Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

VIEWPOINT ESTIMATION IN IMAGES BY A KEY-POINT BASED DEEP NEURAL NETWORK

Abstract: 

Viewpoint estimation in a 2D image is a challenging task due to the great variations in the object’s shape, appearance,
visible parts, etc. To overcome the above difficulties, a new deep neural network is proposed, which employs the key-points of the object as a regularization term and a semantic bridge connecting the raw pixels with the object’s viewpoint. A series of Hourglass structures are adopted for key-point
extraction. With the extracted key-points, an LSTM based network is designed to model both the intrinsic relationship among the key-points and the underlying connections between the key-points and the object’s viewpoint. A multitasks learning scheme is designed to optimize the key-point detection and the viewpoint estimation performance simultaneously. The experiment results on the PASCAL 3D+ dataset have demonstrated the effectiveness of the proposed approach.

up
1 user has voted: yiwei zhu

Paper Details

Authors:
Jiana Yang, Shilin Wang*, Senior Member, IEEE, and Gongshen Liu
Submitted On:
18 September 2019 - 9:34am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Jiana Yang
Paper Code:
1237

Document Files

Jiana_poster_v2.pdf

(18)

Subscribe

[1] Jiana Yang, Shilin Wang*, Senior Member, IEEE, and Gongshen Liu, "VIEWPOINT ESTIMATION IN IMAGES BY A KEY-POINT BASED DEEP NEURAL NETWORK", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4676. Accessed: Dec. 12, 2019.
@article{4676-19,
url = {http://sigport.org/4676},
author = {Jiana Yang; Shilin Wang*; Senior Member; IEEE; and Gongshen Liu },
publisher = {IEEE SigPort},
title = {VIEWPOINT ESTIMATION IN IMAGES BY A KEY-POINT BASED DEEP NEURAL NETWORK},
year = {2019} }
TY - EJOUR
T1 - VIEWPOINT ESTIMATION IN IMAGES BY A KEY-POINT BASED DEEP NEURAL NETWORK
AU - Jiana Yang; Shilin Wang*; Senior Member; IEEE; and Gongshen Liu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4676
ER -
Jiana Yang, Shilin Wang*, Senior Member, IEEE, and Gongshen Liu. (2019). VIEWPOINT ESTIMATION IN IMAGES BY A KEY-POINT BASED DEEP NEURAL NETWORK. IEEE SigPort. http://sigport.org/4676
Jiana Yang, Shilin Wang*, Senior Member, IEEE, and Gongshen Liu, 2019. VIEWPOINT ESTIMATION IN IMAGES BY A KEY-POINT BASED DEEP NEURAL NETWORK. Available at: http://sigport.org/4676.
Jiana Yang, Shilin Wang*, Senior Member, IEEE, and Gongshen Liu. (2019). "VIEWPOINT ESTIMATION IN IMAGES BY A KEY-POINT BASED DEEP NEURAL NETWORK." Web.
1. Jiana Yang, Shilin Wang*, Senior Member, IEEE, and Gongshen Liu. VIEWPOINT ESTIMATION IN IMAGES BY A KEY-POINT BASED DEEP NEURAL NETWORK [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4676