Learning an Ontology for Visual Tasks -- Ontology and Algorithms Integration for Image Analysis -- EmotiWord: Affective Lexicon Creation with Application to Interaction and Multimedia Data -- A Bayesian Active Learning Framework for a Two-Class Classification Problem -- Unsupervised Classification of SAR Images Using Hierarchical Agglomeration and EM -- Geometrical and Textural Component Separation with Adaptive Scale Selection -- Bayesian Shape from Silhouettes -- Shape Retrieval and Recognition on Mobile Devices -- Directionally Selective Fractional Wavelet Transform Using a 2-D Non-separable Unbalanced Lifting Structure -- Visible and Infrared Image Registration Employing Line-Based Geometric Analysis -- Texture Recognition Using Robust Markovian Features -- A Plausible Texture Enlargement and Editing Compound Markovian Mode -- Bidirectional Texture Function Simultaneous Autoregressive Model -- Analysis of Human Gaze Interactions with Texture and Shape -- Rich Internet Application for Semi-automatic Annotation of Semantic Shots on Keyframes -- Labeling TV Stream Segments with Conditional Random Fields -- Foreground Objects Segmentation for Moving Camera Scenarios Based on SCGMM -- Real Time Image Analysis for Infomobilit -- Tracking the Saliency Features in Images Based on Human Observation Statistics.

This book constitutes the refereed proceedings of the International Workshop  MUSCLE 2011 on Computational Intelligence for Multimedia Understanding, organized by the ERCIM working group in Pisa, Italy on December 2011. The 18 revised full papers were carefully reviewed and selected from over numerous submissions. The papers cover the following topics: multisensor systems, multimodal analysis, crossmodal data analysis and clustering, mixed-reality applications, activity and object detection and recognition, text and speech recognition, multimedia labeling, semantic annotation, and metadata, multimodal indexing and searching in very large data-bases; and case studies.