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

Front Matter....Pages I-XX
Front Matter....Pages 1-1
Deep Representations to Model User ‘Likes’....Pages 3-18
Submodular Reranking with Multiple Feature Modalities for Image Retrieval....Pages 19-34
Accurate Scene Text Recognition Based on Recurrent Neural Network....Pages 35-48
Massive City-Scale Surface Condition Analysis Using Ground and Aerial Imagery....Pages 49-64
Can Visual Recognition Benefit from Auxiliary Information in Training?....Pages 65-80
Low Rank Representation on Grassmann Manifolds....Pages 81-96
Front Matter....Pages 97-97
Learning Detectors Quickly with Stationary Statistics....Pages 99-114
Age Estimation Based on Complexity-Aware Features....Pages 115-128
Efficient On-the-fly Category Retrieval Using ConvNets and GPUs....Pages 129-145
A Latent Clothing Attribute Approach for Human Pose Estimation....Pages 146-161
NOKMeans: Non-Orthogonal K-means Hashing....Pages 162-177
Visual Vocabulary with a Semantic Twist....Pages 178-195
Context Based Re-ranking for Object Retrieval....Pages 196-210
Adaptive Structural Model for Video Based Pedestrian Detection....Pages 211-226
Fusion of Auxiliary Imaging Information for Robust, Scalable and Fast 3D Reconstruction....Pages 227-242
What Visual Attributes Characterize an Object Class?....Pages 243-259
Accurate Object Detection with Location Relaxation and Regionlets Re-localization....Pages 260-275
Unsupervised Feature Learning for RGB-D Image Classification....Pages 276-289
Non-maximum Suppression for Object Detection by Passing Messages Between Windows....Pages 290-306
Stable Radial Distortion Calibration by Polynomial Matrix Inequalities Programming....Pages 307-321
Front Matter....Pages 97-97
Pedestrian Verification for Multi-Camera Detection....Pages 322-334
Color Photometric Stereo Using a Rainbow Light for Non-Lambertian Multicolored Surfaces....Pages 335-350
Predicting the Location of “interactees” in Novel Human-Object Interactions....Pages 351-367
Robust Stereo Matching Using Probabilistic Laplacian Surface Propagation....Pages 368-383
Imposing Differential Constraints on Radial Distortion Correction....Pages 384-398
Automatic Shoeprint Retrieval Algorithm for Real Crime Scenes....Pages 399-413
Lane Detection in Unstructured Environments for Autonomous Navigation Systems....Pages 414-429
Multiple Stage Residual Model for Accurate Image Classification....Pages 430-445
Hybrid-Indexing Multi-type Features for Large-Scale Image Search....Pages 446-460
Look Closely: Learning Exemplar Patches for Recognizing Textiles from Product Images....Pages 461-476
Action Recognition from a Single Web Image Based on an Ensemble of Pose Experts....Pages 477-493
Scene Text Recognition and Retrieval for Large Lexicons....Pages 494-508
Planar Structures from Line Correspondences in a Manhattan World....Pages 509-524
LBP with Six Intersection Points: Reducing Redundant Information in LBP-TOP for Micro-expression Recognition....Pages 525-537
Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos....Pages 538-552
Robust Edge Aware Descriptor for Image Matching....Pages 553-568
Robust Binary Feature Using the Intensity Order....Pages 569-584
Minimal Solution for Computing Pairs of Lines in Non-central Cameras....Pages 585-597
Asymmetric Feature Representation for Object Recognition in Client Server System....Pages 598-612
Leveraging High Level Visual Information for Matching Images and Captions....Pages 613-627
Front Matter....Pages 97-97
Efficient Feature Coding Based on Auto-encoder Network for Image Classification....Pages 628-642
Learning a Representative and Discriminative Part Model with Deep Convolutional Features for Scene Recognition....Pages 643-658
Image Representation Learning by Deep Appearance and Spatial Coding....Pages 659-672
On the Exploration of Joint Attribute Learning for Person Re-identification....Pages 673-688
Complementary Geometric and Optical Information for Match-Propagation-Based 3D Reconstruction....Pages 689-703
Exploring Image Specific Structured Loss for Image Annotation with Incomplete Labelling....Pages 704-719
Back Matter....Pages 721-727