Zobrazeno 1 - 10
of 128
pro vyhledávání: '"Dantcheva, Antitza"'
Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of \textit{video} classi
Externí odkaz:
http://arxiv.org/abs/2411.02065
Autor:
Dey, Arnab, Yang, Di, Agaram, Rohith, Dantcheva, Antitza, Comport, Andrew I., Sridhar, Srinath, Martinet, Jean
Recent advances in Neural Radiance Fields (NeRF) have demonstrated promising results in 3D scene representations, including 3D human representations. However, these representations often lack crucial information on the underlying human pose and struc
Externí odkaz:
http://arxiv.org/abs/2404.06246
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. However, this generalization ability cannot c
Externí odkaz:
http://arxiv.org/abs/2404.06152
Autor:
Yang, Di, Wang, Yaohui, Dantcheva, Antitza, Kong, Quan, Garattoni, Lorenzo, Francesca, Gianpiero, Bremond, Francois
Skeleton-based action segmentation requires recognizing composable actions in untrimmed videos. Current approaches decouple this problem by first extracting local visual features from skeleton sequences and then processing them by a temporal model to
Externí odkaz:
http://arxiv.org/abs/2308.14500
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. The dataset used in our evaluati
Externí odkaz:
http://arxiv.org/abs/2308.13503
Autor:
Yang, Di, Wang, Yaohui, Kong, Quan, Dantcheva, Antitza, Garattoni, Lorenzo, Francesca, Gianpiero, Bremond, Francois
Self-supervised video representation learning aimed at maximizing similarity between different temporal segments of one video, in order to enforce feature persistence over time. This leads to loss of pertinent information related to temporal relation
Externí odkaz:
http://arxiv.org/abs/2305.06437
Spatio-temporal coherency is a major challenge in synthesizing high quality videos, particularly in synthesizing human videos that contain rich global and local deformations. To resolve this challenge, previous approaches have resorted to different f
Externí odkaz:
http://arxiv.org/abs/2305.03989
This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the representation similarity between two augmented views of a same image
Externí odkaz:
http://arxiv.org/abs/2301.00725
Autor:
Yang, Di, Wang, Yaohui, Dantcheva, Antitza, Garattoni, Lorenzo, Francesca, Gianpiero, Bremond, Francois
Current self-supervised approaches for skeleton action representation learning often focus on constrained scenarios, where videos and skeleton data are recorded in laboratory settings. When dealing with estimated skeleton data in real-world videos, s
Externí odkaz:
http://arxiv.org/abs/2209.00065
Autor:
Joshi, Indu, Grimmer, Marcel, Rathgeb, Christian, Busch, Christoph, Bremond, Francois, Dantcheva, Antitza
Deep neural networks have become prevalent in human analysis, boosting the performance of applications, such as biometric recognition, action recognition, as well as person re-identification. However, the performance of such networks scales with the
Externí odkaz:
http://arxiv.org/abs/2208.09191