Computer Vision -- ACCV 2014

Deep Representations to Model User 'Likes'.- Submodular Reranking with Multiple Feature Modalities for Image Retrieval.- Accurate Scene Text Recognition Based on Recurrent Neural Network.- Massive City-Scale Surface Condition Analysis Using Ground and Aerial Imagery.- Can Visual Recognition Benefit from Auxiliary Information in Training.- Low Rank Representation on Grassmann Manifolds.- Learning Detectors Quickly with Stationary Statistics.- Age Estimation Based on Complexity-Aware Features.- Efficient On-the-fly Category Retrieval Using ConvNets and GPUs.- A Latent Clothing Attribute Approach for Human Pose Estimation.- NOKMeans: Non-Orthogonal K-means Hashing.- Visual Vocabulary with a Semantic Twist.- Context Based Re-ranking for Object Retrieval.- Adaptive Structural Model for Video Based Pedestrian Detection.- Fusion of Auxiliary Imaging Information for Robust, Scalable and Fast 3D Reconstruction.- What Visual Attributes Characterize an Object Class.- Accurate Object Detection with Location Relaxation and Regionlets Re-localization.- Unsupervised Feature Learning for RGB-D Image Classification.- Non-maximum Suppression for Object Detection by Passing Messages Between Windows.- Stable Radial Distortion Calibration by Polynomial Matrix Inequalities Programming.- Pedestrian Verification for Multi-Camera Detection.- Color Photometric Stereo Using a Rainbow Light for Non-Lambertian Multicolored Surfaces.- Predicting the Location of "interactees" in Novel Human-Object Interactions.- Robust Stereo Matching Using Probabilistic Laplacian Surface Propagation.- Imposing Differential Constraints on Radial Distortion Correction.- Automatic Shoeprint Retrieval Algorithm for Real Crime Scenes.- Unstructured Environments for Autonomous Navigation Systems.- Multiple Stage Residual Model for Accurate Image Classification.- Hybrid-Indexing Multi-type Features for Large-Scale Image Search.- Look Closely: Learning Exemplar Patches forRecognizing Textiles from Product Images.- Action Recognition from a Single Web Image Based on an Ensemble of Pose Experts.- Scene Text Recognition and Retrieval for Large Lexicons.- Planar Structures from Line Correspondences in a Manhattan World.- LBP with Six Intersection Points: Reducing Redundant Information in LBP-TOP for Micro-expression Recognition.- Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos.- Robust Edge Aware Descriptor for Image Matching.- Robust Binary Feature Using the Intensity Order.- Minimal Solution for Computing Pairs of Lines in Non-central Cameras.- Asymmetric Feature Representation for Object Recognition in Client Server System.- Leveraging High Level Visual Information for Matching Images and Captions.- Efficient Feature Coding Based on Auto-encoder Network for Image Classification.- Learning a Representative and Discriminative Part Model with Deep Convolutional Features for Scene Recognition.- Image Representation Learning by Deep Appearance and Spatial Coding.- On the Exploration of Joint Attribute Learning for Person Re-identification.- Complementary Geometric and Optical Information for Match-Propagation-Based 3D Reconstruction.- Exploring Image Specific Structured Loss for Image Annotation with Incomplete Labelling.