Video summarization via multiview representative selection

Video contents are inherently heterogeneous. To exploit different feature modalities in a diverse video collection for video summarization, we propose to formulate the task as a multiview representative selection problem. The goal is to select visual elements that are representative of a video consi...

Full description

Saved in:
Bibliographic Details
Main Authors: Meng, Jingjing, Wang, Suchen, Wang, Hongxing, Yuan, Junsong, Tan, Yap-Peng
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2019
Subjects:
Online Access:https://hdl.handle.net/10356/106096
http://hdl.handle.net/10220/48870
http://dx.doi.org/10.1109/TIP.2017.2789332
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-106096
record_format dspace
spelling sg-ntu-dr.10356-1060962019-12-06T22:04:29Z Video summarization via multiview representative selection Meng, Jingjing Wang, Suchen Wang, Hongxing Yuan, Junsong Tan, Yap-Peng School of Electrical and Electronic Engineering Rapid-Rich Object Search Lab Video Summarization Multi-view DRNTU::Engineering::Electrical and electronic engineering Video contents are inherently heterogeneous. To exploit different feature modalities in a diverse video collection for video summarization, we propose to formulate the task as a multiview representative selection problem. The goal is to select visual elements that are representative of a video consistently across different views (i.e., feature modalities). We present in this paper the multiview sparse dictionary selection with centroid co-regularization method, which optimizes the representative selection in each view, and enforces that the view-specific selections to be similar by regularizing them towards a consensus selection. We also introduce a diversity regularizer to favor a selection of diverse representatives. The problem can be efficiently solved by an alternating minimizing optimization with the fast iterative shrinkage thresholding algorithm. Experiments on synthetic data and benchmark video datasets validate the effectiveness of the proposed approach for video summarization, in comparison with other video summarization methods and representative selection methods such as K-medoids, sparse dictionary selection, and multiview clustering. MOE (Min. of Education, S’pore) Accepted version 2019-06-20T06:01:31Z 2019-12-06T22:04:29Z 2019-06-20T06:01:31Z 2019-12-06T22:04:29Z 2018 Journal Article Meng, J., Wang, S., Wang, H., Yuan, J., & Tan, Y.-P. (2018). Video summarization via multiview representative selection. IEEE Transactions on Image Processing, 27(5), 2134-2145. doi:10.1109/TIP.2017.2789332 1057-7149 https://hdl.handle.net/10356/106096 http://hdl.handle.net/10220/48870 http://dx.doi.org/10.1109/TIP.2017.2789332 en IEEE Transactions on Image Processing © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TIP.2017.2789332 13 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Video Summarization
Multi-view
DRNTU::Engineering::Electrical and electronic engineering
spellingShingle Video Summarization
Multi-view
DRNTU::Engineering::Electrical and electronic engineering
Meng, Jingjing
Wang, Suchen
Wang, Hongxing
Yuan, Junsong
Tan, Yap-Peng
Video summarization via multiview representative selection
description Video contents are inherently heterogeneous. To exploit different feature modalities in a diverse video collection for video summarization, we propose to formulate the task as a multiview representative selection problem. The goal is to select visual elements that are representative of a video consistently across different views (i.e., feature modalities). We present in this paper the multiview sparse dictionary selection with centroid co-regularization method, which optimizes the representative selection in each view, and enforces that the view-specific selections to be similar by regularizing them towards a consensus selection. We also introduce a diversity regularizer to favor a selection of diverse representatives. The problem can be efficiently solved by an alternating minimizing optimization with the fast iterative shrinkage thresholding algorithm. Experiments on synthetic data and benchmark video datasets validate the effectiveness of the proposed approach for video summarization, in comparison with other video summarization methods and representative selection methods such as K-medoids, sparse dictionary selection, and multiview clustering.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Meng, Jingjing
Wang, Suchen
Wang, Hongxing
Yuan, Junsong
Tan, Yap-Peng
format Article
author Meng, Jingjing
Wang, Suchen
Wang, Hongxing
Yuan, Junsong
Tan, Yap-Peng
author_sort Meng, Jingjing
title Video summarization via multiview representative selection
title_short Video summarization via multiview representative selection
title_full Video summarization via multiview representative selection
title_fullStr Video summarization via multiview representative selection
title_full_unstemmed Video summarization via multiview representative selection
title_sort video summarization via multiview representative selection
publishDate 2019
url https://hdl.handle.net/10356/106096
http://hdl.handle.net/10220/48870
http://dx.doi.org/10.1109/TIP.2017.2789332
_version_ 1681045432983093248