Vicky Kalogeiton

vicky.jpg
· · · ·

I am the Assistant Professor (MCF) in Computer Vision at École Polytechnique. I am affiated with the VISTA team (previously GeoViC) at the Computer Science Laboratory (LIX). My research interests focus on multimodal learning split into three axes: generativeAI (text-to-image generation), video understanding using text and audio, and multimodal medical applications! At Polytechnique, I am the main genAI researcher and I publish papers in the most prestigious computer vision conferences (CVPR, ICCV, ECCV) and top journals (T-PAMI, IJCV).

Previously, I was a research fellow at VGG, University of Oxford, where I worked with Andrew Zisserman. I completed my PhD at the CALVIN group, University of Edinburgh and the THOTH team, INRIA Grenoble (previous name LEAR) advised by Vittorio Ferrari and Cordelia Schmid.

I am always looking for new collaborations and students! Email me, if you want to discuss or work with me!

News

People

Current Alumni

Selected publications

  1. ET the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness
    Robin Courant, Nicolas Dufour, Xi Wang, and 2 more authors
    In European Conference on Computer Vision (ECCV) 2024
  2. Your diffusion model is an implicit synthetic image detector
    Xi Wang, and Vicky Kalogeiton
    In European Conference on Computer Vision Workshop (ECCV-W) 2024
  3. Bridging Text and Image for Artist Style Transfer via Contrastive Learning
    Zhi-Song Liu, Li-Wen Wang, Jun Xiao, and 1 more author
    In European Conference on Computer Vision Workshop (ECCV-W) 2024
  4. Conditional Gradient-based Textual Inversion
    Xi Wang, and Vicky Kalogeiton
    In European Conference on Computer Vision Workshop (ECCV-W) 2024
  5. Don’t drop your samples! Coherence-aware training benefits Conditional diffusion
    Nicolas Dufour, Victor Besnier, Vicky Kalogeiton, and 1 more author
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024
  6. ADAPT: Multimodal Learning for Detecting Physiological Changes under Missing Modalities
    Julie Mordacq, Leo Milecki, Maria Vakalopoulou, and 2 more authors
    In Medical Imaging with Deep Learning (MIDL) 2024
  7. Collaborating Foundation models for Domain Generalized Semantic Segmentation
    Yasser Benigmim, Subhankar Roy, Slim Essid, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024
  8. FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild
    Zhi-Song Liu, Robin Courant, and Vicky Kalogeiton
    In International Journal of Computer Vision (IJCV) 2024
  9. Learning the What and How of Annotation in Video Object Segmentation
    Thanos Delatolas, Vicky Kalogeiton, and Dim P Papadopoulos
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024
  10. BluNF: Blueprint Neural Field
    Robin Courant, Xi Wang, Marc Christie, and 1 more author
    In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshop (ICCV-W) 2023
  11. MEDIMP: 3D Medical Images with clinical Prompts from limited tabular data for renal transplantation
    Leo Milecki, Vicky Kalogeiton, Sylvain Bodard, and 4 more authors
    In Medical Imaging with Deep Learning 2023
  12. One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models
    Yasser Benigmim, Subhankar Roy, Slim Essid, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPR-W) 2023
  13. Reward Function Design for Crowd Simulation via Reinforcement Learning
    Ariel Kwiatkowski, Vicky Kalogeiton, Julien Pettré, and 1 more author
    In Proceedings of the 16th ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG) 2023
  14. Machine Learning for Brain Disorders: Transformers and Visual Transformers
    Robin Courant, Maika Edberg, Nicolas Dufour, and 1 more author
    Book Chapter Machine Learning for Brain Disorders, Springer 2023
  15. Name Your Style: Text-Guided Artistic Style Transfer
    Zhi-Song Liu, Li-Wen Wang, Wan-Chi Siu, and 1 more author
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPR-W) 2023
  16. FunnyNet: Audiovisual Learning of Funny Moments in Videos
    Zhi-Song Liu, Robin Courant, and Vicky Kalogeiton
    In Asian Conference on Computer Vision (ACCV) 2022
  17. SCAM! Transferring humans between images with Semantic Cross Attention Modulation
    Nicolas Dufour, David Picard, and Vicky Kalogeiton
    In European Conference on Computer Vision (ECCV) 2022
  18. Understanding reinforcement learned crowds
    Ariel Kwiatkowski, Vicky Kalogeiton, Julien Pettré, and 1 more author
    In Motion, Interaction and Games (MIG) 2022
  19. Contrastive Masked Transformers for Forecasting Renal Transplant Function
    Leo Milecki, Vicky Kalogeiton, Sylvain Bodard, and 4 more authors
    In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022
  20. Constrative Learning for Kidney Transplant Analysis using MRI data and Deep Convolutional Networks
    Leo Milecki, Vicky Kalogeiton, Sylvain Bodard, and 4 more authors
    In Medical Imaging with Deep Learning (MIDL) 2022
  21. A survey on reinforcement learning methods in character animation
    Ariel Kwiatkowski, Eduardo Alvarado, Vicky Kalogeiton, and 4 more authors
    In Computer Graphics Forum (Eurographics State-of-the-Art Report); arXiv:2203.04735 2022
  22. Name Your Style: An Arbitrary Artist-aware Image Style Transfer
    Zhi-Song Liu, Li-Wen Wang, Wan-Chi Siu, and 1 more author
    arXiv preprint arXiv:2202.13562 2022
  23. UGaitNet: Multimodal Gait Recognition With Missing Input Modalities
    Manuel J Marı́n-Jiménez, Francisco M Castro, Rubén Delgado-Escano, and 2 more authors
    IEEE Transactions on Information Forensics and Security (TIFS) 2021
  24. Face, body, voice: Video person-clustering with multiple modalities
    Andrew Brown, Vicky Kalogeiton, and Andrew Zisserman
    2021
  25. High-Level Features for Movie Style Understanding
    Robin Courant, Christophe Lino, Marc Christie, and 1 more author
    In ICCV 2021 Workshop on AI for Creative Video Editing and Understanding (ICCV-W) 2021
  26. Multimodal Gait Recognition Under Missing Modalities
    Rubén Delgado-Escano, Francisco M Castro, Nicolás Guil, and 2 more authors
    In 2021 IEEE International Conference on Image Processing (ICIP) 2021
  27. Me-NDT: Neural-backed Decision Tree for visual Explainability of deep Medical models
    Guanghui Fu, Ruiqian Wang, Jianqiang Li, and 2 more authors
    In Medical Imaging with Deep Learning (MIDL) 2021
  28. Multiple Style Transfer Via Variational Autoencoder
    Zhi-Song Liu, Vicky Kalogeiton, and Marie-Paule Cani
    In 2021 IEEE International Conference on Image Processing (ICIP) 2021
  29. LAEO-Net++: revisiting people Looking At Each Other in videos
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021
  30. Constrained video face clustering using 1NN relations
    V Kalogeiton, and A Zisserman
    In The British Machine Vision Conference (BMVC) 2020
  31. Smooth-AP: Smoothing the path towards large-scale image retrieval
    Andrew Brown, Weidi Xie, Vicky Kalogeiton, and 1 more author
    In European Conference on Computer Vision (ECCV); arXiv:2007.12163 2020
  32. Real-time active SLAM and obstacle avoidance for an autonomous robot based on stereo vision
    Vicky Kalogeiton, Konstantinos Ioannidis, G Ch Sirakoulis, and 1 more author
    Cybernetics and Systems 2019
  33. LAEO-Net: revisiting people Looking At Each Other in videos
    Manuel J Marin-Jimenez, Vicky Kalogeiton, Pablo Medina-Suarez, and 1 more author
    In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2019
  34. Localizing spatially and temporally objects and actions in videos
    Vicky Kalogeiton
    PhD Thesis, University of Edinburgh, UK, Inria Grenoble 2017
  35. Joint learning of object and action detectors
    Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari, and 1 more author
    In Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2017
  36. Action tubelet detector for spatio-temporal action localization
    Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari, and 1 more author
    In Proceedings of the IEEE International Conference on Computer Vision 2017
  37. Programmable crossbar quantum-dot cellular automata circuits
    Vicky Kalogeiton, Dim P Papadopoulos, Orestis Liolis, and 3 more authors
    IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2017
  38. Analysing domain shift factors between videos and images for object detection
    Vicky Kalogeiton, Vittorio Ferrari, and Cordelia Schmid
    IEEE transactions on pattern analysis and machine intelligence (TPAMI) 2016
  39. Bio-inspired electronic systems for crowd evacuation with bio-robot guidance
    Vicky Kalogeiton
    2015
  40. Cellular automaton model of crowd evacuation inspired by slime mould
    Vicky Kalogeiton, Dim P Papadopoulos, IP Georgilas, and 2 more authors
    International Journal of General Systems (IJGS) 2015
  41. Biomimicry of crowd evacuation with a slime mould cellular automaton model
    Vicky Kalogeiton, Dim P Papadopoulos, Ioannis P Georgilas, and 2 more authors
    In Computational Intelligence, Medicine and Biology 2015
  42. Hey Physarum! Can you Perform SLAM?
    Vicky Kalogeiton, Dim P Papadopoulos, and Georgios Ch Sirakoulis
    International Journal of Unconventional Computing 2014
  43. Morphological Edge Detector Implemented in Quantum Cellular Automata
    Orestis Liolis, Vicky Kalogeiton, Dim P Papadopoulos, and 3 more authors
    In Imaging Systems and Techniques (IST), 2013 IEEE International Conference on 2013
  44. Automatic summarization and annotation of videos with lack of metadata information
    Dim P Papadopoulos, Vicky Kalogeiton, Savvas A Chatzichristofis, and 1 more author
    Expert Systems with Applications 2013
  45. DUTH does Probabilities of Relevance at the Legal Track
    Dim P Papadopoulos, Vicky Kalogeiton, and Avi Arampatzis
    In The Nineteenth Text REtrieval Conference Proceedings (TREC 2010). National Institute of Standards and Technology (NIST) the Defense Advanced Research Projects Agency (DARPA) and the Advanced Research and Development Activity (ARDA) 2011
  46. A novel video summarization method based on the compact composite descriptors and fuzzy classifier
    Vicky Kalogeiton,  Papadopoulos, Dim P, and 2 more authors
    In 4th international conference for undergraduate and postgraduate students in computer engineering, informatics, related technologies and applications 2010

Teaching

2023-2024 2022-2023 2021-2022 2020-2021 Before 2020
  • Introduction to Computer Vision. Guest Lectures Lady Margaret Hall, St Hugh’s College, University of Oxford, 2019
  • Introduction to Computer Vision. Term Lectures, Oxford Royale Academy, 2018-2021

Misc

Service
  • Area Chair. ECCV 2024, ACCV 2024, WACV 2024, ICCV 2023, ACCV 2022, CVPR 2021
  • Associate Editor. CMBBE: Imaging & Visualization 2017-2022
  • Conferences Program committee.
    • 2023: CVPR
    • 2022: CVPR
    • 2021: ICCV, TCSVT, AIMLSystems, AAAI, WiCV ICCV, WiCV CVPR
    • 2020: ECCV, CVPR, ACCV, BMVC, TCSVT, WiCV ECCV
    • 2019: CVPR, ICCV, BMVC, TCSVT, ICCV-W 'Neural Architects'
    • 2018: ECCV, CVPR, ACCV, NeurIPS, IVC, IMAVIS, ECCV-W 'Optical flow', WiCV CVPR, WiCV ECCV
    • 2017: TCSVT
  • Journal Reviewer.
    • 2023: TPAMI
    • 2022: TPAMI, CVIU, TIP
    • 2021: TPAMI, IJCN
    • 2020: TPAMI, IJCV, CVIU
    • 2019: TPAMI, IJCV, CVIU, TOM, TIP
    • 2018: TPAMI, IJCV, CVIU, TOM, TIP
Awards Miscellaneous