Supervised manifold learning for media interestingness prediction

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

5 Citations (Scopus)


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 languageEnglish
Title of host publicationWorking Notes Proceedings of the MediaEval 2016 Workshop
EditorsGuillaume 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
Number of pages3
Publication statusPublished - Oct 2016
Event2016 Multimedia Benchmark Workshop, MediaEval 2016 - Hilversum, Netherlands
Duration: 20 Oct 201621 Oct 2016

Publication series

NameCEUR Workshop Proceedings
ISSN (Print)1613-0073


Conference2016 Multimedia Benchmark Workshop, MediaEval 2016
Internet address

Scopus Subject Areas

  • Computer Science(all)


Dive into the research topics of 'Supervised manifold learning for media interestingness prediction'. Together they form a unique fingerprint.

Cite this