no code implementations • 19 Apr 2024 • Xi Wang, Nicolas Dufour, Nefeli Andreou, Marie-Paule Cani, Victoria Fernandez Abrevaya, David Picard, Vicky Kalogeiton
Classifier-Free Guidance (CFG) enhances the quality and condition adherence of text-to-image diffusion models.
1 code implementation • 8 Jan 2024 • Zhi-Song Liu, Robin Courant, Vicky Kalogeiton
In this paper, we propose FunnyNet-W, a model that relies on cross- and self-attention for visual, audio and text data to predict funny moments in videos.
1 code implementation • 15 Dec 2023 • Yasser Benigmim, Subhankar Roy, Slim Essid, Vicky Kalogeiton, Stéphane Lathuilière
Domain Generalized Semantic Segmentation (DGSS) deals with training a model on a labeled source domain with the aim of generalizing to unseen domains during inference.
no code implementations • 8 Nov 2023 • Thanos Delatolas, Vicky Kalogeiton, Dim P. Papadopoulos
To reduce this annotation cost, in this paper, we propose EVA-VOS, a human-in-the-loop annotation framework for video object segmentation.
no code implementations • 22 Sep 2023 • Ariel Kwiatkowski, Vicky Kalogeiton, Julien Pettré, Marie-Paule Cani
Crowd simulation is important for video-games design, since it enables to populate virtual worlds with autonomous avatars that navigate in a human-like manner.
no code implementations • 7 Sep 2023 • Robin Courant, Xi Wang, Marc Christie, Vicky Kalogeiton
BluNF provides a robust and user-friendly 2D blueprint, enabling intuitive scene editing.
1 code implementation • 31 Mar 2023 • Yasser Benigmim, Subhankar Roy, Slim Essid, Vicky Kalogeiton, Stéphane Lathuilière
Departing from the common notion of transferring only the target ``texture'' information, we leverage text-to-image diffusion models (e. g., Stable Diffusion) to generate a synthetic target dataset with photo-realistic images that not only faithfully depict the style of the target domain, but are also characterized by novel scenes in diverse contexts.
Data Augmentation One-shot Unsupervised Domain Adaptation +2
1 code implementation • 22 Mar 2023 • Leo Milecki, Vicky Kalogeiton, Sylvain Bodard, Dany Anglicheau, Jean-Michel Correas, Marc-Olivier Timsit, Maria Vakalopoulou
Our goal is to learn meaningful manifolds of renal transplant DCE MRI, interesting for the prognosis of the transplant or patient status (2, 3, and 4 years after the transplant), fully exploiting the limited available multi-modal data most efficiently.
no code implementations • 21 Mar 2023 • Robin Courant, Maika Edberg, Nicolas Dufour, Vicky Kalogeiton
For image classification, the most common Transformer Architecture uses only the Transformer Encoder in order to transform the various input tokens.
no code implementations • 11 Feb 2023 • Ariel Kwiatkowski, Vicky Kalogeiton, Julien Pettré, Marie-Paule Cani
We also show experimentally that agents with non-exponential discounting trained via UGAE outperform variants trained with Monte Carlo advantage estimation.
1 code implementation • 10 Oct 2022 • Nicolas Dufour, David Picard, Vicky Kalogeiton
In this work, we introduce SCAM (Semantic Cross Attention Modulation), a system that encodes rich and diverse information in each semantic region of the image (including foreground and background), thus achieving precise generation with emphasis on fine details.
Ranked #1 on Pose Transfer on CelebAMask-HQ
1 code implementation • 19 Sep 2022 • Ariel Kwiatkowski, Vicky Kalogeiton, Julien Pettré, Marie-Paule Cani
Each of these choices has a significant, and potentially nontrivial impact on the results, and so researchers should be mindful about choosing and reporting them in their work.
no code implementations • 7 Mar 2022 • Ariel Kwiatkowski, Eduardo Alvarado, Vicky Kalogeiton, C. Karen Liu, Julien Pettré, Michiel Van de Panne, Marie-Paule Cani
Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment.
1 code implementation • 28 Feb 2022 • Zhi-Song Liu, Li-Wen Wang, Wan-Chi Siu, Vicky Kalogeiton
Moreover, it can mimic the styles of one or many artists to achieve attractive results, thus highlighting a promising direction in image style transfer.
1 code implementation • 13 Oct 2021 • Zhi-Song Liu, Vicky Kalogeiton, Marie-Paule Cani
Modern works on style transfer focus on transferring style from a single image.
no code implementations • 20 May 2021 • Andrew Brown, Vicky Kalogeiton, Andrew Zisserman
In this paper we make contributions to address both these deficiencies: first, we introduce a Multi-Modal High-Precision Clustering algorithm for person-clustering in videos using cues from several modalities (face, body, and voice).
1 code implementation • 6 Jan 2021 • Manuel J. Marin-Jimenez, Vicky Kalogeiton, Pablo Medina-Suarez, Andrew Zisserman
For this purpose, we propose LAEO-Net++, a new deep CNN for determining LAEO in videos.
2 code implementations • ECCV 2020 • Andrew Brown, Weidi Xie, Vicky Kalogeiton, Andrew Zisserman
Optimising a ranking-based metric, such as Average Precision (AP), is notoriously challenging due to the fact that it is non-differentiable, and hence cannot be optimised directly using gradient-descent methods.
Ranked #4 on Vehicle Re-Identification on VehicleID Medium
1 code implementation • CVPR 2019 • Manuel J. Marin-Jimenez, Vicky Kalogeiton, Pablo Medina-Suarez, Andrew Zisserman
For this purpose, we propose LAEO-Net, a new deep CNN for determining LAEO in videos.
no code implementations • ICCV 2017 • Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari, Cordelia Schmid
dog and cat jumping, enabling to detect actions of an object without training with these object-actions pairs.
2 code implementations • ICCV 2017 • Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari, Cordelia Schmid
We propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, i. e., sequences of bounding boxes with associated scores.
Spatio-Temporal Action Localization Temporal Action Localization
1 code implementation • 6 Jan 2015 • Vicky Kalogeiton, Vittorio Ferrari, Cordelia Schmid
Object detection is one of the most important challenges in computer vision.