Efficient Search with an Interactive Video Retrieval System for Novice Users in IVR4B

Conference proceedings article

Authors/Editors

CHONLAMETH ARPNIKANONDT

Strategic Research Themes

Machine Learning (Big Data Analytics)

Publication Details

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

Publisher: Association for Computing Machinery

Publication year: 2023

Start page: 168

End page: 172

Number of pages: 5

ISBN: 979-840070912-8

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85182599783&doi=10.1145%2f3617233.3617273&partnerID=40&md5=f08afcae96da2d2c594b9eea71de6096

Languages: English-Great Britain (EN-GB)

View on publisher site

Abstract

In this paper, we present the second release of VideoCLIP, an interactive CLIP-based video retrieval system that participated in the Video Browser Showdown 2023. While we continue to use the underlying architecture to map the content between image and text, we concentrate on improving the user experience for novice users. Specifically, we have implemented three different query modalities and redesigned the user interface in order to adapt to the context of the Interactive Video Retrieval for Beginners (IVR4B) workshop. These modifications ultimately aim to provide newcomers with a simple and efficient user experience to locate the desired videos. ฉ 2023 Owner/Author.

Keywords

retrieval system, user interface