Computer Vision -- ACCV 2014

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.

Multi-view Geometry Compression.- Camera Calibration Based on the Common Self-polar Triangle of Sphere Images.- Multi-scale Tetrahedral Fusion of a Similarity Reconstruction and Noisy Positional Measurements.- DEPT: Depth Estimation by Parameter Transfer for Single Still Images.- Object Ranking on Deformable Part Models with Bagged Lambda MART.- Representation Learning with Smooth Auto encoder.- Single Image Smoke Detection.- Adaptive Sparse Coding for Painting Style Analysis.- Efficient Image Detail Mining.- Accuracy and Specificity Trade-off in k-nearest Neighbors Classification.- Multi-view Point Cloud Registration Using Affine Shape Distributions.- Part Detector Discovery in Deep Convolutional Neural Networks.- Performance Evaluation of 3D Local Feature Descriptors.- Scene Text Detection Based on Robust Stroke Width Transform and Deep Belief Network.- Cross-Modal Face Matching: Beyond Viewed Sketches.- 3D Aware Correction and Completion of Depth Maps in Piecewise Planar Scenes.- Regularity Guaranteed Human Pose Correction.- Accelerated Kmeans Clustering Using Binary Random Projection.- Divide and Conquer: Efficient Large-Scale Structure from Motion Using Graph Partitioning.- A Homography Formulation to the 3pt Plus a Common Direction Relative Pose Problem.- MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation.- Accelerating Cost Volume Filtering Using Salient Subvolumes and Robust Occlusion Handling.- 3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network.- Plant Leaf Identification via a Growing Convolution Neural Network with Progressive Sample Learning.- Understanding Convolutional Neural Networks in Terms of Category-Level Attributes.- Robust Scene Classification with Cross-Level LLC Coding on CNN Features.- A Graphical Model for Rapid Obstacle Image-Map Estimation from Unmanned Surface Vehicles.- On the Performance of Pose-Based RGB-D Visual NavigationSystems.- Elastic Shape Analysis of Boundaries of Planar Objects with Multiple Components and Arbitrary Topologies.- A Minimal Solution to Relative Pose with Unknown Focal Length and Radial Distortion.- Simultaneous Entire Shape Registration of Multiple Depth Images Using Depth Difference and Shape Silhouette.- Joint Camera Pose Estimation and 3D Human Pose Estimation in a Multi-camera Setup.- Singly-Bordered Block-Diagonal Form for Minimal Problem Solvers.- Stereo Fusion Using a Refractive Medium on a Binocular Base.- Saliency Detection via Nonlocal L0 Minimization.- N4-Fields: Neural Network Nearest Neighbor Fields for Image Transforms.- Super-Resolution Using Sub-Band Self-Similarity.- Raindrop Detection and Removal from Long Range Trajectories.- Interest Points via Maximal Self-Dissimilarities.- Improving Local Features by Dithering-Based Image Sampling.- Sparse Kernel Learning for Image Set Classification.- Automatic Feature Learning to Grade Nuclear Cataracts Based on Deep Learning.- Texture Classification Using Dense Micro-block Difference (DMD).- Nuclear-L1 Norm Joint Regression for Face Reconstruction and Recognition.- Segmentation of X-ray Images by 3D-2D Registration Based on Multibody Physics.- View-Adaptive Metric Learning for Multi-view Person Re-identification.