Anticipating Next Active Objects for Egocentric Videos
Abstract
This paper addresses the problem of anticipating the next-active-object location in the future, for a given egocentric video clip where the contact might happen, before any action takes place. The problem is considerably hard, as we aim at estimating the position of such objects in a scenario where the observed clip and the action segment are separated by the so-called ``time to contact'' (TTC) segment. Many methods have been proposed to anticipate the action of a person based on previous hand movements and interactions with the surroundings. However, there have been no attempts to investigate the next possible interactable object, and its future location with respect to the first-person's motion and the field-of-view drift during the TTC window. We define this as the task of Anticipating the Next ACTive Object (ANACTO). To this end, we propose a transformer-based self-attention framework to identify and locate the next-active-object in an egocentric clip. We benchmark our method on three datasets: EpicKitchens-100, EGTEA+ and Ego4D. We also provide annotations for the first two datasets. Our approach performs best compared to relevant baseline methods. We also conduct ablation studies to understand the effectiveness of the proposed and baseline methods on varying conditions. Code and ANACTO task annotations will be made available upon paper acceptance.
Keywords
Cite
@article{arxiv.2302.06358,
title = {Anticipating Next Active Objects for Egocentric Videos},
author = {Sanket Thakur and Cigdem Beyan and Pietro Morerio and Vittorio Murino and Alessio Del Bue},
journal= {arXiv preprint arXiv:2302.06358},
year = {2024}
}
Comments
Accepted by IEEE ACCESS, this paper carries the Manuscript DOI: 10.1109/ACCESS.2024.3395282. The complete peer-reviewed version is available via this DOI, while the arXiv version is a post-author manuscript without peer-review