Computer Vision -- Accv 2012

Oral Session 1: Object Detection and Learning.- Beyond Dataset Bias: Multi-task Unaligned Shared Knowledge Transfer.- Cross-Database Transfer Learning via Learnable and Discriminant Error-Correcting Output Codes.- Human Reidentification with Transferred Metric Learning.- Poster Session 1: Object Detection, Learning and Matching.- Tell Me What You Like and I'll Tell You What You Are: Discriminating Visual Preferences on Flickr Data.- Local Context Priors for Object Proposal Generation.- Arbitrary-Shape Object Localization Using Adaptive Image Grids.- Disambiguation in Unknown Object Detection by Integrating Image and Speech Recognition Confidences.- Class-Specific Weighted Dominant Orientation Templates for Object Detection.- Salient Object Detection via Color Contrast and Color Distribution.- Data Decomposition and Spatial Mixture Modeling for Part Based Model.- Appearance Sharing for Collective Human Pose Estimation.- Max-Margin Regularization for Reducing Accidentalness in Chamfer Matching.- Coupling-and-Decoupling: A Hierarchical Model for Occlusion-Free Car Detection.- The Pooled NBNN Kernel: Beyond Image-to-Class and Image-to-Image.- Local Hypersphere Coding Based on Edges between Visual Words.- Spatially Local Coding for Object Recognition.- Semantic Segmentation with Millions of Features: Integrating Multiple Cues in a Combined Random Forest Approach.- Semi-Supervised Learning on a Budget: Scaling Up to Large Datasets.- One-Class Multiple Instance Learning via Robust PCA for Common Object Discovery.- Online Semi-Supervised Discriminative Dictionary Learning for Sparse Representation.- Efficient Discriminative Learning of Class Hierarchy for Many Class Prediction.- Oral Session 2: Object Recognition I.- Grouping Active Contour Fragments for Object Recognition.- Detecting Partially Occluded Objects with an Implicit Shape Model Random Field.- Relative Forest for Attribute Prediction.- Discriminative Dictionary Learning with Pairwise Constraints.- Poster Session 2: Feature, Representation, and Recognition.- Adaptive Unsupervised Multi-view Feature Selection for Visual Concept Recognition.- Iris Recognition Using Consistent Corner Optical Flow.- Face Recognition in Videos - A Graph Based Modified Kernel Discriminant Analysis.- Learning Hierarchical Bag of Words Using Naive Bayes Clustering.- Efficient Human Parsing Based on Sketch Representation.- Exclusive Visual Descriptor Quantization.- Underwater Live Fish Recognition Using a Balance-Guaranteed Optimized Tree.- Local 3D Symmetry for Visual Saliency in 2.5D Point Clouds.- Exploiting Features - Locally Interleaved Sequential Alignment for Object Detection.- Efficient and Scalable 4th-Order Match Propagation.- Hierarchical Object Representations for Visual Recognition via Weakly Supervised Learning.- Invariant Surface-Based Shape Descriptor for Dynamic Surface Encoding.- Linear Discriminant Analysis with Maximum Correntropy Criterion.- AfNet: The Affordance Network.- A Directed Graphical Model for Linear Barcode Scanning from Blurred Images.- A Probabilistic 3D Model Retrieval System Using Sphere Image.- Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes.- Boosting with Side Information.- Generalized Mutual Subspace Based Methods for Image Set Classification.- Oral Session 3: Segmentation and Grouping Simultaneous Monocular 2D Segmentation, 3D Pose Recovery and 3D Reconstruction.- Joint Kernel Learning for Supervised Image Segmentation.- Application of Heterogenous Motion Models towards Structure Recovery from Motion.- Poster Session 3: Segmentation, Grouping, and Classification Locality-Constrained Active Appearance Model.- Modeling Hidden Topics with Dual Local Consistency for Image Analysis.- Design of Non-Linear Discriminative Dictionaries for Image Classification.- Efficient Background Subtraction under Abrupt Illumination Variations.- Naive Bayes Image Classification: Beyond Nearest Neighbors.- Contextual Pooling in Image Classification.- Spatial Graph for Image Classification.- Knowledge Leverage from Contours to Bounding Boxes: A Concise Approach to Annotation.- Efficient Pixel-Grouping Based on Dempster's Theory of Evidence for Image Segmentation.- Video Segmentation with Superpixels.- A Noise Tolerant Watershed Transformation with Viscous Force for Seeded Image Segmentation.- Active Learning for Interactive Segmentation with Expected Confidence Change.- Cross Anisotropic Cost Volume Filtering for Segmentation.