Computer Vision - ACCV 2012 [electronic resource] : 11th Asian Conference on Computer Vision, Daejeon, Korea, November 5-9, 2012, Revised Selected Papers, Part II / edited by Kyoung Mu Lee, Yasuyuki Matsushita, James M. Rehg, Zhanyi Hu.

Poster Session 3 (Continued): Segmentation, Grouping, and Classification Multi-layer Spectral Clustering for Video Segmentation -- Video Co-segmentation -- Globally Minimal Path Method Using Dynamic Speed Functions Based on Progressive Wave Propagation -- Vanishing Points Estimation and Line Classification in a Manhattan World -- Online Learning for Fast Segmentation of Moving Objects -- A Linear Programming Based Method for Joint Object Region Matching and Labeling -- Using Models of Objects with Deformable Parts for Joint Categorization and Segmentation of Objects -- A Robust Stereo Prior for Human Segmentation -- Voronoi-Based Extraction of a Feature Skeleton from Noisy Triangulated Surfaces -- Maximal Cliques Based Rigid Body Motion Segmentation with a RGB-D Camera -- Online Web-Data-Driven Segmentation of Selected Moving Objects in Videos -- Multi-Level Structured Image Coding on High-Dimensional Image Representation -- Incremental Slow Feature Analysis with Indefinite Kernel for Online Temporal Video Segmentation -- Texture Classification Based on BIMF Monogenic Signals -- Toward Perception-Based Shape Decomposition -- Co-regularized PLSA for Multi-view Clustering -- Oral Session 4: Image Representation -- Quadra-Embedding: Binary Code Embedding with Low Quantization Error -- Learning a Context Aware Dictionary for Sparse Representation -- Robust Multiple-Instance Learning with Superbags -- Poster Session 4: Image/Video Retrieval and Medical Image Analysis -- Automatic Grading of Cortical and PSC Cataracts Using Retroillumination Lens Images -- Registration of Pre-operative CT and Non-contrast-Enhanced C-arm CT: An Application to Trans-Catheter Aortic Valve Implantation (TAVI) -- Automatic Webcam-Based Human Heart Rate Measurements Using Laplacian Eigenmap -- Superpixel Classification Based Optic Disc Segmentation -- Anterior Cruciate Ligament Segmentation from Knee MR Images Using Graph Cuts with Geometric and Probabilistic Shape Constraints -- Robust Mid-Sagittal Plane Extraction in 3-D Ultrasound Fetal Volume for First Trimester Screening -- Automatic Skin Lesion Segmentation Based on Texture Analysis and Supervised Learning -- Multiscale Convolutional Neural Networks for Vision-Based Classification of Cells -- Semantic-Context-Based Augmented Descriptor for Image Feature Matching -- Image Synthesis and Occlusion Removal of Intermediate Views by Stereo Matching -- PEDIVHANDI: Multimodal Indexation and Retrieval System for Lecture Videos -- Digitization of Deformed Documents Using a High-Speed Multi-camera Array -- A Phase-Based Approach for Caption Detection in Videos -- Efficient Clothing Retrieval with Semantic-Preserving Visual Phrases -- VISOR: Towards On-the-Fly Large-Scale Object Category Retrieval -- A Picture Is Worth a Thousand Tags: Automatic Web Based Image Tag Expansion -- Image Retrieval Using Eigen Queries -- Fast and Effective Retrieval of Plant Leaf Shapes -- Complete Generic Camera Calibration and Modeling Using Spline Surfaces -- q-Gaussian Mixture Models Based on Non-extensive Statistics for Image And Video Semantic Indexing -- Oral Session 5: Object Recognition II -- Rapid Uncertainty Computation with Gaussian Processes and Histogram Intersection Kernels -- Histogram of Oriented Normal Vectors for Object Recognition with a Depth Sensor -- Globally Optimal Consensus Set Maximization through Rotation Search -- Graspable Parts Recognition in Man-Made 3D Shapes -- Poster Session 5: Face/Gesture Analysis and Recognition -- Face Recognition after Plastic Surgery: A Comprehensive Study -- Enhancing Expression Recognition in the Wild with Unlabeled Reference Data -- Benchmarking Still-to-Video Face Recognition via Partial and Local Linear Discriminant Analysis on COX-S2V Dataset -- Fusing Magnitude and Phase Features for Robust Face Recognition -- Finding Happiest Moments in a Social Context -- Sparsity Sharing Embedding for Face Verification -- Semantic Pixel Sets Based Local Binary Patterns for Face Recognition -- An Adaptation Framework for Head-Pose Classification in Dynamic Multi-view Scenarios -- Face Parts Localization Using Structured-Output Regression Forests -- Human Face Super-Resolution Based on NSCT -- Digital Paparazzi: Spotting Celebrities in Professional Photo Libraries -- Nighttime Face Recognition at Long Distance: Cross-Distance and Cross-Spectral Matching -- Hand Posture Recognition from Disparity Cost Map -- Qualitative Pose Estimation by Discriminative Deformable Part Models -- Learning Discriminant Face Descriptor for Face Recognition -- Optimal Operator Space Pursuit: A Framework for Video Sequence Data Analysis -- Cross-view Graph Embedding -- Fast Training of Effective Multi-class Boosting Using Coordinate Descent Optimization -- Hierarchical Space Tiling for Scene Modeling.