Computer Vision – ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part V

Front Matter....Pages I-XIII
Front Matter....Pages 1-1
Divide and Conquer: Efficient Density-Based Tracking of 3D Sensors in Manhattan Worlds....Pages 3-19
Visual Saliency Detection for RGB-D Images with Generative Model....Pages 20-35
A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method....Pages 36-51
Unifying Algebraic Solvers for Scaled Euclidean Registration from Point, Line and Plane Constraints....Pages 52-66
Generalized Fusion Moves for Continuous Label Optimization....Pages 67-81
Front Matter....Pages 83-83
Learning to Describe E-Commerce Images from Noisy Online Data....Pages 85-100
phi-LSTM: A Phrase-Based Hierarchical LSTM Model for Image Captioning....Pages 101-117
Deep Relative Attributes....Pages 118-133
Fast Fashion Guided Clothing Image Retrieval: Delving Deeper into What Feature Makes Fashion....Pages 134-149
Using Gaussian Processes to Improve Zero-Shot Learning with Relative Attributes....Pages 150-164
MARVEL: A Large-Scale Image Dataset for Maritime Vessels....Pages 165-180
‘Part’ly First Among Equals: Semantic Part-Based Benchmarking for State-of-the-Art Object Recognition Systems....Pages 181-197
End-to-End Training of Object Class Detectors for Mean Average Precision....Pages 198-213
R-CNN for Small Object Detection....Pages 214-230
Image Set Classification via Template Triplets and Context-Aware Similarity Embedding....Pages 231-247
Object-Centric Representation Learning from Unlabeled Videos....Pages 248-263
Visual Concept Recognition and Localization via Iterative Introspection....Pages 264-279
Aggregating Local Context for Accurate Scene Text Detection....Pages 280-296
Bilinear Discriminant Analysis Hashing: A Supervised Hashing Approach for High-Dimensional Data....Pages 297-310
Signature of Geometric Centroids for 3D Local Shape Description and Partial Shape Matching....Pages 311-326
Front Matter....Pages 327-327
Unsupervised Crowd Counting....Pages 329-345
Long-Term Activity Forecasting Using First-Person Vision....Pages 346-360
Video Summarization Using Deep Semantic Features....Pages 361-377
Towards Segmenting Consumer Stereo Videos: Benchmark, Baselines and Ensembles....Pages 378-395
No-Reference Video Shakiness Quality Assessment....Pages 396-411
Learning to Extract Motion from Videos in Convolutional Neural Networks....Pages 412-428
Back Matter....Pages 429-434