Spotlights and Posters W1.- Kernel Sparse Representation for Image Classification and Face Recognition.- Every Picture Tells a Story: Generating Sentences from Images.- An Eye Fixation Database for Saliency Detection in Images.- Face Image Relighting using Locally Constrained Global Optimization.- Correlation-Based Intrinsic Image Extraction from a Single Image.- ADICT: Accurate Direct and Inverse Color Transformation.- Real-Time Specular Highlight Removal Using Bilateral Filtering.- Learning Artistic Lighting Template from Portrait Photographs.- Photometric Stereo from Maximum Feasible Lambertian Reflections.- Part-Based Feature Synthesis for Human Detection.- Improving the Fisher Kernel for Large-Scale Image Classification.- Max-Margin Dictionary Learning for Multiclass Image Categorization.- Towards Optimal Naive Bayes Nearest Neighbor.- Weakly Supervised Classification of Objects in Images Using Soft Random Forests.- Learning What and How of Contextual Models for Scene Labeling.- Adapting Visual Category Models to New Domains.- Improved Human Parsing with a Full Relational Model.- Multiresolution Models for Object Detection.- Accurate Image Localization Based on Google Maps Street View.- A Minimal Case Solution to the Calibrated Relative Pose Problem for the Case of Two Known Orientation Angles.- Bilinear Factorization via Augmented Lagrange Multipliers.- Piecewise Quadratic Reconstruction of Non-Rigid Surfaces from Monocular Sequences.- Extrinsic Camera Calibration Using Multiple Reflections.- Probabilistic Deformable Surface Tracking from Multiple Videos.- Theory of Optimal View Interpolation with Depth Inaccuracy.- Practical Methods for Convex Multi-view Reconstruction.- Building Rome on a Cloudless Day.- Camera Pose Estimation Using Images of Planar Mirror Reflections.- Element-Wise Factorization for N-View Projective Reconstruction.- Learning Relations among Movie Characters: A Social Network Perspective.- Scene and Object Recognition.- What, Where and HowMany? Combining Object Detectors and CRFs.- Visual Recognition with Humans in the Loop.- Localizing Objects While Learning Their Appearance.- Monocular 3D Scene Modeling and Inference: Understanding Multi-Object Traffic Scenes.- Blocks World Revisited: Image Understanding Using Qualitative Geometry and Mechanics.- Discriminative Learning with Latent Variables for Cluttered Indoor Scene Understanding.- Spotlights and Posters W2.- Visual Tracking Using a Pixelwise Spatiotemporal Oriented Energy Representation.- A Globally Optimal Approach for 3D Elastic Motion Estimation from Stereo Sequences.- Occlusion Boundary Detection Using Pseudo-depth.- Multiple Target Tracking in World Coordinate with Single, Minimally Calibrated Camera.- Joint Estimation of Motion, Structure and Geometry from Stereo Sequences.- Dense, Robust, and Accurate Motion Field Estimation from Stereo Image Sequences in Real-Time.- Estimation of 3D Object Structure, Motion and Rotation Based on 4D Affine Optical Flow Usinga Multi-camera Array.- Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces.- Robust and Fast Collaborative Tracking with Two Stage Sparse Optimization.- Nonlocal Multiscale Hierarchical Decomposition on Graphs.- Adaptive Regularization for Image Segmentation Using Local Image Curvature Cues.- A Static SMC Sampler on Shapes for the Automated Segmentation of Aortic Calcifications.- Fast Dynamic Texture Detection.- Finding Semantic Structures in Image Hierarchies Using Laplacian Graph Energy.- Semantic Segmentation of Urban Scenes Using Dense Depth Maps.- Tensor Sparse Coding for Region Covariances.- Improving Local Descriptors by Embedding Global and Local Spatial Information.- Detecting Faint Curved Edges in Noisy Images.- Spatial Statistics of Visual Keypoints for Texture Recognition.- BRIEF: Binary Robust Independent Elementary Features.- Multi-label Feature Transform for Image Classifications.