VCR: Video representation for Contextual Retrieval

Oron Nir, Idan Vidra, Avi Neeman, Barak Kinarti, Ariel Shamir

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Streamlining content discovery in media archives requires advanced data representations and effective visualization techniques for clear communication of video topics to users. The proposed system addresses the challenge of efficiently navigating large video collections by exploiting a fusion of visual, audio, and textual features to accurately index and categorize video content through a text-based method. Additionally, semantic embeddings are employed to provide contextually relevant information and recommendations to users, resulting in an intuitive and engaging exploratory experience over our topics ontology map using LLMs (GitHub).

Original languageEnglish
Title of host publicationCMLDS 2024 - 2024 International Conference on Computing, Machine Learning and Data Science, Conference Proceedings
PublisherAssociation for Computing Machinery
ISBN (Electronic)9798400716393
DOIs
StatePublished - 12 Apr 2024
Externally publishedYes
Event2024 International Conference on Computing, Machine Learning and Data Science, CMLDS 2024 - Singapore, Singapore
Duration: 12 Apr 202414 Apr 2024

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2024 International Conference on Computing, Machine Learning and Data Science, CMLDS 2024
Country/TerritorySingapore
CitySingapore
Period12/04/2414/04/24

Keywords

  • Archive Exploration
  • Media Search
  • Video Representation

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint

Dive into the research topics of 'VCR: Video representation for Contextual Retrieval'. Together they form a unique fingerprint.

Cite this