Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Alletto, Stefano"'
Understanding human motion from video is essential for a range of applications, including pose estimation, mesh recovery and action recognition. While state-of-the-art methods predominantly rely on transformer-based architectures, these approaches ha
Externí odkaz:
http://arxiv.org/abs/2404.10880
In this paper we present a novel approach for bottom-up multi-person 3D human pose estimation from monocular RGB images. We propose to use high resolution volumetric heatmaps to model joint locations, devising a simple and effective compression metho
Externí odkaz:
http://arxiv.org/abs/2004.00329
Autor:
Alletto, Stefano, Huang, Shenyang, Francois-Lavet, Vincent, Nakata, Yohei, Rabusseau, Guillaume
Almost all neural architecture search methods are evaluated in terms of performance (i.e. test accuracy) of the model structures that it finds. Should it be the only metric for a good autoML approach? To examine aspects beyond performance, we propose
Externí odkaz:
http://arxiv.org/abs/2003.01181
When you see a person in a crowd, occluded by other persons, you miss visual information that can be used to recognize, re-identify or simply classify him or her. You can imagine its appearance given your experience, nothing more. Similarly, AI solut
Externí odkaz:
http://arxiv.org/abs/1901.08097
We address unsupervised optical flow estimation for ego-centric motion. We argue that optical flow can be cast as a geometrical warping between two successive video frames and devise a deep architecture to estimate such transformation in two stages.
Externí odkaz:
http://arxiv.org/abs/1706.00322
Despite the advent of autonomous cars, it's likely - at least in the near future - that human attention will still maintain a central role as a guarantee in terms of legal responsibility during the driving task. In this paper we study the dynamics of
Externí odkaz:
http://arxiv.org/abs/1611.08215
Multi-object tracking has recently become an important area of computer vision, especially for Advanced Driver Assistance Systems (ADAS). Despite growing attention, achieving high performance tracking is still challenging, with state-of-the- art syst
Externí odkaz:
http://arxiv.org/abs/1609.09156
With the spread of wearable devices and head mounted cameras, a wide range of application requiring precise user localization is now possible. In this paper we propose to treat the problem of obtaining the user position with respect to a known enviro
Externí odkaz:
http://arxiv.org/abs/1607.08434
Publikováno v:
In Computer Vision and Image Understanding April 2017 157:274-283
Publikováno v:
In Pattern Recognition December 2015 48(12):4082-4096