Multimedia Data Mining and Analytics

Aaron K. Baughman is a member of the Special Events Group at IBM (USA) for World Wide Sports. Previously, he was Technical Lead on a DeepQA Embed Research project that included an instance of the Jeopardy! Challenge.Jiang (John) Gao is a Principal Scientist in the Advanced Development and Technology Group at Nokia USA, working on multimedia and mobile applications, data mining and computer vision.Jia-Yu Pan is a software engineer at Google (USA), working on data mining and anomaly detection in big data.Valery A. Petrushin is a Principal Scientist in the Research and Development Group at Opera Solutions (USA). His previous publications include the successful Springer title Multimedia Data Mining and Knowledge Discovery.

"Multimedia data mining and analytics: disruptive innovation highlights new applications in multimedia data mining, presenting fascinating techniques together with comprehensive cases in practice. ... this book is valuable for the insight it provides related to the challenges faced by fast developing technologies, their current needs and future promise. It is a practical guide, a useful handbook for academies and industry practitioners who have interest in multimedia data analysis." (Shanshan Qi, Information Technology & Tourism, Vol. 16, 2016)

• Part I: Introduction.- Disruptive Innovation: Large Scale Multimedia Data Mining.- Part II: Mobile and Social Multimedia Data Exploration.- Sentiment Analysis Using Social Multimedia.- Twitter as a Personalizable Information Service.- Mining Popular Routes from Social Media.- Social Interactions over Location-Aware Multimedia Systems.- In-house Multimedia Data Mining.- Content-based Privacy for Consumer-Produced Multimedia.- Part III: Biometric Multimedia Data Processing.- Large-scale Biometric Multimedia Processing.- Detection of Demographics and Identity in Spontaneous Speech and Writing.- Part IV: Multimedia Data Modeling, Search and Evaluation.- Evaluating Web Image Context Extraction.- Content Based Image Search for Clothing Recommendations in E-Commerce.- Video Retrieval based on Uncertain Concept Detection using Dempster-Shafer Theory.- Multimodal Fusion: Combining Visual and Textual Cues for Concept Detection in Video.- Mining Videos for Featuresthat Drive Attention.- Exposing Image Tampering with the Same Quantization Matrix.- Part V: Algorithms for Multimedia Data Presentation, Processing and Visualization.- Fast Binary Embedding for High-Dimensional Data.- Fast Approximate K-Means via Cluster Closures.- Fast Neighborhood Graph Search using Cartesian Concatenation.- Listen to the Sound of Data.