no code implementations • 9 Apr 2024 • Arnab Dey, Di Yang, Antitza Dantcheva, Jean Martinet
In recent advancements in novel view synthesis, generalizable Neural Radiance Fields (NeRF) based methods applied to human subjects have shown remarkable results in generating novel views from few images.
no code implementations • 9 Apr 2024 • Arnab Dey, Di Yang, Rohith Agaram, Antitza Dantcheva, Andrew I. Comport, Srinath Sridhar, Jean Martinet
In this paper, we introduce a novel approach, termed GHNeRF, designed to address these limitations by learning 2D/3D joint locations of human subjects with NeRF representation.
no code implementations • 28 Aug 2023 • Di Yang, Yaohui Wang, Antitza Dantcheva, Quan Kong, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond
In this context, we propose Latent Action Composition (LAC), a novel self-supervised framework aiming at learning from synthesized composable motions for skeleton-based action segmentation.
no code implementations • 25 Aug 2023 • Pranav Balaji, Abhijit Das, Srijan Das, Antitza Dantcheva
This work explores various ways of exploring multi-task learning (MTL) techniques aimed at classifying videos as original or manipulated in cross-manipulation scenario to attend generalizability in deep fake scenario.
no code implementations • 10 May 2023 • Di Yang, Yaohui Wang, Quan Kong, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond
Self-supervised video representation learning aimed at maximizing similarity between different temporal segments of one video, in order to enforce feature persistence over time.
5 code implementations • 6 May 2023 • Yaohui Wang, Xin Ma, Xinyuan Chen, Antitza Dantcheva, Bo Dai, Yu Qiao
Our key idea is to represent motion as a sequence of flow maps in the generation process, which inherently isolate motion from appearance.
1 code implementation • 2 Jan 2023 • Hao Chen, Yaohui Wang, Benoit Lagadec, Antitza Dantcheva, Francois Bremond
This work focuses on unsupervised representation learning in person re-identification (ReID).
no code implementations • ICCV 2023 • Di Yang, Yaohui Wang, Antitza Dantcheva, Quan Kong, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond
In this context, we propose Latent Action Composition (LAC), a novel self-supervised framework aiming at learning from synthesized composable motions for skeleton-based action segmentation.
1 code implementation • 31 Aug 2022 • Di Yang, Yaohui Wang, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond
Current self-supervised approaches for skeleton action representation learning often focus on constrained scenarios, where videos and skeleton data are recorded in laboratory settings.
no code implementations • 19 Aug 2022 • Indu Joshi, Marcel Grimmer, Christian Rathgeb, Christoph Busch, Francois Bremond, Antitza Dantcheva
This survey is intended for researchers and practitioners in the field of human analysis.
no code implementations • 17 Mar 2022 • Yaohui Wang, Di Yang, Francois Bremond, Antitza Dantcheva
Specifically, motion in generated video is constructed by linear displacement of codes in the latent space.
no code implementations • 12 Jan 2022 • David Anghelone, Cunjian Chen, Arun Ross, Antitza Dantcheva
Secondly, we discuss the appropriate spectral bands for face recognition and discuss recent CFR methods, placing emphasis on deep neural networks.
1 code implementation • ICLR 2022 • Yaohui Wang, Di Yang, Francois Bremond, Antitza Dantcheva
Deviating from such models, we here introduce Latent Image Animator (LIA), a self-supervised auto-encoder that evades need for structure representation.
1 code implementation • 19 Jul 2021 • Di Yang, Yaohui Wang, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca, Francois Bremond
This is achieved by learning an optimal dependency matrix from the uniform distribution based on a multi-head attention mechanism.
Ranked #1 on Skeleton Based Action Recognition on UPenn Action
no code implementations • 3 Jul 2021 • Indu Joshi, Ayush Utkarsh, Riya Kothari, Vinod K Kurmi, Antitza Dantcheva, Sumantra Dutta Roy, Prem Kumar Kalra
In order to save the human effort in generating annotations required by state-of-the-art, we propose a fingerprint roi segmentation model which aligns the features of fingerprint images derived from the unseen sensor such that they are similar to the ones obtained from the fingerprints whose ground truth roi masks are available for training.
no code implementations • 2 Jul 2021 • Indu Joshi, Ayush Utkarsh, Riya Kothari, Vinod K Kurmi, Antitza Dantcheva, Sumantra Dutta Roy, Prem Kumar Kalra
The effectiveness of fingerprint-based authentication systems on good quality fingerprints is established long back.
no code implementations • 9 Feb 2021 • Michal Balazia, S L Happy, Francois Bremond, Antitza Dantcheva
Face recognition has been widely accepted as a means of identification in applications ranging from border control to security in the banking sector.
no code implementations • 8 Jan 2021 • Yaohui Wang, Francois Bremond, Antitza Dantcheva
We design the architecture of InMoDeGAN-generator in accordance to proposed Linear Motion Decomposition, which carries the assumption that motion can be represented by a dictionary, with related vectors forming an orthogonal basis in the latent space.
2 code implementations • CVPR 2021 • Hao Chen, Yaohui Wang, Benoit Lagadec, Antitza Dantcheva, Francois Bremond
In this context, we propose a mesh-based view generator.
no code implementations • 26 Mar 2020 • Xiaobai Li, Hu Han, Hao Lu, Xuesong Niu, Zitong Yu, Antitza Dantcheva, Guoying Zhao, Shiguang Shan
Remote measurement of physiological signals from videos is an emerging topic.
1 code implementation • CVPR 2020 • Yaohui Wang, Piotr Bilinski, Francois Bremond, Antitza Dantcheva
Creating realistic human videos entails the challenge of being able to simultaneously generate both appearance, as well as motion.