Search Results for author:
Found 5 papers, 2 papers with code
Hyperbolic Active Learning for Semantic Segmentation under Domain Shift
In HALO (Hyperbolic Active Learning Optimization), for the first time, we propose the use of epistemic uncertainty as a data acquisition strategy, following the intuition of selecting data points that are the least known.
HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations
We propose to use hyperbolic uncertainty to determine the algorithmic learning pace, under the assumption that less uncertain samples should be more strongly driving the training, with a larger weight and pace.
Ranked #61 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Deep learning for laboratory earthquake prediction and autoregressive forecasting of fault zone stress
We demonstrate that DL models based on Long-Short Term Memory (LSTM) and Convolution Neural Networks predict labquakes under several conditions, and that fault zone stress can be predicted with fidelity, confirming that acoustic energy is a fingerprint of fault zone stress.
Under the Hood of Transformer Networks for Trajectory Forecasting
This paper proposes the first in-depth study of Transformer Networks (TF) and Bidirectional Transformers (BERT) for the forecasting of the individual motion of people, without bells and whistles.
Space-Time-Separable Graph Convolutional Network for Pose Forecasting
For the first time, STS-GCN models the human pose dynamics only with a graph convolutional network (GCN), including the temporal evolution and the spatial joint interaction within a single-graph framework, which allows the cross-talk of motion and spatial correlations.
Ranked #1 on
Human Pose Forecasting
on 3DPW
