Papers
arxiv:2006.11393

Unifying Few- and Zero-Shot Egocentric Action Recognition

Published on May 27, 2020
Authors:
,
,

Abstract

Research explores open-set action recognition by combining few- and zero-shot learning approaches, demonstrating improved zero-shot classification through metric-learning loss integration.

Although there has been significant research in egocentric action recognition, most methods and tasks, including EPIC-KITCHENS, suppose a fixed set of action classes. Fixed-set classification is useful for benchmarking methods, but is often unrealistic in practical settings due to the compositionality of actions, resulting in a functionally infinite-cardinality label set. In this work, we explore generalization with an open set of classes by unifying two popular approaches: few- and zero-shot generalization (the latter which we reframe as cross-modal few-shot generalization). We propose a new set of splits derived from the EPIC-KITCHENS dataset that allow evaluation of open-set classification, and use these splits to show that adding a metric-learning loss to the conventional direct-alignment baseline can improve zero-shot classification by as much as 10%, while not sacrificing few-shot performance.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2006.11393 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2006.11393 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.