Interactive Indexing and Retrieval -- A Comparative Study on the Use of Multi-Label Classification Techniques for Concept-Based Video Indexing and Annotation -- Coherence Analysis of Metrics in LBP space for Interactive Face Retrieval -- A Hybrid Machine-Crowd Approach to Photo Retrieval Result Diversification -- Visual Saliency Weighting and Cross-Domain Manifold Ranking for Sketch-based Image Retrieval -- A Novel Approach for Semantics-enabled Search of Multimedia Documents on the Web -- Video to Article Hyperlinking by Multiple Tag Property Exploration -- Rebuilding Visual Vocabulary via Spatial-Temporal Context Similarity for Video Retrieval -- Approximating the Signature Quadratic Form Distance Using Scalable Feature Signatures -- A Novel Human Action Representation via Convolution of Shape-Motion Histograms -- How do Users Search with basic HTML5 Video Players? -- Multimedia Collections -- Visual Recognition by Exploiting Latent Social Links in Image Collections -- Collections for Automatic Image Annotation and Photo Tag Recommendation -- Graph-based multimodal clustering for social event detection in large collections of images -- Tag Relatedness using Laplacian Score Feature Selection & Adapted Jensen-Shannon Divergence -- User Intentions in Digital Photo Production: a Test Data Set -- Personal Media Reunion: Re-Collecting Media Content Scattered over Smart Devices and Social Networks -- Summarised presentation of personal photo sets -- Applications -- MOSRO: Enabling Mobile Sensing for Real-Scene Objects with Grid based Structured Output Learning -- Travel Buddy : Interactive Travel Route Recommendation with a Visual Scene Interface -- Who's the best Charades player? Mining Iconic Movement of Semantic Concepts -- Tell me about TV commercials of this product -- A data-driven personalized digital ink for Chinese characters -- Local Segmentation for Pedestrian Tracking in Dense Crowds -- An Optimization Model for Aesthetic Two-Dimensional Barcodes -- Live Key Frame Extraction in User Generated Content scenarios for Embedded Mobile Platforms -- Understanding Affective Content of Music Videos Through Learned Representations -- Robust Image Restoration via Reweighted Low-Rank Matrix Recovery -- Learning to Infer Public Emotions from Large-scale Networked Voice Data -- Joint People Recognition across Photo Collections using Sparse Markov Random Fields -- Temporal Analysis -- Event Detection by Velocity Pyramid -- Fusing appearance and spatio-temporal features for multiple camera tracking -- A Dense SURF and Triangulation based Spatio-Temporal Feature for Action Recognition -- Resource Constrained Multimedia Event Detection -- Random Matrix Ensembles of Time Correlation Matrices to Analyze Visual Life logs -- 3D and Augmented Reality -- Exploring Distance-Aware Weighting Strategies for Accurate Reconstruction of Voxel-Based 3D Synthetic Models -- Exploitation of Gaze Data for Photo Region Labeling in an Immersive Environment -- MR Simulation for Re-Wallpapering a Room in a Free-Hand Movie -- Segment and Label Indoor Scene based on RGB-D for the Visually Impaired -- A Low-cost Head and Eye Tracking System for Realistic Eye Movements in Virtual Avatars -- Real-time Skeleton-tracking-based Human Action Recognition Using Kinect Data -- Kinect vs. Low-cost Inertial Sensing For Gesture Recognition -- Yoga Posture Recognition for Self-Training -- Real-Time Gaze Estimation using a Kinect and a HD Webcam -- Compression, Trans coding & Streaming -- A Framework of Video Coding for Compressing Near-Duplicate Videos -- An improved similarity-based fast coding unit depth decision algorithm for inter-frame coding in HEVC -- Low-Complexity Rate-Distortion Optimization Algorithms for HEVC Intra Prediction -- Stixel on the Bus: An Efficient Lossless Compression Scheme for Depth Information in Traffic Scenarios -- A New Saliency Model using Intra Coded High Efficiency Video Coding(HEVC) Frames -- Multiple Reference Frame Trans coding from H.264/AVC to HEVC.

The two-volume set LNCS 8325 and 8326 constitutes the thoroughly refereed proceedings of the 20th Anniversary International Conference on Multimedia Modeling, MMM 2014, held in Dublin, Ireland, in January 2014. The 46 revised regular papers, 11 short papers, and 9 demonstration papers were carefully reviewed and selected from 176 submissions. 28 special session papers and 6 papers from Video Browser Showdown workshop are also included in the proceedings. The papers included in these two volumes cover a diverse range of topics including: applications of multimedia modelling, interactive retrieval, image and video collections, 3D and augmented reality, temporal analysis of multimedia content, compression and streaming. Special session papers cover the following topics: Mediadrom: artful post-TV scenarios, MM analysis for surveillance video and security applications, 3D multimedia computing and modeling, social geo-media analytics and retrieval, multimedia hyperlinking and retrieval.