AI-Based Semantic Multimedia Indexing and Retrieval for Social Media on Smartphones

Felix Engel,Matthias Hemmje,Paul Mc Kevitt,Stefan Wagenpfeil

doi:10.3390/info12010043

Abstract

To cope with the growing number of multimedia assets on smartphones and social media, an integrated approach for semantic indexing and retrieval is required. Here, we introduce a generic framework to fuse existing image and video analysis tools and algorithms into a unified semantic annotation, indexing and retrieval model resulting in a multimedia feature vector graph representing various levels of media content, media structures and media features. Utilizing artificial intelligence (AI) and machine learning (ML), these feature representations can provide accurate semantic indexing and retrieval. Here, we provide an overview of the generic multimedia analysis framework (GMAF) and the definition of a multimedia feature vector graph framework (MMFVGF). We also introduce AI4MMRA to detect differences, enhance semantics and refine weights in the feature vector graph. To address particular requirements on smartphones, we introduce an algorithm for fast indexing and retrieval of graph structures. Experiments to prove efficiency, effectiveness and quality of the algorithm are included. All in all, we describe a solution for highly flexible semantic indexing and retrieval that offers unique potential for applications such as social media or local applications on smartphones.

Highlights

IntroductionOf them taken on smartphones, and this number is still increasing [1]
Introduction and MotivationEvery year, more than 1.2 trillion digital photos and videos are taken; more than 85%of them taken on smartphones, and this number is still increasing [1]
To exhibit our conceptual approach, we provide several selected implementations of the relevant components of generic multimedia analysis framework (GMAF), multimedia feature vector graph framework (MMFVGF) and graph codes

Summary

Introduction

Of them taken on smartphones, and this number is still increasing [1]. This volume of media is neither manageable for users nor for content providers and/or platforms such as social media. Cloud services and storage costs continue to decrease, which makes it simple and affordable for users to store large volumes of media assets on their smartphones [2]. Smartphone vendors provide solutions enabling access to all user media assets directly through the device by transparently up- and downloading them to cloud services [3]. The large volume of multimedia assets provides significant challenges for indexing, querying and retrieval algorithms. There is great progress in image analysis, object detection and content analysis [4], there is still potential for improvement and further research to optimize the results of information retrieval algorithms

Results

Discussion

Conclusion