BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:3D pose estimation for behavior analysis with deep learning
DTSTART:20220719T140000
DTEND:20220719T160000
DTSTAMP:20260407T064118Z
UID:14c35a4d8a20ec12651ab78f3d5135d9ca698d30160ff9bdfcf026d1
CATEGORIES:Conferences - Seminars
DESCRIPTION:Haozhe Qi\nEDIC candidacy exam\nExam president: Prof. Pascal F
 ua\nThesis advisor: Prof. Alexander Mathis\nCo-examiner: Prof. Amir Zamir\
 n\nAbstract\nFor the automated behavioral analysis\, 3D pose estimation pr
 ovides an ideal representation of animals. However\, 3D pose estimation is
  less well-studied due to the lack of annotated data sets\, as well as the
  higher computational burden compared to the well-established 2D pose esti
 mation. To tackle those challenges\, during my Ph.D study\, I will focus o
 n three sub-areas of the 3D pose estimation: multi-view single individual 
 pose estimation\, multi-view multi-individual pose estimation and egocentr
 ic pose estimation. By doing so\, I will make sure that those innovations 
 are suitable for various behavioral analysis applications (mouse behavior 
 analysis\, fish behavior analysis and measurement of patients' functional 
 impairment respectively). Thus\, I can create methods that are robust and 
 universal and thus strongly impact to the computational ethology and neuro
 science.\n\nBackground papers\n1. Title: Cross View Fusion for 3D Human Po
 se Estimation\n    Authors: Haibo Qiu\, Chunyu Wang\, Jingdong Wang\, Na
 iyan Wang\, Wenjun Zeng.\n    Link: https://openaccess.thecvf.com/conte
 nt_ICCV_2019/papers/Qiu_Cross_View_Fusion_for_3D_Human_Pose_Estimation_ICC
 V_2019_paper.pdf\n\n2. Title: H2O: Two Hands Manipulating Objects for Firs
 t Person Interaction Recognition \n    Authors: Taein Kwon\, Bugra Teki
 n\, Jan Stuhmer\, Federica Bogo\, Marc Pollefeys.\n   Link: https://ope
 naccess.thecvf.com/content/ICCV2021/papers/Kwon_H2O_Two_Hands_Manipulating
 _Objects_for_First_Person_Interaction_Recognition_ICCV_2021_paper.pdf\n\n3
 . Title: Interacting Attention Graph for Single Image Two-Hand Reconstruct
 ion\n    Authors: Mengcheng Li\, Liang An\, Hongwen Zhang\, Lianpeng Wu\
 , Feng Chen\, Tao Yu\, Yebin Liu.\n    Link: https://arxiv.org/pdf/2203
 .09364.pdf\n 
LOCATION:
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR