Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Replay detection and multi-stream synchronization in CS:GO game streams using content-based Image retrieval and Image signature matching

Ninh, Van-Tu orcid logoORCID: 0000-0003-0641-8806, Le, Tu-Khiem orcid logoORCID: 0000-0003-3013-9380, Dang-Nguyen, Duc-Tien orcid logoORCID: 0000-0002-2761-2213 and Gurrin, Cathal orcid logoORCID: 0000-0003-2903-3968 (2019) Replay detection and multi-stream synchronization in CS:GO game streams using content-based Image retrieval and Image signature matching. In: The MediaEval 2019, 10th Anniversary Workshop, 27 - 29 Oct 2019, Antipolis, France.

Abstract
In GameStory: The 2019 Video Game Analytics Challenge, two main tasks are nominated to solve in the challenge, which are replay detection - multi-stream synchronization, and game story summarization. In this paper, we propose a data-driven based approach to solve the first task: replay detection - multi-stream synchronization. Our solution aims to determine the replays which lie between two logo-transitional endpoints and synchronize them with their sources by extracting frames from videos, then applying image processing and retrieval remedies. In detail, we use the Bag of Visual Words approach to detect the logo-transitional endpoints, which contains multiple replays in between, then employ an Image Signature Matching algorithm for multi-stream synchronization and replay boundaries refinement. The best configuration of our proposed solution manages to achieve the second-highest scores in all evaluation metrics of the challenge.
Metadata
Item Type:Conference or Workshop Item (Speech)
Event Type:Workshop
Refereed:Yes
Subjects:Computer Science > Algorithms
Computer Science > Information retrieval
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Research Initiatives and Centres > ADAPT
Published in: MediaEval 2019 Multimedia Benchmark Workshop. CEUR Workshop Proceedings 1(2670). CEUR-WS.
Publisher:CEUR-WS
Official URL:http://ceur-ws.org/Vol-2670/MediaEval_19_paper_12....
Copyright Information:© 2019 The Authors. Creative Commons License Attribution 4.0 International (CC BY 4.0)
Funders:Science Foundation Ireland under grant numbers SFI/12/RC2289 and 13/RC/2106., ADAPT Centre, DCU, INSIGHT Centre for Data Analytics
ID Code:23953
Deposited On:26 Nov 2019 11:00 by Van Tu Ninh . Last Modified 15 Dec 2021 15:48
Documents

Full text available as:

[thumbnail of MediaEval_GameStoryTask2019.pdf]
Preview
 PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
629kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record