We present a fully unsupervised approach for the discovery of i) task relevant objects and ii) how these objects have been used. A Task Relevant Object (TRO) is an object, or part of an object, with which a person interacts during task performance. Given egocentric video from multiple operators, the approach can discover objects with which the users interact, both static objects such as a coffee machine as well as movable ones such as a cup. Importantly, we also introduce the term Mode of Interaction (MOI) to refer to the different ways in which TROs are used. Say, a cup can be lifted, washed, or poured into. When harvesting interactions with the same object from multiple operators, common MOIs can be found. Setup and Dataset: Using a wearable camera and gaze tracker (Mobile Eye-XG from ASL), egocentric video is collected of users performing tasks, along with their gaze in pixel coordinates. Six locations were chosen: kitchen, workspace, laser printer, corridor with a locked door, cardiac gym and weight-lifting machine. The Bristol Egocentric Object Interactions Dataset is publically available 1 . Discovering TROs: Given a sequence of images {I 1 , .., I T } collected from multiple operators around a common environment, we aim to extract K TROs, where each object T RO k is represented by the images from the sequence that feature the object of interest . We investigate using appearance, position and attention, and present results using each and a combination of relevant features. For attention, we exploit the high quality and predictive nature of eye gaze fixations.Results compare k-means clustering to spectral clustering, and propose estimating the optimal number of clusters using the standard DaviesBouldin (DB) index. Figure 2 shows the best performance for discovering TROs by combining position (relative to a map of the scene) and appearance (HOG features within BoW) over a sliding window w = 25, using gaze fixations for attention, spectral clustering and estimating the number of clusters using the Davies-Bouldin (DB) index. Finding MOIs: Given consecutive images (I t , I t+1 ,