Zobrazeno 1 - 10
of 150
pro vyhledávání: '"DiPietro, Robert"'
Successful training of deep neural networks with noisy labels is an essential capability as most real-world datasets contain some amount of mislabeled data. Left unmitigated, label noise can sharply degrade typical supervised learning approaches. In
Externí odkaz:
http://arxiv.org/abs/2109.14563
Autor:
DiPietro, Robert, Hager, Gregory D.
Prior work has demonstrated the feasibility of automated activity recognition in robot-assisted surgery from motion data. However, these efforts have assumed the availability of a large number of densely-annotated sequences, which must be provided ma
Externí odkaz:
http://arxiv.org/abs/1907.08825
Autor:
DiPietro, Robert, Hager, Gregory D.
We show that it is possible to learn meaningful representations of surgical motion, without supervision, by learning to predict the future. An architecture that combines an RNN encoder-decoder and mixture density networks (MDNs) is developed to model
Externí odkaz:
http://arxiv.org/abs/1806.03318
One-shot pose estimation for tasks such as body joint localization, camera pose estimation, and object tracking are generally noisy, and temporal filters have been extensively used for regularization. One of the most widely-used methods is the Kalman
Externí odkaz:
http://arxiv.org/abs/1708.01885
Recurrent neural networks (RNNs) have achieved state-of-the-art performance on many diverse tasks, from machine translation to surgical activity recognition, yet training RNNs to capture long-term dependencies remains difficult. To date, the vast maj
Externí odkaz:
http://arxiv.org/abs/1702.07805
Autor:
Rupprecht, Christian, Laina, Iro, DiPietro, Robert, Baust, Maximilian, Tombari, Federico, Navab, Nassir, Hager, Gregory D.
Many prediction tasks contain uncertainty. In some cases, uncertainty is inherent in the task itself. In future prediction, for example, many distinct outcomes are equally valid. In other cases, uncertainty arises from the way data is labeled. For ex
Externí odkaz:
http://arxiv.org/abs/1612.00197
Autor:
DiPietro, Robert, Lea, Colin, Malpani, Anand, Ahmidi, Narges, Vedula, S. Swaroop, Lee, Gyusung I., Lee, Mija R., Hager, Gregory D.
We apply recurrent neural networks to the task of recognizing surgical activities from robot kinematics. Prior work in this area focuses on recognizing short, low-level activities, or gestures, and has been based on variants of hidden Markov models a
Externí odkaz:
http://arxiv.org/abs/1606.06329
Autor:
Plouffe, Brian D., Nagesha, Dattatri K., DiPietro, Robert S., Sridhar, Srinvas, Heiman, Don, Murthy, Shashi K., Lewis, Lewis H.
Publikováno v:
In Journal of Magnetism and Magnetic Materials 2011 323(17):2310-2317
Autor:
DiPietro, Robert, Hager, Gregory D.
Publikováno v:
In Handbook of Medical Image Computing and Computer Assisted Intervention 2020:503-519