Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Brent Griffin"'
Publikováno v:
IEEE Access, Vol 4, Pp 3469-3478 (2016)
Analysis and controller design methods abound in the literature for planar (also known as 2-D) bipedal models. This paper takes one of them developed for underactuated bipeds and documents the process of designing a family of controllers on the basis
Externí odkaz:
https://doaj.org/article/e68f6f59d4d944c0a0e13b497f468bff
Autor:
Jason J. Corso, Brent Griffin
Publikováno v:
CVPR
This paper addresses the problem of learning to estimate the depth of detected objects given some measurement of camera motion (e.g., from robot kinematics or vehicle odometry). We achieve this by 1) designing a recurrent neural network (DBox) that e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::61f9529b9746742a89b0b965f1e33a18
https://doi.org/10.1109/cvpr46437.2021.00145
https://doi.org/10.1109/cvpr46437.2021.00145
Autor:
Jason J. Corso, Brent Griffin
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585709
ECCV (7)
ECCV (7)
Video object segmentation, i.e., the separation of a target object from background in video, has made significant progress on real and challenging videos in recent years. To leverage this progress in 3D applications, this paper addresses the problem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::880534785938bedcddd35452241759eb
https://doi.org/10.1007/978-3-030-58571-6_18
https://doi.org/10.1007/978-3-030-58571-6_18
Autor:
Brent Griffin
Publikováno v:
Ben Jonson Journal. 25:19-31
Over the past twenty years or so, performance-based efforts to recreate the staging conditions and production modes of Elizabethan/Jacobean playhouses through “original practices” (OP) have developed at a considerable rate. One has only to note t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::08c9c677106721b5fbe7f7251c1b4e49
https://doi.org/10.3366/bjj.2018.0208
https://doi.org/10.3366/bjj.2018.0208
Autor:
Jessy W. Grizzle, Brent Griffin
Publikováno v:
The International Journal of Robotics Research. 36:895-922
A key challenge in robotic bipedal locomotion is the design of feedback controllers that function well in the presence of uncertainty, in both the robot and its environment. This paper addresses the design of feedback controllers and periodic gaits t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2b5d9d57876807230702ce414d355370
https://doi.org/10.1177/0278364917708249
https://doi.org/10.1177/0278364917708249
Autor:
Brent Griffin
Publikováno v:
Ben Jonson Journal. 25:1-3
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0845500bb6117d98ca6598859239460f
https://doi.org/10.3366/bjj.2018.0206
https://doi.org/10.3366/bjj.2018.0206
Autor:
Jason J. Corso, Brent Griffin
Publikováno v:
CVPR
Semi-supervised video object segmentation has made significant progress on real and challenging videos in recent years. The current paradigm for segmentation methods and benchmark datasets is to segment objects in video provided a single annotation i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8c5a8842d919bf987e8ca24894b02b0b
https://doi.org/10.1109/cvpr.2019.00912
https://doi.org/10.1109/cvpr.2019.00912
Publikováno v:
ICRA
To be effective in unstructured and changing environments, robots must learn to recognize new objects. Deep learning has enabled rapid progress for object detection and segmentation in computer vision; however, this progress comes at the price of hum
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b40b4f524069cfd6c969ff4d98752dec
http://arxiv.org/abs/1904.00952
http://arxiv.org/abs/1904.00952
Publikováno v:
WACV
To be useful in everyday environments, robots must be able to identify and locate real-world objects. In recent years, video object segmentation has made significant progress on densely separating such objects from background in real and challenging
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f46b54fb29c167d972268ba798e24c1
http://arxiv.org/abs/1903.08336
http://arxiv.org/abs/1903.08336
Autor:
Jason J. Corso, Brent Griffin
Publikováno v:
WACV
We investigate the problem of strictly unsupervised video object segmentation, i.e., the separation of a primary object from background in video without a user-provided object mask or any training on an annotated dataset. We find foreground objects i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f901e9e31b2f43506e752be80534e08f
https://doi.org/10.1109/wacv.2019.00188
https://doi.org/10.1109/wacv.2019.00188