no code implementations • 10 Apr 2024 • Xingyu Song, Zhan Li, Shi Chen, Xin-Qiang Cai, Kazuyuki Demachi
(3) We achieve the same performance with only 10% of the original data for training as with all of the original data from the real-world dataset, and a better performance on In-the-wild videos, by employing our data augmentation techniques.
no code implementations • 3 Mar 2024 • Michel Pohl, Mitsuru Uesaka, Hiroyuki Takahashi, Kazuyuki Demachi, Ritu Bhusal Chhatkuli
We use UORO, SnAp-1, and DNI to forecast each marker's 3D position with horizons (the time interval in advance for which the prediction is made) h<=2. 1s and compare them with RTRL, least mean squares, and linear regression.
no code implementations • 24 Jan 2024 • Xingyu Song, Zhan Li, Shi Chen, Kazuyuki Demachi
Current datasets for action recognition tasks face limitations stemming from traditional collection and generation methods, including the constrained range of action classes, absence of multi-viewpoint recordings, limited diversity, poor video quality, and labor-intensive manually collection.
1 code implementation • 13 Jul 2022 • Michel Pohl, Mitsuru Uesaka, Kazuyuki Demachi, Ritu Bhusal Chhatkuli
The amplitude of the motion of the tracked points ranged from 12. 0mm to 22. 7mm.
1 code implementation • 28 Nov 2021 • Akihiro Nakano, Shi Chen, Kazuyuki Demachi
We theoretically prove that both losses help the model learn more efficiently and that cross-task consistency loss is better in terms of alignment with the straight-forward predictions.
1 code implementation • 2 Jun 2021 • Michel Pohl, Mitsuru Uesaka, Hiroyuki Takahashi, Kazuyuki Demachi, Ritu Bhusal Chhatkuli
Prediction with online learning of recurrent neural networks (RNN) allows for adaptation to non-stationary respiratory signals, but classical methods such as RTRL and truncated BPTT are respectively slow and biased.
Ranked #1 on Multivariate Time Series Forecasting on ExtMarker