Table of Contents [Back inside cover] [Front inside cover] [Back cover] AD-VAT+: An Asymmetric Dueling Mechanism for Learning and Understanding Visual Active Tracking Cascade R-CNN: High Quality Object Detection and Instance Segmentation DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors Dynamical Hyperparameter Optimization via Deep Reinforcement Learning in Tracking Exploring Discriminative Word-Level Domain Contexts for Multi-Domain Neural Machine Translation Generalized Separable Nonnegative Matrix Factorization GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications On Symbiosis of Attribute Prediction and Semantic Segmentation Ordinal Multi-Task Part Segmentation With Recurrent Prior Generation Person Re-Identification With Deep Kronecker-Product Matching and Group-Shuffling Random Walk Quicker ADC : Unlocking the Hidden Potential of Product Quantization With SIMD Scalar Quantization as Sparse Least Square Optimization Structure From Motion on XSlit Cameras Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene Tensor Low-Rank Representation for Data Recovery and Clustering Text-Guided Neural Network Training for Image Recognition in Natural Scenes and Medicine Using Statistical Measures and Machine Learning for Graph Reduction to Solve Maximum Weight Clique Problems Vision Models for Wide Color Gamut Imaging in Cinema What is a Tabby? Interpretable Model Decisions by Learning Attribute-Based Classification Criteria Learning From Large-Scale Noisy Web Data With Ubiquitous Reweighting for Image Classification Table of Contents. Cover. State of the Journal Editorial. Adversarial Margin Maximization Networks. Affine Invariants of Vector Fields. Appearance and Pose-Conditioned Human Image Generation Using Deformable GANs. Assessing Transferability From Simulation to Reality for Reinforcement Learning. Bayesian Joint Matrix Decomposition for Data Integration with Heterogeneous Noise. Bilinear Image Translation for Temporal Analysis of Photo Collections. Corner Detection Using Second-Order Generalized Gaussian Directional Derivative Representations. Deep Depth from Uncalibrated Small Motion Clip. Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification. Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation. Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets. Ideals of the Multiview Variety. InLoc: Indoor Visual Localization with Dense Matching and View Synthesis. Interpreting the Rhetoric of Visual Advertisements. Joint Embedding of Graphs. Large Scale Shadow Annotation and Detection Using Lazy Annotation and Stacked CNNs. Orthogonal Deep Neural Networks. Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency. Sinusoidal Sampling Enhanced Compressive Camera for High Speed Imaging. SpaRTA Tracking Across Occlusions via Partitioning of 3D Clouds of Points. Visual Semantic Information Pursuit: A Survey.