You-Do, I-Learn: Unsupervised Multi-User egocentric Approach Towards Video-Based Guidance

TL;DR

This paper introduces an unsupervised egocentric video analysis method that automatically extracts object usage guidance from multi-user data, enabling assistive task support and object interaction understanding.

Contribution

It presents a novel unsupervised multi-user approach for extracting object usage guidance from egocentric videos, including object discovery, modeling, and interaction dependency analysis.

Findings

Effective object discovery and modeling from egocentric videos.

Successful online and offline guidance generation.

Demonstrated on daily tasks like printer setup and coffee preparation.

Abstract

This paper presents an unsupervised approach towards automatically extracting video-based guidance on object usage, from egocentric video and wearable gaze tracking, collected from multiple users while performing tasks. The approach i) discovers task relevant objects, ii) builds a model for each, iii) distinguishes different ways in which each discovered object has been used and iv) discovers the dependencies between object interactions. The work investigates using appearance, position, motion and attention, and presents results using each and a combination of relevant features. Moreover, an online scalable approach is presented and is compared to offline results. The paper proposes a method for selecting a suitable video guide to be displayed to a novice user indicating how to use an object, purely triggered by the user's gaze. The potential assistive mode can also recommend an object to be used next based on the learnt sequence of object interactions. The approach was tested on a variety of daily tasks such as initialising a printer, preparing a coffee and setting up a gym machine.