An Evaluation of Action Recognition Models on EPIC-Kitchens

by   Will Price, et al.

We benchmark contemporary action recognition models (TSN, TRN, and TSM) on the recently introduced EPIC-Kitchens dataset and release pretrained models on GitHub ( for others to build upon. In contrast to popular action recognition datasets like Kinetics, Something-Something, UCF101, and HMDB51, EPIC-Kitchens is shot from an egocentric perspective and captures daily actions in-situ. In this report, we aim to understand how well these models can tackle the challenges present in this dataset, such as its long tail class distribution, unseen environment test set, and multiple tasks (verb, noun and, action classification). We discuss the models' shortcomings and avenues for future research.


page 3

page 5


Win-Fail Action Recognition

Current video/action understanding systems have demonstrated impressive ...

Quo Vadis, Skeleton Action Recognition ?

In this paper, we study current and upcoming frontiers across the landsc...

Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories

We propose a feature for action recognition called Trajectory-Set (TS), ...

Top-1 Solution of Multi-Moments in Time Challenge 2019

In this technical report, we briefly introduce the solutions of our team...

Vision-based Behavioral Recognition of Novelty Preference in Pigs

Behavioral scoring of research data is crucial for extracting domain-spe...

Actions Transformations

What defines an action like "kicking ball"? We argue that the true meani...

MSC: A Dataset for Macro-Management in StarCraft II

Macro-management is an important problem in StarCraft, which has been st...