Toward Optimized Multimodal Concept Indexing

Type: 
Journal article
Proceedings: 
Publisher: 
Journal of Transactions on Computational Collective Intelligence (TCCI), 10190-XXVI
Pages: 
144 - 161
ISBN: 
Year: 
2017
Abstract: 
Information retrieval on the (social) web moves from a pure term-frequency-based approach to an enhanced method that includes conceptual multimodal features on a semantic level. In this paper, we present an approach for semantic-based keyword search and focus especially on its optimization to scale it to real-world sized collections in the social media domain. Furthermore, we present a faceted indexing framework and architecture that relates content to semantic concepts to be indexed and searched semantically. We study the use of textual concepts in a social media domain and observe a significant improvement from using a concept-based solution for keyword searching. We address the problem of time-complexity that is a critical issue for concept-based methods by focusing on optimization to enable larger and more real-world style applications.
TU Focus: 
Computational Science and Engineering
Reference: 

N. Rekabsaz, R. Bierig, M. Lupu, A. Hanbury:
"Toward Optimized Multimodal Concept Indexing";
Journal of Transactions on Computational Collective Intelligence (TCCI), 10190 (2017), XXVI; S. 144 - 161.

Zusätzliche Informationen

Last changed: 
10.12.2017 09:43:56
TU Id: 
263992
Accepted: 
Accepted
Invited: 
Department Focus: 
Author List: 
N. Rekabsaz, R. Bierig, M. Lupu, A. Hanbury
Abstract German: