6 citations · 6 across the 3 of their papers we have counts for
3 papers
cs.LG2026
EgoNeMo: Transferable Map of Pedestrian Dynamics via Egocentric LiDAR Scan
Azusa Sawada, Allan Wang, Hideo Saito +1
This paper proposes a transferable Map of Dynamics (MoD) framework that generalizes to unknown environments using only egocentric 3D LiDAR point clouds to overcome the long-standin…
cs.LG2022
Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series
Azusa Sawada, Taiki Miyagawa, Akinori F. Ebihara +2
Time series data are often obtained only within a limited time range due to interruptions during observation process. To classify such partial time series, we need to account for 1…
cs.LG2020★ 6 cited
Trade-offs in Top-k Classification Accuracies on Losses for Deep Learning
Azusa Sawada, Eiji Kaneko, Kazutoshi Sagi
This paper presents an experimental analysis about trade-offs in top-k classification accuracies on losses for deep leaning and proposal of a novel top-k loss. Commonly-used cross…