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

facebooktwittermailshare

Fashion style recognition using component-dependent convolutional neural networks

Abstract: 

The fashion style recognition is important in online marketing applications. Several algorithms have been proposed, but their accuracy is still unsatisfactory. In this paper, we share our proposed method for creating an improved fashion style recognition algorithm, component-dependent convolutional neural networks (CD-CNNs). Given that a lot of fashion styles largely depend on the features of specific body parts or human body postures, first, we obtain images of the body parts and postures by using semantic segmentation and pose estimation algorithms; then, we pre-train CD-CNNs. We perform the classification by the concatenated outputs of CD-CNNs and a support vector machine (SVM). Experimental results using the HipsterWars and FashionStyle14 datasets prove that our method is effective and can improve classification accuracy, namely 85.3% for HipsterWars and 77.7% for FashionStyle14, while those of existing methods were 80.9% for HipsterWars and 72.0% for FashionStyle14.

up
0 users have voted:

Paper Details

Authors:
Takahisa Yamamoto, Atsushi Nakazawa
Submitted On:
19 September 2019 - 2:20am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Takahisa Yamamoto
Paper Code:
1786
Document Year:
2019
Cite

Document Files

ICIP2019_paper1786_poster_rev1.pdf

(15)

Subscribe

[1] Takahisa Yamamoto, Atsushi Nakazawa, "Fashion style recognition using component-dependent convolutional neural networks", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4708. Accessed: Oct. 18, 2019.
@article{4708-19,
url = {http://sigport.org/4708},
author = {Takahisa Yamamoto; Atsushi Nakazawa },
publisher = {IEEE SigPort},
title = {Fashion style recognition using component-dependent convolutional neural networks},
year = {2019} }
TY - EJOUR
T1 - Fashion style recognition using component-dependent convolutional neural networks
AU - Takahisa Yamamoto; Atsushi Nakazawa
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4708
ER -
Takahisa Yamamoto, Atsushi Nakazawa. (2019). Fashion style recognition using component-dependent convolutional neural networks. IEEE SigPort. http://sigport.org/4708
Takahisa Yamamoto, Atsushi Nakazawa, 2019. Fashion style recognition using component-dependent convolutional neural networks. Available at: http://sigport.org/4708.
Takahisa Yamamoto, Atsushi Nakazawa. (2019). "Fashion style recognition using component-dependent convolutional neural networks." Web.
1. Takahisa Yamamoto, Atsushi Nakazawa. Fashion style recognition using component-dependent convolutional neural networks [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4708