Papers
arxiv:2102.00649

Forecasting Action through Contact Representations from First Person Video

Published on Feb 1, 2021
Authors:
,
,
,
,

Abstract

Researchers developed contact-centered representations and models for action anticipation by introducing Contact Anticipation Maps and Next Active Object Segmentations, achieving state-of-the-art results in action prediction and anticipation on the EPIC Kitchens dataset.

Human actions involving hand manipulations are structured according to the making and breaking of hand-object contact, and human visual understanding of action is reliant on anticipation of contact as is demonstrated by pioneering work in cognitive science. Taking inspiration from this, we introduce representations and models centered on contact, which we then use in action prediction and anticipation. We annotate a subset of the EPIC Kitchens dataset to include time-to-contact between hands and objects, as well as segmentations of hands and objects. Using these annotations we train the Anticipation Module, a module producing Contact Anticipation Maps and Next Active Object Segmentations - novel low-level representations providing temporal and spatial characteristics of anticipated near future action. On top of the Anticipation Module we apply Egocentric Object Manipulation Graphs (Ego-OMG), a framework for action anticipation and prediction. Ego-OMG models longer term temporal semantic relations through the use of a graph modeling transitions between contact delineated action states. Use of the Anticipation Module within Ego-OMG produces state-of-the-art results, achieving 1st and 2nd place on the unseen and seen test sets, respectively, of the EPIC Kitchens Action Anticipation Challenge, and achieving state-of-the-art results on the tasks of action anticipation and action prediction over EPIC Kitchens. We perform ablation studies over characteristics of the Anticipation Module to evaluate their utility.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2102.00649 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2102.00649 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.