Computer Vision -- ACCV 2014 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised Selected Papers, Part I

The five-volume set LNCS 9003--9007 constitutes the thoroughly refereed post-conference proceedings of the 12th Asian Conference on Computer Vision, ACCV 2014, held in Singapore, Singapore, in November 2014.

The total of 227 contributions presented in these volumes was carefully reviewed and selected from 814 submissions. The papers are organized in topical sections on recognition; 3D vision; low-level vision and features; segmentation; face and gesture, tracking;  stereo, physics, video and events; and poster sessions 1-3.

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 for Recognizing 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.