Special Session: Mediadrom: Artful Post-TV Scenarios -- Organising Crowd-Sourced Media Content via a Tangible Desktop Application -- Scenarizing Metropolitan Views: FlanoGraphing the urban spaces -- Scenarizing CADastre Exquisse: a crossover between snoezeling in hospitals/domes, and authoring/experiencing soundful comic strips -- An interactive device for exploring thematically sorted art-works -- Special Session: MM Analysis for Surveillance Video and Security Applications -- Hierarchical Audio-Visual Surveillance for Passenger Elevators -- An evaluation of local action descriptors for human action classification in the presence of occlusion -- Online Identification of Primary Social Groups -- Gait based gender recognition using Sparse Spatio Temporal Features -- Perspective Multiscale Detection and Tracking of Persons -- Human action recognition in video via fused optical flow and moment features - towards a hierarchical approach to complex scenario recognition -- Special Session: 3D Multimedia Computing and Modeling -- Sparse Patch Coding for 3D Model Retrieval -- 3D Object Classification Using Deep Belief Networks -- Pursuing Detector Efficiency For Simple Scene Pedestrian Detection -- Multi-view Action Synchronization In Complex Background -- Parameter-Free Inter-view Depth Propagation for Mobile Free-view Video -- Coverage Field Analysis to the Quality of Light Field Rendering -- Special Session: Social Geo-Media Analytics and Retrieval -- Personalized Recommendation by Exploring Social Users' Behaviors -- Where is the news breaking? Towards a location-based event detection framework for journalists -- Location-Aware Music Artist Recommendation -- Task-driven Image Retrieval using Geographic Information -- The Evolution of Research on Multimedia Travel Guide Search and Recommender Systems -- Special Session: Multimedia Hyperlinking and Retrieval -- Average Precision: Good Guide Or False Friend to Multimedia Search Effectiveness? -- An Investigation into Feature Effectiveness for Multimedia Hyperlinking -- Mining the Web for Multimedia-based Enriching -- Short Papers -- Spatial Similarity Measure of Visual Phrases for Image Retrieval -- Semantic based Background Music Recommendation for Home Videos -- Smoke Detection Based on a Semi-supervised Clustering Model -- Empirical exploration of extreme SVM-RBF parameter values for visual object classification -- Real-World Event Detection Using Flickr Images -- Spectral Classification of 3D Articulated Shapes -- Improving Scene Detection Algorithms Using new Similarity Measures -- EvoTunes: Crowdsourcing-based Music Recommendation -- Affect Recognition using Magnitude Models of Motion -- Effects of Audio Compression on Chord Recognition -- The Perceptual Characteristics of 3D Orientation -- Demonstrations -- Folkioneer: Efficient Browsing of Community Geotagged Images on a Worldwide Scale -- Muithu: A touch-based Annotation Interface for Activity Logging in the Norwegian Premier League -- FoodCam: A Real-time Mobile Food Recognition System employing Fisher Vector -- The LIRE Request Handler: A Solr Plug-In for Large Scale Content Based Image Retrieval -- M3+P3+O3=Multi-D Photo Browsing -- Tools for User Interaction in Immersive Environments -- Resic: A Tool for Music Stretching Resistance Estimation -- A Visual Information Retrieval System for Radiology Reports and the Medical Literature -- Eolas: Video Retrieval Application for Helping Tourists -- Video Browser Showdown -- Audio-Visual Classification Video Browser -- Content-based Video Browsing with Collaborating Mobile Clients -- Browsing Linked Video Collections for Media Production -- VERGE: An Interactive Search Engine for Browsing Video Collections -- Signature-based Video Browser -- NII-UIT: A Tool for Known Item Search by Sequential Pattern Filtering.