Cover Table of Contents Table of Contents. Cover. Guest Editors’ Introduction to the Special Section on Compact and Efficient Feature Representation and Learning in Computer Vision. Runtime Network Routing for Efficient Image Classification. Denoising Prior Driven Deep Neural Network for Image Restoration. Two-Stream Region Convolutional 3D Network for Temporal Activity Detection. Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning. Side Information for Face Completion: A Robust PCA Approach. Robust Kronecker Component Analysis. Min-Entropy Latent Model for Weakly Supervised Object Detection. Late Fusion Incomplete Multi-View Clustering. Hashing with Mutual Information. Label Consistent Matrix Factorization Hashing for Large-Scale Cross-Modal Similarity Search. Cover Table of Contents Cover. Table of Contents Cover Back Cover [Table of Contents] Anticipating Where People will Look Using Adversarial Networks A Region-Based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking Calibrating Classification Probabilities with Shape-Restricted Polynomial Regression EuroCity Persons: A Novel Benchmark for Person Detection in Traffic Scenes Exploiting Unlabeled Data in CNNs by Self-Supervised Learning to Rank Focal Visual-Text Attention for Memex Question Answering Richer Convolutional Features for Edge Detection View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition Visibility Constrained Generative Model for Depth-Based 3D Facial Pose Tracking Advances in Variational Inference Social Anchor-Unit Graph Regularized Tensor Completion for Large-Scale Image Retagging Table of Contents. Cover. Information for authors. A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping. Content Aware Image Pre-Compensation. DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation. End-to-End Policy Learning for Active Visual Categorization. Error Backprojection Algorithms for Non-Line-of-Sight Imaging. Feedback Convolutional Neural Network for Visual Localization and Segmentation. Large Scale Image Segmentation with Structured Loss Based Deep Learning for Connectome Reconstruction. Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition. Cover Table of Contents A Fast Frequent Directions Algorithm for Low Rank Approximation CNN-Based Real-Time Dense Face Reconstruction with Inverse-Rendered Photo-Realistic Face Images Composite Quantization Dynamic Clustering Algorithms via Small-Variance Analysis of Markov Chain Mixture Models. Egocentric Meets Top-View