Query-by-Emoji Video Search

Open Access
Authors
Publication date 2015
Book title MM'15
Book subtitle proceedings of the 2015 ACM Multimedia Conference: October 26-30, 2015, Brisbane, Australia
ISBN (electronic)
  • 9781450334594
Event 2015 ACM International Conference on Multimedia
Pages (from-to) 735-736
Publisher New York, NY: Association for Computing Machinery
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract
This technical demo presents Emoji2Video, a query-by-emoji interface for exploring video collections. Ideogram-based video search and representation presents an opportunity for an intuitive, visual interface and concise non-textual summary of video contents, in a form factor that is ideal for small screens. The demo allows users to build search strings comprised of ideograms which are used to query a large dataset of YouTube videos. The system returns a list of the top-ranking videos for the user query along with an emoji summary of the video contents so that users may make an informed decision whether to view a video or refine their search terms. The ranking of the videos is done in a zero-shot, multi-modal manner that employs an embedding space to exploit semantic relationships between user-selected ideograms and the video's visual and textual content.
Document type Conference contribution
Language English
Published at https://doi.org/10.1145/2733373.2807961
Downloads
p735-cappallo (Final published version)
Permalink to this page
Back