Vicky Kalogeiton

Selected publications

1. 

   Balancing Frequencies and Pixels in Flow Matching

   Lucas Degeorge, Paul Couairon, Arijit Ghosh, and 3 more authors

   In The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) 2026

   PDF Website arXiv
2. 

   AR-Edit: Training-Free Autoregressive Video Editing without Inversion

   Hovhannes Margaryan, Quentin Bammey, Christian Sandor, and 1 more author

   In The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) 2026

   Website
3. 

   FakeParts: a New Family of AI-Generated DeepFakes

   Ziyi Liu, Firas Gabetni, Awais Hussain Sani, and 5 more authors

   In The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) – Datasets and Benchmarks Track 2026

   PDF Website Code Dataset arXiv
4. 

   From Proxemic Blindness Toward Geometry-Aware Proxemic Recognition in Vision-Language Models

   Isabel Jiménez-Velasco, Rafael Muñoz-Salinas, Manuel J.* Marín-Jiménez, and 1 more author

   In International Journal of Computer Vision (IJCV) 2026
5. 

   What Images Cannot Say: Language-Guided Olfactory Representation Learning

   Eleftherios Tsonis, Xi Wang, and Vicky Kalogeiton

   In European Conference on Computer Vision (ECCV) 2026

   Website arXiv
6. 

   TAKE 85: Testing Audiovisual filmmaKer’s intEnt across 85 Hours of Film

   Kaishuu Shinozaki-Conefrey, Olivier Pascaud, Robin Courant, and 3 more authors

   In European Conference on Computer Vision Workshops (ECCV-W) 2026

   PDF Dataset
7. 

   Long story short: Story-level video understanding from 20k short films

   Ridouane Ghermi, Xi Wang, Vicky Kalogeiton, and 1 more author

   In International Journal of Computer Vision (IJCV) 2026

   PDF Website Dataset arXiv
8. 

   MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency

   Nicolas Dufour, Lucas Degeorge, Arijit Ghosh, and 2 more authors

   In International Conference on Machine Learning (ICML) 2026

   arXiv
9. 

   IDES T: Assessing Self-Supervised Learning Representations via Intrinsic Dimension

   Julie Mordacq, Vicky Kalogeiton, and Steve Oudot

   In International Conference on Machine Learning (ICML) 2026

   arXiv
10. 

    Pulp Motion: framing-aware multimodal camera and human motion generation

    Robin Courant, Xi Wang, David Loiseaux, and 2 more authors

    In International Conference on Learning Representations (ICLR) 2026

    Website Code Hal arXiv
11. 

    Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings

    Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière, and 1 more author

    In International Conference on Learning Representations (ICLR) 2026

    Hal arXiv
12. 

    Long Story Short: Story-level Video Understanding from 20K Short Films

    Ridouane Ghermi, Wang Xi, Vicky Kalogeiton, and 1 more author

    In International Journal of Computer Vision (IJCV) 2026

    Website Code Dataset arXiv
13. 

    ProxiVideoFriends: Revisiting Proxemics through Temporal and Social Reasoning

    Isabel Jiménez-Velasco, Rafael Muñoz-Salinas, Vicky Kalogeiton, and 1 more author

    In Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2026

    [Best Paper Award Nomination] Hal
14. 

    When Surgery Meets the Unknown: Uncertainty-Aware Open-Set Recognition for Surgery Phase Classification

    Stefan Geyer, Vicky Kalogeiton, and Alina Roitberg

    In Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP) 2026

    Hal
15. 

    T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning

    Julie Mordacq, David Loiseaux, Vicky Kalogeiton, and 1 more author

    In The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS) 2025

    PDF Website Code arXiv
16. 

    Di[M]o: Distilling masked diffusion models into one-step generator

    Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière, and 1 more author

    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2025

    PDF Website Code arXiv
17. 

    Around the world in 80 timesteps: A generative approach to global visual geolocation

    Nicolas Dufour, Vicky* Kalogeiton, David* Picard, and 1 more author

    In Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) 2025

    PDF Website Code arXiv
18. 

    Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance

    Luc Boudier, Loris Manganell, Eleftherios Tsonis, and 2 more authors

    In The British Machine Vision Conference (BMVC) 2025

    PDF Website Code arXiv
19. 

    AKiRa: Augmentation Kit on Rays for optical video generation

    Xi Wang, Robin Courant, Marc Christie, and 1 more author

    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025

    PDF Website Code arXiv
20. 

    Lead: Latent realignment for human motion diffusion

    Nefeli Andreou, Xi Wang, Victoria Fernández Abrevaya, and 3 more authors

    In Computer Graphics Forum (CFG) 2025

    PDF
21. 

    Story-level multimodal generativeAI: from understanding to generating visual data using multiple modalities

    Vicky Kalogeiton

    In Habilitation to direct research (HDR) 2024

    Hal
22. 

    Analysis of Classifier-Free Guidance Weight Schedulers

    Xi Wang, Nicolas Dufour, Nefeli Andreou, and 4 more authors

    In Transactions on Machine Learning Research (TMLR) 2024

    PDF Hal arXiv
23. 

    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

    Website Code arXiv
24. 

    Your diffusion model is an implicit synthetic image detector

    Xi Wang, and Vicky Kalogeiton

    In European Conference on Computer Vision Workshop (ECCV-W) 2024

    Website Hal
25. 

    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

    arXiv
26. 

    Conditional Gradient-based Textual Inversion

    Xi Wang, and Vicky Kalogeiton

    In European Conference on Computer Vision Workshop (ECCV-W) 2024

    Hal
27. 

    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

    PDF Website Code arXiv
28. 

    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

    PDF Code
29. 

    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

    PDF Code arXiv
30. 

    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

    PDF Website Code Dataset arXiv
31. 

    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

    PDF Website Code
32. 

    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

    PDF Code
33. 

    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

    PDF Code
34. 

    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

    PDF Code arXiv
35. 

    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

    PDF
36. 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

    PDF arXiv
37. 

    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

    PDF
38. 

    FunnyNet: Audiovisual Learning of Funny Moments in Videos

    Zhi-Song Liu, Robin Courant, and Vicky Kalogeiton

    In Asian Conference on Computer Vision (ACCV) 2022

    [Oral] [Student Honorable mention Award] PDF Website Code Dataset arXiv
39. 

    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

    Website Code Video Poster arXiv
40. 

    Understanding reinforcement learned crowds

    Ariel Kwiatkowski, Vicky Kalogeiton, Julien Pettré, and 1 more author

    In Motion, Interaction and Games (MIG) 2022

    Hal arXiv
41. 

    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

    Website Code Hal
42. 

    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

    PDF Website Code
43. 

    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

    Hal arXiv
44. 

    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

    arXiv
45. 

    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

    PDF Website Code
46. 

    Face, body, voice: Video person-clustering with multiple modalities

    Andrew Brown, Vicky Kalogeiton, and Andrew Zisserman

    2021

    [Spotlight] Website Code Dataset Hal arXiv
47. 

    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

    [Best Paper Award] PDF Video Hal
48. 

    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

    Website Code Colab Hal
49. 

    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

    PDF Hal
50. 

    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

    PDF Website Poster Hal
51. 

    LAEO-Net++: revisiting people Looking At Each Other in videos

    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021

    PDF Website Code Dataset Hal arXiv
52. 

    Constrained video face clustering using 1NN relations

    V Kalogeiton, and A Zisserman

    In The British Machine Vision Conference (BMVC) 2020

    PDF Website Code Dataset
53. 

    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

    PDF Website Code arXiv
54. 

    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
55. 

    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

    PDF Website Code Dataset arXiv
56. 

    Localizing spatially and temporally objects and actions in videos

    Vicky Kalogeiton

    PhD Thesis, University of Edinburgh, UK, Inria Grenoble 2017

    PDF Hal
57. 

    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

    PDF Website Code Hal
58. 

    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

    PDF Website Code Hal arXiv
59. 

    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

    arXiv
60. 

    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

    PDF Website Dataset arXiv
61. 

    Bio-inspired electronic systems for crowd evacuation with bio-robot guidance

    Vicky Kalogeiton

    2015

    PDF
62. 

    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

    PDF
63. 

    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

    PDF
64. 

    Hey Physarum! Can you Perform SLAM?

    Vicky Kalogeiton, Dim P Papadopoulos, and Georgios Ch Sirakoulis

    International Journal of Unconventional Computing 2014
65. 

    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

    PDF
66. 

    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

    PDF
67. 

    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

    PDF
68. 

    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

    [Best Paper Award]