Please use this identifier to cite or link to this item:
https://doi.org/10.1109/TCSVT.2018.2889514
DC Field | Value | |
---|---|---|
dc.title | Unsupervised Video Action Clustering via Motion-Scene Interaction Constraint | |
dc.contributor.author | Bo Peng | |
dc.contributor.author | Jianjun Lei | |
dc.contributor.author | Huazhu Fu | |
dc.contributor.author | Changqing Zhang | |
dc.contributor.author | Tat-Seng Chua | |
dc.contributor.author | Xuelong Li | |
dc.date.accessioned | 2020-10-21T04:03:03Z | |
dc.date.available | 2020-10-21T04:03:03Z | |
dc.date.issued | 2020-01-01 | |
dc.identifier.citation | Bo Peng, Jianjun Lei, Huazhu Fu, Changqing Zhang, Tat-Seng Chua, Xuelong Li (2020-01-01). Unsupervised Video Action Clustering via Motion-Scene Interaction Constraint. IEEE Transactions on Circuits and Systems for Video Technology 30 (1) : 131 - 144. ScholarBank@NUS Repository. https://doi.org/10.1109/TCSVT.2018.2889514 | |
dc.identifier.issn | 10518215 | |
dc.identifier.uri | https://scholarbank.nus.edu.sg/handle/10635/178637 | |
dc.description.abstract | In the past few years, scene contextual information has been increasingly used for action understanding with promising results. However, unsupervised video action clustering using context has been less explored, and existing clustering methods cannot achieve satisfactory performances. In this paper, we propose a novel unsupervised video action clustering method by using the motion-scene interaction constraint (MSIC). The proposed method takes the unique static scene and dynamic motion characteristics of video action into account, and develops a contextual interaction constraint model under a self-representation subspace clustering framework. First, the complementarity of multi-view subspace representation in each context is explored by single-view and multi-view constraints. Afterward, the context-constrained affinity matrix is calculated and the MSIC is introduced to mutually regularize the disagreement of subspace representation in scene and motion. Finally, by jointly constraining the complementarity of multi-views and the consistency of multi-contexts, an overall objective function is constructed to guarantee the video action clustering result. The experiments on four video benchmark datasets (Weizmann, KTH, UCFsports, and Olympic) demonstrate that the proposed method outperforms the state-of-the-art methods. © 1991-2012 IEEE. | |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | |
dc.subject | Video action clustering | |
dc.subject | intra-context constraint | |
dc.subject | contextual interaction constraint | |
dc.subject | subspace representation | |
dc.type | Article | |
dc.contributor.department | DEPARTMENT OF COMPUTER SCIENCE | |
dc.description.doi | 10.1109/TCSVT.2018.2889514 | |
dc.description.sourcetitle | IEEE Transactions on Circuits and Systems for Video Technology | |
dc.description.volume | 30 | |
dc.description.issue | 1 | |
dc.description.page | 131 - 144 | |
dc.description.coden | ITCTE | |
dc.grant.id | R-252-300-002-490 | |
dc.grant.fundingagency | Infocomm Media Development Authority | |
dc.grant.fundingagency | National Research Foundation | |
Appears in Collections: | Elements Staff Publications |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
Unsupervised Video Action Clustering via Motion-Scene Interaction Constraint.pdf | 5.28 MB | Adobe PDF | OPEN | None | View/Download |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.