Název: Isomorphic loss function for head pose estimation
Autoři: Felea, Iulian
Florea, Corneliu
Vertan, Constantin
Florea, Laura
Citace zdrojového dokumentu: WSCG 2017: poster papers proceedings: 25th International Conference in Central Europe on Computer Graphics, Visualization and Computer Visionin co-operation with EUROGRAPHICS Association, p. 89-94.
Datum vydání: 2017
Nakladatel: Václav Skala - UNION Agency
Typ dokumentu: konferenční příspěvek
conferenceObject
URI: wscg.zcu.cz/WSCG2017/!!_CSRN-2703.pdf
http://hdl.handle.net/11025/29618
ISBN: 978-80-86943-46-6
Klíčová slova: odhad pozice hlavy;funkce ztráty;vzdálenost L1;izomorfní transformace
Klíčová slova v dalším jazyce: head pose estimation;loss function;L1 distance;isomorphic transformation
Abstrakt v dalším jazyce: Accurate head pose estimation is a key step in many practical applications involving face analysis tasks, such as emotion recognition. We address the problem of head pose estimation in still color images acquired with a standard camera with limited resolution details. To achieve the proposed goal, we make use of the recent advances of Deep Convolutional Neural Networks. As head angles with respect on yaw and pitch are continuous, the problem is one of regression. Typical loss function for regression are based on L1 and L2 distances which are notorious for susceptibility to outliers. To address this aspect we introduce an isomorphic transformation which maps the initially infinite space into a closed space compressed at the ends and thus significantly down–weighting the significance of outliers. We have thoroughly evaluated the proposed approach on multiple publicly head pose databases.
Práva: © Václav Skala - Union Agency
Vyskytuje se v kolekcích:WSCG 2017: Poster Papers Proceedings

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
Felea.pdfPlný text1,11 MBAdobe PDFZobrazit/otevřít


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/29618

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.