Re-evaluating word mover's distance

R Sato, M Yamada, H Kashima - … Conference on Machine …, 2022 - proceedings.mlr.press
The word mover's distance (WMD) is a fundamental technique for measuring the similarity of
two documents. As the crux of WMD, it can take advantage of the underlying geometry of the …

Weakly-supervised temporal action alignment driven by unbalanced spectral fused Gromov-Wasserstein distance

D Luo, Y Wang, A Yue, H Xu - Proceedings of the 30th ACM International …, 2022 - dl.acm.org
Temporal action alignment aims at segmenting videos into clips and tagging each clip with a
textual description, which is an important task of video semantic analysis. Most existing …

Towards uncertainty and efficiency in reinforcement learning

R Zhang - 2021 - search.proquest.com
Deep reinforcement learning (RL) has received great success in playing video games and
strategic board games, where a simulator is well-defined, and massive samples are …