A multimodality approach to predicting the popularity of sneakers

Mei Chen Yeh, Shao Ting Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a computational approach for predicting the popularity score of sneakers through the analysis of growing amount of online data. Sneakers are described in several aspects based on which a popularity prediction model is constructed. In particular, we utilize the multiple kernel learning technique with customized kernels to analyze multimodal data extracted from an online sneaker magazine. The construction of a prediction model from multiple facets is not trivial - the effectiveness of each feature depends on the way we compute and combine it with the others. We examine a few design choices and study how multimodal data should be utilized to achieve practical prediction.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages27-28
Number of pages2
ISBN (Electronic)9781479987443
DOIs
Publication statusPublished - 2015 Aug 20
Event2nd IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015 - Taipei, Taiwan
Duration: 2015 Jun 62015 Jun 8

Publication series

Name2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015

Other

Other2nd IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015
CountryTaiwan
CityTaipei
Period15/6/615/6/8

Fingerprint

predictions
learning
flat surfaces

Keywords

  • Computational modeling
  • Feature extraction
  • Image color analysis
  • Kernel
  • Predictive models
  • Shape
  • Training

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Electrical and Electronic Engineering
  • Instrumentation
  • Media Technology

Cite this

Yeh, M. C., & Yang, S. T. (2015). A multimodality approach to predicting the popularity of sneakers. In 2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015 (pp. 27-28). [7216892] (2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-TW.2015.7216892

A multimodality approach to predicting the popularity of sneakers. / Yeh, Mei Chen; Yang, Shao Ting.

2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 27-28 7216892 (2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yeh, MC & Yang, ST 2015, A multimodality approach to predicting the popularity of sneakers. in 2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015., 7216892, 2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015, Institute of Electrical and Electronics Engineers Inc., pp. 27-28, 2nd IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015, Taipei, Taiwan, 15/6/6. https://doi.org/10.1109/ICCE-TW.2015.7216892
Yeh MC, Yang ST. A multimodality approach to predicting the popularity of sneakers. In 2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 27-28. 7216892. (2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015). https://doi.org/10.1109/ICCE-TW.2015.7216892
Yeh, Mei Chen ; Yang, Shao Ting. / A multimodality approach to predicting the popularity of sneakers. 2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 27-28 (2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015).
@inproceedings{e921ee28a0234345a69df1a2bb397832,
title = "A multimodality approach to predicting the popularity of sneakers",
abstract = "We present a computational approach for predicting the popularity score of sneakers through the analysis of growing amount of online data. Sneakers are described in several aspects based on which a popularity prediction model is constructed. In particular, we utilize the multiple kernel learning technique with customized kernels to analyze multimodal data extracted from an online sneaker magazine. The construction of a prediction model from multiple facets is not trivial - the effectiveness of each feature depends on the way we compute and combine it with the others. We examine a few design choices and study how multimodal data should be utilized to achieve practical prediction.",
keywords = "Computational modeling, Feature extraction, Image color analysis, Kernel, Predictive models, Shape, Training",
author = "Yeh, {Mei Chen} and Yang, {Shao Ting}",
year = "2015",
month = "8",
day = "20",
doi = "10.1109/ICCE-TW.2015.7216892",
language = "English",
series = "2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "27--28",
booktitle = "2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015",

}

TY - GEN

T1 - A multimodality approach to predicting the popularity of sneakers

AU - Yeh, Mei Chen

AU - Yang, Shao Ting

PY - 2015/8/20

Y1 - 2015/8/20

N2 - We present a computational approach for predicting the popularity score of sneakers through the analysis of growing amount of online data. Sneakers are described in several aspects based on which a popularity prediction model is constructed. In particular, we utilize the multiple kernel learning technique with customized kernels to analyze multimodal data extracted from an online sneaker magazine. The construction of a prediction model from multiple facets is not trivial - the effectiveness of each feature depends on the way we compute and combine it with the others. We examine a few design choices and study how multimodal data should be utilized to achieve practical prediction.

AB - We present a computational approach for predicting the popularity score of sneakers through the analysis of growing amount of online data. Sneakers are described in several aspects based on which a popularity prediction model is constructed. In particular, we utilize the multiple kernel learning technique with customized kernels to analyze multimodal data extracted from an online sneaker magazine. The construction of a prediction model from multiple facets is not trivial - the effectiveness of each feature depends on the way we compute and combine it with the others. We examine a few design choices and study how multimodal data should be utilized to achieve practical prediction.

KW - Computational modeling

KW - Feature extraction

KW - Image color analysis

KW - Kernel

KW - Predictive models

KW - Shape

KW - Training

UR - http://www.scopus.com/inward/record.url?scp=84959546166&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959546166&partnerID=8YFLogxK

U2 - 10.1109/ICCE-TW.2015.7216892

DO - 10.1109/ICCE-TW.2015.7216892

M3 - Conference contribution

AN - SCOPUS:84959546166

T3 - 2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015

SP - 27

EP - 28

BT - 2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -