VideoCLIP: An Interactive CLIP-based Video Retrieval System at VBS2023

Conference proceedings article

Authors/Editors

Strategic Research Themes

Publication Details

Author list: Nguyen, Thao-Nhu; Puangthamawathanakun, Bunyarit; Caputo, Annalina; Healy, Graham; Nguyen, Binh T.;
Arpnikanondt, Chonlameth; Gurrin, Cathal;

Publisher: Springer Science and Business Media Deutschland GmbH

Publication year: 2023

Volume number: 13833 LNCS

Start page: 671

End page: 677

Number of pages: 7

ISBN: 9783031270765

ISSN: 3029743

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85152586672&doi=10.1007%2f978-3-031-27077-2_57&partnerID=40&md5=b5b8bfe02eab30709d5a210ccafcf1ce

Languages: English-Great Britain (EN-GB)

View in Web of Science | View on publisher site | View citing articles in Web of Science

Abstract

In this paper, we present an interactive video retrieval system named VideoCLIP developed for the Video Browser Showdown 2023. To support users in solving retrieval tasks, the system enables search using a variety of modalities, such as rich text, dominant colour, OCR, and query-by-image. Moreover, a new search modality has been added to empower our core engine, which is inherited from the Contrastive Language-Image Pre-training (CLIP) model. Finally, the user interface is enhanced to display results in groups in order to reduce the effort for a user when locating potentially relevant targets. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

Embedding model, Interactive video retrieval, Video browser showdown