Search Results for author:
Found 5 papers, 2 papers with code
MoST: Motion Style Transformer between Diverse Action Contents
While existing motion style transfer methods are effective between two motions with identical content, their performance significantly diminishes when transferring style between motions with different contents.
Dimensionality reduction can be used as a surrogate model for high-dimensional forward uncertainty quantification
The proposed method also diverges from the Probabilistic Learning on Manifold, as a reconstruction mapping from the feature space to the input-output space is circumvented.
R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement
The trajectory refinement network enhances each of the M proposals using 1) tube-query scene attention (TQSA) and 2) proposal-level interaction attention (PIA) mechanisms.
Ranked #13 on
Motion Forecasting
on Argoverse CVPR 2020
Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning
To tackle the learning of whole-body motion, long-range temporal dynamics, and person-to-person interactions, we design a global and local attention mechanism, where, global body motions and local joint motions pay attention to each other.
Magnon-spinon dichotomy in the Kitaev hyperhoneycomb \blio
The family of edge-sharing tri-coordinated iridates and ruthenates has emerged in recent years as a major platform for Kitaev spin liquid physics, where spins fractionalize into emergent magnetic fluxes and Majorana fermions with Dirac-like dispersions.
Strongly Correlated Electrons
