Supervised manifold learning for media interestingness prediction

Yang Liu; Zhonglei Gu; Yiu Ming Cheung

Supervised manifold learning for media interestingness prediction

Yang Liu, Zhonglei Gu, Yiu Ming Cheung

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

In this paper, we describe the models designed for automatically selecting multimedia data, e.g., image and video segments, which are considered to be interesting for a common viewer. Specifically, we utilize an existing dimensionality reduction method called Neighborhood MinMax Projections (NMMP) to extract the low-dimensional features for predicting the discrete interestingness labels. Meanwhile, we introduce a new dimensionality reduction method dubbed Supervised Manifold Regression (SMR) to learn the compact representations for predicting the continuous interestingness levels. Finally, we use the nearest neighbor classifier and support vector regressor for classification and regression, respectively. Experimental results demonstrate the effectiveness of the low-dimensional features learned by NMMP and SMR.

Original language	English
Title of host publication	Working Notes Proceedings of the MediaEval 2016 Workshop
Editors	Guillaume Gravier, Claire-Hélène Demarty, Hervé Bredin, Bogdan Ionescu, Christina Boididou, Emmanuel Dellandrea, Jaeyong Choi, Michael Riegler , Richard Sutcliffe, Igor Szoke, Gareth J. F. Jones, Martha Larson
Publisher	CEUR-WS
Number of pages	3
Publication status	Published - Oct 2016
Event	2016 Multimedia Benchmark Workshop, MediaEval 2016 - Hilversum, Netherlands Duration: 20 Oct 2016 → 21 Oct 2016 https://ceur-ws.org/Vol-1739/

Publication series

Name	CEUR Workshop Proceedings
Publisher	CEUR-WS
Volume	1739
ISSN (Print)	1613-0073

Conference

Conference	2016 Multimedia Benchmark Workshop, MediaEval 2016
Country/Territory	Netherlands
City	Hilversum
Period	20/10/16 → 21/10/16
Internet address	https://ceur-ws.org/Vol-1739/

Scopus Subject Areas

Computer Science(all)

Access to Document

http://ceur-ws.org/Vol-1739/MediaEval_2016_paper_29.pdf

Cite this

Liu, Y., Gu, Z., & Cheung, Y. M. (2016). Supervised manifold learning for media interestingness prediction. In G. Gravier, C-H. Demarty, H. Bredin, B. Ionescu, C. Boididou, E. Dellandrea, J. Choi, M. Riegler , R. Sutcliffe, I. Szoke, G. J. F. Jones, & M. Larson (Eds.), Working Notes Proceedings of the MediaEval 2016 Workshop (CEUR Workshop Proceedings; Vol. 1739). CEUR-WS. http://ceur-ws.org/Vol-1739/MediaEval_2016_paper_29.pdf

Liu, Yang ; Gu, Zhonglei ; Cheung, Yiu Ming. / Supervised manifold learning for media interestingness prediction. Working Notes Proceedings of the MediaEval 2016 Workshop. editor / Guillaume Gravier ; Claire-Hélène Demarty ; Hervé Bredin ; Bogdan Ionescu ; Christina Boididou ; Emmanuel Dellandrea ; Jaeyong Choi ; Michael Riegler ; Richard Sutcliffe ; Igor Szoke ; Gareth J. F. Jones ; Martha Larson. CEUR-WS, 2016. (CEUR Workshop Proceedings).

@inproceedings{95ed642ee7b84d1da3c9f8f67daaf077,

title = "Supervised manifold learning for media interestingness prediction",

abstract = "In this paper, we describe the models designed for automatically selecting multimedia data, e.g., image and video segments, which are considered to be interesting for a common viewer. Specifically, we utilize an existing dimensionality reduction method called Neighborhood MinMax Projections (NMMP) to extract the low-dimensional features for predicting the discrete interestingness labels. Meanwhile, we introduce a new dimensionality reduction method dubbed Supervised Manifold Regression (SMR) to learn the compact representations for predicting the continuous interestingness levels. Finally, we use the nearest neighbor classifier and support vector regressor for classification and regression, respectively. Experimental results demonstrate the effectiveness of the low-dimensional features learned by NMMP and SMR.",

author = "Yang Liu and Zhonglei Gu and Cheung, {Yiu Ming}",

note = "Funding Information: The authors would like to thank the reviewer for the helpful comments. This work was supported in part by the National Natural Science Foundation of China under Grant 61503317.; 2016 Multimedia Benchmark Workshop, MediaEval 2016 ; Conference date: 20-10-2016 Through 21-10-2016",

year = "2016",

month = oct,

language = "English",

series = "CEUR Workshop Proceedings",

publisher = "CEUR-WS",

editor = "Guillaume Gravier and Claire-H{\'e}l{\`e}ne Demarty and Herv{\'e} Bredin and Bogdan Ionescu and Christina Boididou and Emmanuel Dellandrea and Jaeyong Choi and {Riegler }, Michael and Richard Sutcliffe and Igor Szoke and Jones, {Gareth J. F.} and Martha Larson",

booktitle = "Working Notes Proceedings of the MediaEval 2016 Workshop",

url = "https://ceur-ws.org/Vol-1739/",

}

Liu, Y, Gu, Z & Cheung, YM 2016, Supervised manifold learning for media interestingness prediction. in G Gravier, C-H Demarty, H Bredin, B Ionescu, C Boididou, E Dellandrea, J Choi, M Riegler , R Sutcliffe, I Szoke, GJF Jones & M Larson (eds), Working Notes Proceedings of the MediaEval 2016 Workshop. CEUR Workshop Proceedings, vol. 1739, CEUR-WS, 2016 Multimedia Benchmark Workshop, MediaEval 2016, Hilversum, Netherlands, 20/10/16. <http://ceur-ws.org/Vol-1739/MediaEval_2016_paper_29.pdf>

Supervised manifold learning for media interestingness prediction. / Liu, Yang; Gu, Zhonglei; Cheung, Yiu Ming.

Working Notes Proceedings of the MediaEval 2016 Workshop. ed. / Guillaume Gravier; Claire-Hélène Demarty; Hervé Bredin; Bogdan Ionescu; Christina Boididou; Emmanuel Dellandrea; Jaeyong Choi; Michael Riegler ; Richard Sutcliffe; Igor Szoke; Gareth J. F. Jones; Martha Larson. CEUR-WS, 2016. (CEUR Workshop Proceedings; Vol. 1739).

Research output: Chapter in book/report/conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Supervised manifold learning for media interestingness prediction

AU - Liu, Yang

AU - Gu, Zhonglei

AU - Cheung, Yiu Ming

N1 - Funding Information: The authors would like to thank the reviewer for the helpful comments. This work was supported in part by the National Natural Science Foundation of China under Grant 61503317.

PY - 2016/10

Y1 - 2016/10

N2 - In this paper, we describe the models designed for automatically selecting multimedia data, e.g., image and video segments, which are considered to be interesting for a common viewer. Specifically, we utilize an existing dimensionality reduction method called Neighborhood MinMax Projections (NMMP) to extract the low-dimensional features for predicting the discrete interestingness labels. Meanwhile, we introduce a new dimensionality reduction method dubbed Supervised Manifold Regression (SMR) to learn the compact representations for predicting the continuous interestingness levels. Finally, we use the nearest neighbor classifier and support vector regressor for classification and regression, respectively. Experimental results demonstrate the effectiveness of the low-dimensional features learned by NMMP and SMR.

AB - In this paper, we describe the models designed for automatically selecting multimedia data, e.g., image and video segments, which are considered to be interesting for a common viewer. Specifically, we utilize an existing dimensionality reduction method called Neighborhood MinMax Projections (NMMP) to extract the low-dimensional features for predicting the discrete interestingness labels. Meanwhile, we introduce a new dimensionality reduction method dubbed Supervised Manifold Regression (SMR) to learn the compact representations for predicting the continuous interestingness levels. Finally, we use the nearest neighbor classifier and support vector regressor for classification and regression, respectively. Experimental results demonstrate the effectiveness of the low-dimensional features learned by NMMP and SMR.

UR - http://ceur-ws.org/Vol-1739/

UR - http://www.scopus.com/inward/record.url?scp=85006320562&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85006320562

T3 - CEUR Workshop Proceedings

BT - Working Notes Proceedings of the MediaEval 2016 Workshop

A2 - Gravier, Guillaume

A2 - Demarty, Claire-Hélène

A2 - Bredin, Hervé

A2 - Ionescu, Bogdan

A2 - Boididou, Christina

A2 - Dellandrea, Emmanuel

A2 - Choi, Jaeyong

A2 - Riegler , Michael

A2 - Sutcliffe, Richard

A2 - Szoke, Igor

A2 - Jones, Gareth J. F.

A2 - Larson, Martha

PB - CEUR-WS

T2 - 2016 Multimedia Benchmark Workshop, MediaEval 2016

Y2 - 20 October 2016 through 21 October 2016

ER -

Supervised manifold learning for media interestingness prediction

Abstract

Publication series

Conference

Scopus Subject Areas

Access to Document

Other files and links

Fingerprint

Cite this