Multi-View Manifold Learning For Media Interestingness Prediction
Keywords
Media interestingness analysis; Multi-view manifold learning
Abstract
Media interestingness prediction plays an important role in many real-world applications and attracts much research attention recently. In this paper, we aim to investigate this problem from the perspective of supervised feature extraction. Specifically, we design a novel algorithm dubbed Multi-view Manifold Learning (M2L) to uncover the latent factors that are capable of distinguishing interesting media data from non-interesting ones. By modelling both geometry preserving criterion and discrimination maximization criterion in a unified framework, M2L learns a common subspace for data from multiple views. The analytical solution of M2 L is obtained by solving a generalized eigen-decomposition problem. Experiments on the Predicting Media Interestingness Dataset validate the effectiveness of the proposed method.
Publication Date
6-6-2017
Publication Title
ICMR 2017 - Proceedings of the 2017 ACM International Conference on Multimedia Retrieval
Number of Pages
308-314
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1145/3078971.3079021
Copyright Status
Unknown
Socpus ID
85021816539 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85021816539
STARS Citation
Liu, Yang; Gu, Zhonglei; Cheung, Yiu Ming; and Hua, Kien A., "Multi-View Manifold Learning For Media Interestingness Prediction" (2017). Scopus Export 2015-2019. 7140.
https://stars.library.ucf.edu/scopus2015/7140