Guest Editorial: Big Data
SUN Database: Exploring a Large Collection of Scene Categories
Joint Inference in Weakly-Annotated Image Datasets via Dense Correspondence
Large Scale Retrieval and Generation of Image Descriptions
Sparse Output Coding for Scalable Visual Recognition
Do We Need More Training Data?
Schwarps: Locally Projective Image Warps Based on 2D Schwarzian Derivatives
Robust Tracking via Locally Structured Representation
Visualizing Object Detection Features
Hierarchical Adaptive Structural SVM for Domain Adaptation
Linear Time Illumination Invariant Stereo Matching
Pictorial Human Spaces: A Computational Study on the Human Perception of 3D Articulated Poses
Guest Editorial: Video Recognition
A Robust and Efficient Video Representation for Action Recognition
EXMOVES: Mid-level Features for Efficient Action Recognition and Video Analysis
MoFAP: A Multi-level Representation for Action Recognition
LIBSVX: A Supervoxel Library and Benchmark for Early Video Processing
Circulant Temporal Encoding for Video Retrieval and Temporal Alignment
First-Person Activity Recognition: Feature, Temporal Structure, and Prediction
Learning Relevance Restricted Boltzmann Machine for Unstructured Group Activity and Event Understanding
Recognizing Fine-Grained and Composite Activities Using Hand-Centric Features and Script Data