Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Georgios Pavlakos"'
Autor:
Karl Schmeckpeper, Kostas Daniilidis, Daniel E. Koditschek, Vasileios Vasilopoulos, Georgios Pavlakos
Publikováno v:
The International Journal of Robotics Research. 41:85-126
This paper solves the planar navigation problem by recourse to an online reactive scheme that exploits recent advances in SLAM and visual object recognition to recast prior geometric knowledge in terms of an offline catalogue of familiar objects. The
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::44a76df86ce5c4cde946efa4929f54e1
https://doi.org/10.1177/02783649211048931
https://doi.org/10.1177/02783649211048931
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb0ec62da201bd6958529575488ed6db
https://doi.org/10.1109/cvprw56347.2022.00014
https://doi.org/10.1109/cvprw56347.2022.00014
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4f83d554e5cb41871bb238743a540853
https://doi.org/10.1109/cvpr52688.2022.00276
https://doi.org/10.1109/cvpr52688.2022.00276
Autor:
Daniel E. Koditschek, Georgios Pavlakos, J. Diego Caporale, Vasileios Vasilopoulos, Kostas Daniilidis, Sean L. Bowman, George J. Pappas
Publikováno v:
IEEE Robotics and Automation Letters. 5:4455-4462
This letter presents a reactive planning system that enriches the topological representation of an environment with a tightly integrated semantic representation, achieved by incorporating and exploiting advances in deep perceptual learning and probab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::807989c85686c00e55eb0ac05fbaafd1
https://doi.org/10.1109/lra.2020.3001496
https://doi.org/10.1109/lra.2020.3001496
Autor:
Karl Schmeckpeper, Philip Osteen, Yufu Wang, Georgios Pavlakos, Kenneth Chaney, Wyatt Jordan, Xiaowei Zhou, Konstantinos Derpanis, Kostas Daniilidis
This paper presents an approach to estimating the continuous 6-DoF pose of an object from a single RGB image. The approach combines semantic keypoints predicted by a convolutional network (convnet) with a deformable shape model. Unlike prior investig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7da34f1844d83adea56a71ddd835a885
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198359
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::133c6bb7406bb663d86c83456bdbb814
https://doi.org/10.1007/978-3-031-19836-6_41
https://doi.org/10.1007/978-3-031-19836-6_41
Publikováno v:
ICASSP
Independent Sign Language Recognition is a complex visual recognition problem that combines several challenging tasks of Computer Vision due to the necessity to exploit and fuse information from hand gestures, body features and facial expressions. Wh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::466ace5fe34c27e51aeb14dab80f0d54
https://doi.org/10.1109/icassp39728.2021.9414278
https://doi.org/10.1109/icassp39728.2021.9414278
This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and typically regress a single estimate for a given input. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::96459f45370a4d58167d82cc32cb5233
Autor:
Petros Maragos, Gerasimos Potamianos, Galini Sapountzaki, Maria Parelli, Georgios Pavlakos, Katerina Papadimitriou
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030780944
HCI (8)
HCI (8)
Cued Speech (CS) constitutes a non-vocal mode of communication that relies on lip movements in conjunction with hand positional and gestural cues, in order to disambiguate phonetic information and make it accessible to the speech and hearing impaired
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f9f7b0716d93c81e0d6f4865eb0c7c99
https://doi.org/10.1007/978-3-030-78095-1_21
https://doi.org/10.1007/978-3-030-78095-1_21
Videos from edited media like movies are a useful, yet under-explored source of information. The rich variety of appearance and interactions between humans depicted over a large temporal context in these films could be a valuable source of data. Howe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c83e3b9acde181e7fd3ff33b44d8427
http://arxiv.org/abs/2012.09843
http://arxiv.org/abs/2012.09843