Search Results for author: Antitza Dantcheva

Found 19 papers, 7 papers with code

LAC: Latent Action Composition for Skeleton-based Action Segmentation

no code implementations28 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.

Action Segmentation Contrastive Learning +2

Attending Generalizability in Course of Deep Fake Detection by Exploring Multi-task Learning

no code implementations25 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.

Multi-Task Learning

Self-Supervised Video Representation Learning via Latent Time Navigation

no code implementations10 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.

Action Classification Action Recognition +2

LEO: Generative Latent Image Animator for Human Video Synthesis

5 code implementations6 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.

Disentanglement Video Editing

LAC - Latent Action Composition for Skeleton-based Action Segmentation

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.

Action Segmentation Contrastive Learning +2

ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting

1 code implementation31 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.

Action Classification Action Recognition +4

Latent Image Animator: Learning to Animate Images via Latent Space Navigation

no code implementations17 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.

Beyond the Visible: A Survey on Cross-spectral Face Recognition

no code implementations12 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.

Face Recognition

Latent Image Animator: Learning to animate image via latent space navigation

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.

Image Animation Video Generation

Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning

no code implementations3 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.

Segmentation

Data Uncertainty Guided Noise-aware Preprocessing Of Fingerprints

no code implementations2 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.

How Unique Is a Face: An Investigative Study

no code implementations9 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.

Face Recognition

InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation

no code implementations8 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.

Generative Adversarial Network Video Generation

G3AN: Disentangling Appearance and Motion for Video Generation

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.

Video Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.