You-Do, I-Learn

Discovering task-relevant objects from egocentric video sequences of multiple users, using appearance, position, motion and attention features.Distinguishing different ways in which a task-relevant object has been used.Automatically extracting usage snippets, to be used for video-based guidance.Tested on a variety of daily tasks such as initialising a printer, preparing a coffee and setting up a gym machine. Display Omitted 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)źdiscovers task relevant objects, (ii) builds a model for each, (iii)źdistinguishes different ways in which each discovered object has been used and (iv)źdiscovers 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.