SmallTAL: Real-Time Egocentric Online Temporal Action Localization for the Data-Impoverished

Eric C. Joyce, Yao Chen, Eduardo Neeter, Philippos Mordohai

Research output: Contribution to journalArticlepeer-review

Abstract

We propose a real-time, online temporal action localization system that requires a small amount of annotated data. The main challenges we address are high intra-class variability and a large and diverse background class. We address these using a flexible frame descriptor, dynamic time warping, and a novel approach to database construction. Our solution receives egocentric RGB-D streams as input and makes predictions at regular temporal intervals. We validate our approach by localizing actions in a digital twin of an electrical substation, in which certain objects have been replaced by functional virtual replicas.

Original languageEnglish
Pages (from-to)179-203
Number of pages25
JournalPresence: Teleoperators and Virtual Environments
Volume32
DOIs
StatePublished - 2023

Fingerprint

Dive into the research topics of 'SmallTAL: Real-Time Egocentric Online Temporal Action Localization for the Data-Impoverished'. Together they form a unique fingerprint.

Cite this