Multimodal Location Estimation of Videos and Images - Softcover

Über die Autorin bzw. den Autor

Dr. Gerald Friedland is the Director at the  Audio and Multimedia Research, International Computer Science Institute
Dr. Jaeyoung Chois is a Researcher at the Audio and Multimedia Research, International Computer Science Institute

Von der hinteren Coverseite

This book presents an overview of the field of multimodal location estimation, i.e. using acoustic, visual, and/or textual cues to estimate the shown location of a video recording. The authors' sample research results in this field in a unified way integrating research work on this topic that focuses on different modalities, viewpoints, and applications. The book describes fundamental methods of acoustic, visual, textual, social graph, and metadata processing as well as multimodal integration methods used for location estimation. In addition, the text covers benchmark metrics and explores the limits of the technology based on a human baseline.

· Discusses localization of multimedia data;

· Examines fundamental methods of establishing location metadata for images and videos (other than GPS tagging);

· Covers Data-Driven as well as Semantic Location Estimation.