Leveraging the Present to Anticipate the Future in Videos

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F19%3A00340394" target="_blank" >RIV/68407700:21730/19:00340394 - isvavai.cz</a>

Výsledek na webu

<a href="http://openaccess.thecvf.com/content_CVPRW_2019/papers/Precognition/Miech_Leveraging_the_Present_to_Anticipate_the_Future_in_Videos_CVPRW_2019_paper.pdf" target="_blank" >http://openaccess.thecvf.com/content_CVPRW_2019/papers/Precognition/Miech_Leveraging_the_Present_to_Anticipate_the_Future_in_Videos_CVPRW_2019_paper.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Leveraging the Present to Anticipate the Future in Videos

Popis výsledku v původním jazyce

Anticipating actions before they are executed is crucial for a wide range of practical applications including autonomous driving and robotics. While most prior work in this area requires partial observation of executed actions, in the paper, we focus on anticipating actions seconds before they start. Our proposed approach is the fusion of a purely anticipatory model with a complementary model constrained to reason about the present. In particular, the latter predicts present action and scene attributes, and reasons about how they evolve over time. By doing so, we aim at modelling action anticipation at a more conceptual level than directly predicting future actions. Our model outperforms previously reported methods on the EPIC-KITCHENS and Breakfast datasets.

Název v anglickém jazyce

Leveraging the Present to Anticipate the Future in Videos

Popis výsledku anglicky

Anticipating actions before they are executed is crucial for a wide range of practical applications including autonomous driving and robotics. While most prior work in this area requires partial observation of executed actions, in the paper, we focus on anticipating actions seconds before they start. Our proposed approach is the fusion of a purely anticipatory model with a complementary model constrained to reason about the present. In particular, the latter predicts present action and scene attributes, and reasons about how they evolve over time. By doing so, we aim at modelling action anticipation at a more conceptual level than directly predicting future actions. Our model outperforms previously reported methods on the EPIC-KITCHENS and Breakfast datasets.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF15_003%2F0000468" target="_blank" >EF15_003/0000468: Inteligentní strojové vnímání</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů