Joint Discovery of Object States and Manipulation Actions

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F17%3A00318983" target="_blank" >RIV/68407700:21730/17:00318983 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ICCV.2017.234" target="_blank" >http://dx.doi.org/10.1109/ICCV.2017.234</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCV.2017.234" target="_blank" >10.1109/ICCV.2017.234</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Joint Discovery of Object States and Manipulation Actions

Popis výsledku v původním jazyce

Many human activities involve object manipulations aiming to modify the object state. Examples of common state changes include full/empty bottle, open/closed door, and attached/detached car wheel. In this work, we seek to automatically discover the states of objects and the associated manipulation actions. Given a set of videos for a particular task, we propose a joint model that learns to identify object states and to localize state-modifying actions. Our model is formulated as a discriminative clustering cost with constraints. We assume a consistent temporal order for the changes in object states and manipulation actions, and introduce new optimization techniques to learn model parameters without additional supervision. We demonstrate successful discovery of seven manipulation actions and corresponding object states on a new dataset of videos depicting real-life object manipulations. We show that our joint formulation results in an improvement of object state discovery by action recognition and vice versa.

Název v anglickém jazyce

Joint Discovery of Object States and Manipulation Actions

Popis výsledku anglicky

Many human activities involve object manipulations aiming to modify the object state. Examples of common state changes include full/empty bottle, open/closed door, and attached/detached car wheel. In this work, we seek to automatically discover the states of objects and the associated manipulation actions. Given a set of videos for a particular task, we propose a joint model that learns to identify object states and to localize state-modifying actions. Our model is formulated as a discriminative clustering cost with constraints. We assume a consistent temporal order for the changes in object states and manipulation actions, and introduce new optimization techniques to learn model parameters without additional supervision. We demonstrate successful discovery of seven manipulation actions and corresponding object states on a new dataset of videos depicting real-life object manipulations. We show that our joint formulation results in an improvement of object state discovery by action recognition and vice versa.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20201 - Electrical and electronic engineering

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

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

2017 IEEE International Conference on Computer Vision (ICCV 2017)

ISBN

978-1-5386-1032-9

ISSN

1550-5499

e-ISSN

—

Počet stran výsledku

10

Strana od-do

2146-2155

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Venice

Datum konání akce

22. 10. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000425498402022