Interactive exploration of journalistic video footage through multimodal semantic matching

Title

Interactive exploration of journalistic video footage through multimodal semantic matching

 Author

Ibrahimi, Sarah (Universiteit van Amsterdam)
Chen, Shuo (Universiteit van Amsterdam)
Arya, Devanshu (Universiteit van Amsterdam)
Câmara, Arthur (TU Delft Web Information Systems)
Chen, Yunlu (Universiteit van Amsterdam)
Crijns, Tanja (RTL Nederland)
Van Der Goes, Maurits (RTL Nederland)
Mensink, Thomas (Google LLC)
Van Miltenburg, Emiel (Tilburg University)

Date

2019-10-15

 Abstract

This demo presents a system for journalists to explore video footage for broadcasts. Daily news broadcasts contain multiple news items that consist of many video shots and searching for relevant footage is a labor intensive task. Without the need for annotated video shots, our system extracts semantics from footage and automatically matches these semantics to query terms from the journalist. The journalist can then indicate which aspects of the query term need to be emphasized, e.g. the title or its thematic meaning. The goal of this system is to support the journalists in their search process by encouraging interaction and exploration with the system.


 Subject

Exploration
Matching
Multimodal
Semantics
Video

 To reference this document use:

http://resolver.tudelft.nl/uuid:63fe23c2-11cb-4765-9ea5-4e921daff42e

 DOI

https://doi.org/10.1145/3343031.3350597

 Publisher

Association for Computing Machinery (ACM)

 ISBN

9781450368896

 Source

MM 2019 - Proceedings of the 27th ACM International Conference on Multimedia

 Event

27th ACM International Conference on Multimedia, MM 2019, 2019-10-21 → 2019-10-25, Nice, France

 Part of collection

Institutional Repository

 Document type

conference paper

 Rights

© 2019 Sarah Ibrahimi, Shuo Chen, Devanshu Arya, Arthur Câmara, Yunlu Chen, Tanja Crijns, Maurits Van Der Goes, Thomas Mensink, Emiel Van Miltenburg, More Authors
Files
PDF p2196_ibrahimi.pdf 4.42 MB
Close viewer