2022
bibtex / code / project page
@inproceedings{bartoccioni2022lara,
title={LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation},
author={Bartoccioni, Florent and Zablocki, {\'E}loi and Bursuc, Andrei and P{\'e}rez, Patrick and Cord, Matthieu and Alahari, Karteek},
booktitle={CoRL},
year={2022}
}
MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks
Gianni Franchi, Xuanlong Yu, Andrei Bursuc, Angel Tena, Rémi Kazmierczak, Severine Dubuisson, Emanuel Aldea, David Filliat
BMVC, 2022
bibtex / code / project page
@inproceedings{franchi2022muad,
title={MUAD: Multiple uncertainties for autonomous driving benchmark for multiple uncertainty types and tasks},
author={Franchi, Gianni and Yu, Xuanlong and Bursuc, Andrei and Kazmierczak, R{\'e}mi and Dubuisson, S{\'e}verine and Aldea, Emanuel and Filliat, David},
booktitle={BMVC},
year={2022}
}
Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation
Antonin Vobecky, David Hurych, Oriane Siméoni, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Josef Sivic
ECCV (oral), 2022
bibtex / code / project page
@inproceedings{vobecky2022drive,
title={Drive\&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation},
author={Vobecky, Antonin and Hurych, David and Sim{\'e}oni, Oriane and Gidaris, Spyros and Bursuc, Andrei and P{\'e}rez, Patrick and Sivic, Josef},
booktitle={ECCV},
year={2022}
}
What to Hide from Your Students: Attention-Guided Masked Image Modeling
Ioannis Kakogeorgiou, Spyros Gidaris, Bill Psomas, Yannis Avrithis, Andrei Bursuc, Konstantinos Karantzalos, Nikos Komodakis
ECCV, 2022
bibtex / code
@inproceedings{kakogeorgiou2022hide,
title={What to Hide from Your Students: Attention-Guided Masked Image Modeling},
author={Kakogeorgiou, Ioannis and Gidaris, Spyros and Psomas, Bill and Avrithis, Yannis and Bursuc, Andrei and Karantzalos, Konstantinos and Komodakis, Nikos},
booktitle={ECCV},
year={2022}
}
Latent Discriminant deterministic Uncertainty
Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, David Filliat
ECCV, 2022
bibtex / code / project page
@inproceedings{franchi2022latent,
title={Latent Discriminant deterministic Uncertainty},
author={Franchi, Gianni and Yu, Xuanlong and Bursuc, Andrei and Aldea, Emanuel and Dubuisson, Severine and Filliat, David},
booktitle={ECCV},
year={2022}
}
Active Learning Strategies for Weakly-Supervised Object Detection
Huy V. Vo, Oriane Siméoni, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Jean Ponce
ECCV, 2022
bibtex / code / project page
@inproceedings{vo2022active,
title={Active Learning Strategies for Weakly-Supervised Object Detection},
author={Vo, Huy V and Sim{\'e}oni, Oriane and Gidaris, Spyros and Bursuc, Andrei and P{\'e}rez, Patrick and Ponce, Jean},
booktitle={ECCV},
year={2022}
}
}
Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data
Corentin Sautier, Gilles Puy, Spyros Gidaris, Alexandre Boulch, Andrei Bursuc, Renaud Marlet
CVPR, 2022
bibtex / code / project page
@inproceedings{sautier22slidr,
title={Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data},
author={Corentin Sautier and Gilles Puy and Spyros Gidaris and Alexandre Boulch and Andrei Bursuc and Renaud Marlet},
booktitle={CVPR}
year={2022}
}
Spherical perspective on learning with normalization layers
Simon Roburin, Yann de Mont-Marin, Andrei Bursuc, Renaud Marlet, Patrick Pérez, Mathieu Aubry
Neurocomputing, 2022
bibtex / project page / code
@article{roburin2022spherical,
title={Spherical perspective on learning with normalization layers},
author={Roburin, Simon and de Mont-Marin, Yann and Bursuc, Andrei and Marlet, Renaud and P{\'e}rez, Patrick and Aubry, Mathieu},
journal={Neurocomputing},
volume={487},
pages={66--74},
year={2022},
publisher={Elsevier}
}
Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability using Tree Search and Graph Neural Networks
Kevin Osanlou, Jeremy Frank, J. Benton, Andrei Bursuc, Christophe Guettier, Tristan Cazenave, Eric Jacopin
AAAI (oral), 2022
bibtex
@inproceedings{osanlou2022solving,
title={Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability using Tree Search and Graph Neural Networks},
author={Osanlou, Kevin and Frank, Jeremy and Bursuc, Andrei and Cazenave, Tristan and Jacopin, Eric and Guettier, Christophe and Benton, J},
booktitle={AAAI},
year={2022}
}
Reliable Semantic Segmentation with Superpixel-Mix
Gianni Franchi, Nacim Belkhir, Mai Lan Ha, Yufei Hu, Andrei Bursuc, Volker Blanz, Angela Yao
BMVC, 2021
bibtex / code / project page
@inproceedings{franchi2021robust,
title={Reliable Semantic Segmentation with Superpixel-Mix},
author={Franchi, Gianni and Belkhir, Nacim and Ha, Mai Lan and Hu, Yufei and Bursuc, Andrei and Blanz, Volker and Yao, Angela},
booktitle={BMVC},
year={2021}
}
Localizing Objects with Self-Supervised Transformers and no Labels
Oriane Siméoni, Gilles Puy, Huy V. Vo, Simon Roburin, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Renaud Marlet, and Jean Ponce
BMVC, 2021
bibtex / code / project page
@inproceedings{simeoni2021lost,
title = {Localizing Objects with Self-Supervised Transformers and no Labels},
author = {Oriane Sim\'eoni and Gilles Puy and Huy V. Vo and Simon Roburin and Spyros Gidaris and Andrei Bursuc and Patrick P\'erez and Renaud Marlet and Jean Ponce},
booktitle = {BMVC},
year = {2021}
}
Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation
Victor Besnier, Andrei Bursuc, Alexandre Briot, and David Picard
ICCV, 2021
bibtex / code / video / project page
@inproceedings{besnier2021triggering,
title = {Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation},
author = {Besnier, Victor and Bursuc, Andrei and Picard, David and Briot Alexandre},
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
year={2021}
}
StyleLess layer: Improving robustness for real-world driving
Julien Rebut, Andrei Bursuc, and Patrick Pérez
IROS, 2021
bibtex
@inproceedings{rebut2021styleless,
title={StyleLess layer: Improving robustness for real-world driving},
author={Rebut, Julien and Bursuc, Andrei and P{\'e}rez, Patrick},
booktitle={IROS},
year={2021}
}
Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning
Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, and Matthieu Cord
CVPR, 2021
bibtex / code / project page
@inproceedings{gidaris2021obow,
title={Learning Representations by Predicting Bags of Visual Words},
author={Gidaris, Spyros and Bursuc, Andrei and Komodakis, Nikos and P{\'e}rez, Patrick and Cord, Matthieu},
booktitle={CVPR},
year={2020}
}
PLOP: Probabilistic poLynomial Objects trajectory Prediction for autonomous driving
Thibault Buhet, Emilie Wirbel, Andrei Bursuc, Xavier Perrotton
CoRL, 2020
bibtex / blog post / project page
@inproceedings{buhet2020plop,
title={PLOP: Probabilistic poLynomial Objects trajectory Planning for autonomous driving},
author={Buhet, Thibault and Wirbel, Emilie and Bursuc, Andrei and Perrotton, Xavier},
booktitle={Conference on Robot Learning (CoRL)},
year={2020}
}
TRADI: Tracking deep neural network weight distributions for uncertainty estimation
Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch
ECCV, 2020
bibtex / code
@inproceedings{franchi2020tradi,
title={TRADI: Tracking deep neural network weight distributions for uncertainty estimation},
author={Franchi, Gianni and Bursuc, Andrei and Aldea, Emanuel and Dubuisson, S{\'e}verine and Bloch, Isabelle},
booktitle={ECCV},
year={2020}
}
One Versus all for deep Neural Network Incertitude (OVNNI) quantification
Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch
arXiv, 2020
bibtex
@article{franchi2020one,
title={One Versus all for deep Neural Network Incertitude (OVNNI) quantification},
author={Franchi, Gianni and Bursuc, Andrei and Aldea, Emanuel and Dubuisson, Severine and Bloch, Isabelle},
journal={arXiv preprint arXiv:2006.00954},
year={2020}
}
Learning Representations by Predicting Bags of Visual Words
Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, and Matthieu Cord
CVPR, 2020
bibtex / code
@inproceedings{gidaris2020learning,
title={Learning Representations by Predicting Bags of Visual Words},
author={Gidaris, Spyros and Bursuc, Andrei and Komodakis, Nikos and P{\'e}rez, Patrick and Cord, Matthieu},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={6928--6938},
year={2020}
}
Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systems
Isabelle Leang, Ganesh Sistu, Fabian Burger, Andrei Bursuc, and Senthil Yogamani
ITSC, 2020
bibtex
@inproceedings{leang2020dynamic,
title={Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systems},
author={Leang, Isabelle and Sistu, Ganesh and Burger, Fabian and Bursuc, Andrei and Yogamani, Senthil},
booktitle={ITSC},
year={2020}
}
This dataset does not exist: training models from generated images
Victor Besnier, Himalaya Jain, Andrei Bursuc, Matthieu Cord, and Patrick Pérez
ICASSP, 2020
bibtex
@inproceedings{besnier2020dataset,
title={This dataset does not exist: training models from generated images},
author={Besnier, Victor and Jain, Himalaya and Bursuc, Andrei and Cord, Matthieu and P{\'e}rez, Patrick},
booktitle={ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages={1--5},
year={2020},
organization={IEEE}
}
Boosting Few-Shot Visual Learning With Self-Supervision
Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, and Matthieu Cord
ICCV, 2019
bibtex / code
@inproceedings{gidaris2019boosting,
title={Boosting few-shot visual learning with self-supervision},
author={Gidaris, Spyros and Bursuc, Andrei and Komodakis, Nikos and P{\'e}rez, Patrick and Cord, Matthieu},
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
pages={8059--8068},
year={2019}
}
Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search
Kevin Osanlou, Andrei Bursuc, Christophe Guettier, Tristan Cazenave and Eric Jacopin
IROS, 2019
bibtex
@inproceedings{osanlou2019optimal,
title={Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search},
author={Osanlou, Kevin and Bursuc, Andrei and Guettier, Christophe and Cazenave, Tristan and Jacopin, Eric},
booktitle={2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
pages={3519--3525},
year={2019},
organization={IEEE}
}
Dense Classification and Implanting for Few-Shot Learning
Yann Lifchitz, Yannis Avrithis, Sylvaine Picard, Andrei Bursuc
CVPR, 2019
bibtex
@inproceedings{lifchitz2019dense,
title={Dense classification and implanting for few-shot learning},
author={Lifchitz, Yann and Avrithis, Yannis and Picard, Sylvaine and Bursuc, Andrei},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={9258--9267},
year={2019}
}
Understanding and Improving Kernel Local Descriptors
Arun Mukundan, Giorgos Tolias, Andrei Bursuc, Hervé Jégou, Ondřej Chum
International Journal on Computer Vision (IJCV), 2019
bibtex
@article{mukundan2019understanding,
title={Understanding and improving kernel local descriptors},
author={Mukundan, Arun and Tolias, Giorgos and Bursuc, Andrei and J{\'e}gou, Herv{\'e} and Chum, Ond{\v{r}}ej},
journal={International Journal of Computer Vision},
volume={127},
number={11-12},
pages={1723--1737},
year={2019},
publisher={Springer}
}
Rotation and translation covariant match kernels for image retrieval
Giorgos Tolias, Andrei Bursuc, Teddy Furon, Hervé Jégou
Computer Vision and Image Understanding (CVIU), 2015
bibtex / code
@article{tolias15,
title = {{Rotation and translation covariant match kernels for image retrieval}},
author = {Tolias, Giorgos and Bursuc, Andrei and Furon, Teddy and J{\'e}gou, Herv{\'e}},
url = {https://hal.archives-ouvertes.fr/hal-01168525},
journal = {{Computer Vision and Image Understanding}},
publisher = {{Elsevier}},
year = {2015},
month = Jun,
doi = {10.1016/j.cviu.2015.06.007}
}
Kernel Local Descriptors with Implicit Rotation Matching
Andrei Bursuc, Giorgos Tolias, Hervé Jégou
International Conference on Multimedia Retrieval, 2015
bibtex / poster / code
@inproceedings{Bursuc15,
author = {Bursuc, Andrei and Tolias, Giorgos and J{\'e}gou, Herv{\'e}},
title = {{Kernel Local Descriptors with Implicit Rotation Matching}},
url = {https://hal.inria.fr/hal-01145656},
booktitle = {{ACM International Conference on Multimedia Retrieval }},
year = {2015}
}
A Smartphone-Based Obstacle Detection and Classification System for Assisting Visually Impaired People
Ruxandra Tapu, Bogdan Mocanu, Andrei Bursuc, Titus Zaharia
ICCV Workshop on Wearable Computer Vision Systems, 2013
bibtex
@inproceedings{Tapu13,
author = {Tapu, R. and Mocanu, B. and Bursuc, A. and Zaharia, T.},
title = {A Smartphone-Based Obstacle Detection and Classification System for Assisting Visually Impaired People},
booktitle = {Computer Vision Workshops (ICCVW), 2013 IEEE International Conference on},
year = {2013},
pages = {444-451}
}
ARTEMIS at TRECVID 2013: Instance Search Task
Andrei Bursuc, Titus Zaharia
Trecvid Workshop, 2013
bibtex
@inproceedings{bursuc2013b,
title = {ARTEMIS at TRECVID 2013: Instance Search Task},
author = {Bursuc, Andrei and Titus, Zaharia},
booktitle = {Proc. TRECVID Workshop},
year = {2013}
}
ARTEMIS @ MediaEval 2013: A Content-Based Image Clustering Method for Public Image Repositories
Andrei Bursuc, Titus Zaharia
MediaEval Workshop, 2013
bibtex
@article{bursuc2013c,
title = {ARTEMIS@ MediaEval 2013: A Content-Based Image Clustering Method for Public Image Repositories, Working Notes Proceedings MediaEval 2013 Workshop, Eds},
author = {Bursuc, A and Zaharia, T},
journal = {M Larson, X Anguera, T Reuter, GJF Jones, B Ionescu, M Schedl, T Piatrik, C Hauff, M Soleymani, co-located with ACM Multimedia, Barcelona, Spain, October},
pages = {18--19},
year = {2013}
}
ALICE-Assistance for better mobility and improved cognition of elderly blind and visually impaired
Titus Zaharia, Andrei Bursuc, Matej Zorec, Polona Car, Monica Cunil, Davorka Sel
IEEE WIAMIS, 2013
bibtex / poster
@inproceedings{zaharia13,
title = {ALICE-Assistance for better mobility and improved cognition of elderly blind and visually impaired},
author = {Titus, Zaharia and Bursuc, Andrei and Matej, Zorec and Polona, Car and Monica, Cunil and Davorka, Sel},
booktitle = {Proc. International Workshop on Image and Audio Analysis for Multimedia Interactive Services},
year = {2013}
}
Multi-modal query expansion for video object instances retrieval
Andrei Bursuc, Titus Zaharia
IAPR Machine Vision Applications, 2013
bibtex / poster
@inproceedings{bursuc2013a,
author = {Bursuc, Andrei and Titus, Zaharia},
title = {Multi-modal query expansion for video object instances retrieval},
booktitle = {MVA2013 IAPR International Conference on Machine Vision Applications},
pages = {214-217},
year = {2013}
}
ARTEMIS-UBIMEDIA at TRECVID 2012: Instance Search Task
Andrei Bursuc, Titus Zaharia, Olivier Martinot, Françoise Prêteux
TrecVid Workshop, 2012
bibtex / poster
@inproceedings{bursuc2012a,
title = {ARTEMIS-UBIMEDIA at TRECVid 2012: Instance Search Task},
author = {Bursuc, Andrei and Zaharia, Titus and Martinot, Olivier and Pr{\^e}teux, Fran{\c{c}}oise},
booktitle = {Proc. TRECVID Workshop},
year = {2012}
}
Dynamic detection of visual entities
Andrei Bursuc, Titus Zaharia, Françoise Prêteux
IEEE EUSIPCO , 2012
bibtex
@inproceedings{bursuc2012b,
title = {Dynamic detection of visual entities},
author = {Bursuc, Andrei and Zaharia, Titus and Pr{\^e}teux, Fran{\c{c}}oise},
booktitle = {Signal Processing Conference (EUSIPCO), 2012 Proceedings of the 20th European},
pages = {2392--2396},
year = {2012}
}
OVIDIUS: A Web Platform for Video Browsing and Search
Andrei Bursuc, Titus Zaharia, Françoise Prêteux
MMM Video Browser Showdown, 2012
bibtex
@incollection{bursuc2012c,
title = {OVIDIUS: A Web Platform for Video Browsing and Search},
author = {Bursuc, Andrei and Zaharia, Titus and Prêteux, Françoise},
booktitle = {Advances in Multimedia Modeling},
series = {Lecture Notes in Computer Science},
volume = {7131},
year = {2012},
pages = {649-651}
}
Detection of Multiple Instances of Video Objects
Andrei Bursuc, Titus Zaharia, Françoise Prêteux
IEEE/ACM SITIS, 2011
bibtex
@inproceedings{bursuc2011a,
title = {Detection of Multiple Instances of Video Objects},
author = {Bursuc, Andrei and Zaharia, Titus and Pr{\^e}teux, Francoise},
booktitle = {Signal-Image Technology and Internet-Based Systems (SITIS), 2011 Seventh International Conference on},
pages = {446--453},
year = {2011}
}
ARTEMIS-UBIMEDIA at TRECVid 2011: Instance Search
Andrei Bursuc, Titus Zaharia, Olivier Martinot
TrecVid Workshop, 2011
bibtex
@inproceedings{bursuc2011b,
title = {ARTEMIS-UBIMEDIA at TRECVid 2011: Instance Search},
author = {Bursuc, Andrei and Zaharia, Titus and Martinot, Olivier},
booktitle = {Proc. TRECVID Workshop},
year = {2011}
}
Mobile video browsing and retrieval with the OVIDIUS platform
Andrei Bursuc, Titus Zaharia, Françoise Prêteux
ACM Multimedia, 2010
bibtex / poster
@inproceedings{bursuc2010a,
title = {Mobile video browsing and retrieval with the ovidius platform},
author = {Bursuc, Andrei and Zaharia, Titus and Pr{\^e}teux, Fran{\c{c}}oise},
booktitle = {Proceedings of the international conference on Multimedia},
pages = {1659--1662},
year = {2010}
}
OVIDIUS: An on-line video retrieval platform for multi-terminal access
Andrei Bursuc, Titus Zaharia, Bertrand Delezoide, Françoise Prêteux
Content-Based Multimedia Indexing (CBMI), 2010
bibtex
@inproceedings{bursuc2010b,
title = {OVIDIUS: An on-line video retrieval platform for multi-terminal access},
author = {Bursuc, Andrei and Zaharia, Titus and Delezoide, Bertrand and Pr{\^e}teux, Francoise},
booktitle = {Content-Based Multimedia Indexing (CBMI), 2010 International Workshop on},
pages = {1--6},
year = {2010}
}
Copyright notice This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. The following applies to articles published in IEEE journals and conference proceedings: © 1999-2019 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Talks
Jan 2025: Keynote speaker at the Multimedia Modeling Conference - Multi-modal foundation models in the automotive industry
Oct 2024: Lecture at the A Bayesian Odyssey in Uncertainty: from Theoretical Foundations to Real-World Applications tutorial at ECCV 2024
Jun 2024: Invited talk at the Foundation Models for Autonomous Systems workshop at CVPR 2024 - Foundation Models in the Automotive Industry [slides] [video]
Oct 2023: Lecture at The Many Faces of Reliability of Deep Learning for Real-World Deployment tutorial at ICCV 2023 - Uncertainty estimation and next generation ensembles [slides] [video]
Oct 2023: Lecture at The Many Faces of Reliability of Deep Learning for Real-World Deployment tutorial at ICCV 2023 - Neural performance monitoring [slides] [video]
May 2023: Invited talk at MobiliT.AI 2023 forum - The many faces of reliability of visual perception for autonomous driving [video]
Oct 2022: Lecture at Self-Supervision on Wheels: Advances in Self-Supervised Learning from Autonomous Driving Data tutorial at ECCV 2022 - Self-supervised representation learning from autonomous driving data [slides] [video]
Jun 2021: Lecture at Leave Those Nets Alone: Advances in Self-Supervised Learning tutorial at CVPR 2021 - Introduction to self-supervised learning [slides] [video]
Jun 2020: Lecture at Towards Annotation-Efficient Learning: Few-Shot, Self-Supervised, and Incremental Learning Approaches tutorial at CVPR 2020 - Leveraging self-supervision [slides] [video]
Misc
I'm a Sunday school volunteer teacher for Romanian kids in Paris.
During my undergrad period I was actively involved in BEST (Board of European Students of Technology) organising all sorts of events, traveling and trying to improve the lives of future engineers.
I'm fond of education and I have been representing students' views in the VM-BASE project and in the EUGENE network, where I was co-leading the Attractiveness of Engineering Studies track. I have been elected as member of the Admnistrative Council of SEFI (European Society for Engineering Education) 2010-2013.
During highschool I was fortunate to be an Explorer Scout within the Scouts of Romania organization. Be prepared!