Enhanced Retrieval and Browsing in the IMOTION System

Authors
Luca Rossetto, Ivan Giangreco, Claudiu Tănase, Heiko Schuldt, Stéphane Dupont, Omar Seddati
Type
In Proceedings
Date
2017/1
Appears in
Proceedings of the International Conference on Multimedia Modeling (MMM)
Location
Reykjavik, Iceland
Publisher
Springer
Pages
469-474
Abstract

This paper presents the IMOTION system in its third version. While still focusing on sketch-based retrieval, we improved upon the semantic retrieval capabilities introduced in the previous version by adding more detectors and improving the interface for semantic query speci cation. In addition to previous year's system, we increase the role of features obtained from Deep Neural Networks in three areas: semantic class labels for more entry-level concepts, hidden layer activation vectors for query-by-example and 2D semantic similarity results display. The new graph-based result navigation interface further enriches the system's browsing capabilities. The updated database storage system ADAMpro designed from the ground up for large scale multimedia applications ensures the scalability to steadily growing collections.

 

https://dx.doi.org/10.1007/978-3-319-51814-5_43

Comments

Winner VBS 2017