ABSTRACT
ABSTRACT Nowadays, data heterogeneity is one of the most critical features for multi media Big Data; searching heterogeneous multimedia documents reecting users’ query intent from a Big Data environment is a dicult task in information retrieval and pattern recognition. This chapter proposes a heterogeneous multimedia Big Data retrieval framework that can achieve good retrieval accuracy and performance. e chapter is organized as follows. In Section 18.1, we address the particularity of heterogeneous
CONTENTS 18.1 Introduction 358 18.2 Related Work 359 18.3 Proposed Framework 361
18.3.1 Overview 361 18.3.2 Semantic Annotation 362 18.3.3 Optimization and User Feedback 364 18.3.4 Semantic Representation 364 18.3.5 NoSQL-Based Semantic Storage 366 18.3.6 Heterogeneous Multimedia Retrieval 366
18.4 Performance Evaluation 367 18.4.1 Running Environment and Soware Tools 367 18.4.2 Performance Evaluation Model 369 18.4.3 Precision Ratio Evaluation 370 18.4.4 Time and Storage Cost 371
18.5 Discussions and Conclusions 372 Acknowledgments 373 References 373
multimedia retrieval in a Big Data environment and introduce the background of the topic. en literatures related to current multimedia retrieval approaches are briey reviewed, and the general concept of the proposed framework is introduced briey in Section 18.2. In Section 18.3, the description of this framework is given in detail including semantic information extraction, representation, storage, and multimedia Big Data retrieval. e performance evaluations are shown in Section 18.4, and nally, we conclude the chapter in Section 18.5.
