Multi-view Facial Landmark Detector -- {PhD} Thesis Proposal

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00212092" target="_blank" >RIV/68407700:21230/13:00212092 - isvavai.cz</a>

Výsledek na webu

<a href="http://cmp.felk.cvut.cz/pub/cmp/articles/uricar/Uricar-TR-2013-21.pdf" target="_blank" >http://cmp.felk.cvut.cz/pub/cmp/articles/uricar/Uricar-TR-2013-21.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Multi-view Facial Landmark Detector -- {PhD} Thesis Proposal

Popis výsledku v původním jazyce

In this report we outline recent works on the facial landmark detection. We categorize the work of others to three main groups. Namely, the local independent detectors, the global methods and the combined approaches. The emphasis is on the category of detectors using the pictorial structures, also known as deformable part models (DPM). Some papers, which are not dealing with the facial landmark detection directly but which still contain useful ideas are also mentioned. After the literature survey, we give an outline of our contributions to the topic of facial landmark detection. Namely, we summarize our work on the near-frontal detector and the work, which we did for speeding up the learning novel algorithms we proposed to speed up learning of this detector from fully annotated data. Finally, we identify the open issues arising in facial landmark detection based on the DPM. These open issues will serve as a direction for our future work towards the Ph.D. thesis.

Název v anglickém jazyce

Multi-view Facial Landmark Detector -- {PhD} Thesis Proposal

Popis výsledku anglicky

In this report we outline recent works on the facial landmark detection. We categorize the work of others to three main groups. Namely, the local independent detectors, the global methods and the combined approaches. The emphasis is on the category of detectors using the pictorial structures, also known as deformable part models (DPM). Some papers, which are not dealing with the facial landmark detection directly but which still contain useful ideas are also mentioned. After the literature survey, we give an outline of our contributions to the topic of facial landmark detection. Namely, we summarize our work on the near-frontal detector and the work, which we did for speeding up the learning novel algorithms we proposed to speed up learning of this detector from fully annotated data. Finally, we identify the open issues arising in facial landmark detection based on the DPM. These open issues will serve as a direction for our future work towards the Ph.D. thesis.

Druh

O - Ostatní výsledky

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2013

Kód důvěrnosti údajů

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