Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Soubarna Banik"'
Autor:
Kiwull, Lorenz, Schroeder, Andreas Sebastian, Garcia, Alejandro Mendoza, Koller, Valentin, Streil, Gabriele, Brokel, Gundl, Eschermann, Kirsten, Rueger, Matthias, Soubarna Banik, Bauer, Christin, Edler-Golla, Estelle, Hook, Daniel, Heinen, Florian, Berweck, Steffen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::52b67d58890f8a01eeb9e38dc29dee3e
State-of-the-art reinforcement learning algorithms predominantly learn a policy from either a numerical state vector or images. Both approaches generally do not take structural knowledge of the task into account, which is especially prevalent in robo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2280dd057a80453cf7d2c1154731862f
3D human pose estimation is a difficult task, due to challenges such as occluded body parts and ambiguous poses. Graph convolutional networks encode the structural information of the human skeleton in the form of an adjacency matrix, which is benefic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e2dc7138fdc761df44d7158d0d1326b0
http://arxiv.org/abs/2105.10379
http://arxiv.org/abs/2105.10379
Posture estimation using a single depth camera has become a useful tool for analyzing movements in rehabilitation. Recent advances in posture estimation in computer vision research have been possible due to the availability of large-scale pose datase
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::10b737d3c183a196c437fe3f13b2cba7
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030871550
ICVS
ICVS
We propose a weakly-supervised approach for object localization based on top-down attention which is able to consider both attributes and object classes as attentional cues. This enables to not only search for objects but additionally for objects wit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b740f6cbea49060dab5f0d3654cb06c
https://doi.org/10.1007/978-3-030-87156-7_3
https://doi.org/10.1007/978-3-030-87156-7_3