We present an alternative approach to decompose non-negative tensors, called many-body approximation .

Temporal action segmentation and long-term action anticipation are two popular vision tasks for the temporal analysis of actions in videos.

In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting.

Randomized smoothing is a powerful framework for making models provably robust against small changes to their inputs - by guaranteeing robustness of the majority vote when randomly adding noise before classification.