StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ragusa, Francesco, Farinella, Giovanni Maria, Furnari, Antonino
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917615404843008
author Ragusa, Francesco
Farinella, Giovanni Maria
Furnari, Antonino
author_facet Ragusa, Francesco
Farinella, Giovanni Maria
Furnari, Antonino
contents Anticipation problem has been studied considering different aspects such as predicting humans' locations, predicting hands and objects trajectories, and forecasting actions and human-object interactions. In this paper, we studied the short-term object interaction anticipation problem from the egocentric point of view, proposing a new end-to-end architecture named StillFast. Our approach simultaneously processes a still image and a video detecting and localizing next-active objects, predicting the verb which describes the future interaction and determining when the interaction will start. Experiments on the large-scale egocentric dataset EGO4D show that our method outperformed state-of-the-art approaches on the considered task. Our method is ranked first in the public leaderboard of the EGO4D short term object interaction anticipation challenge 2022. Please see the project web page for code and additional details: https://iplab.dmi.unict.it/stillfast/.
format Preprint
id arxiv_https___arxiv_org_abs_2304_03959
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation
Ragusa, Francesco
Farinella, Giovanni Maria
Furnari, Antonino
Computer Vision and Pattern Recognition
Anticipation problem has been studied considering different aspects such as predicting humans' locations, predicting hands and objects trajectories, and forecasting actions and human-object interactions. In this paper, we studied the short-term object interaction anticipation problem from the egocentric point of view, proposing a new end-to-end architecture named StillFast. Our approach simultaneously processes a still image and a video detecting and localizing next-active objects, predicting the verb which describes the future interaction and determining when the interaction will start. Experiments on the large-scale egocentric dataset EGO4D show that our method outperformed state-of-the-art approaches on the considered task. Our method is ranked first in the public leaderboard of the EGO4D short term object interaction anticipation challenge 2022. Please see the project web page for code and additional details: https://iplab.dmi.unict.it/stillfast/.
title StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2304.03959