Reading List

Visual and Multi-Media Data

Tiny Images
Flickr. Who is Looking?

Computational Photography

Scene Completion Using Millions of Photographs
Photo Clip Art
Interactive Digital Photomontage
Recognising Panoramas
Seam Carving for Content-Aware Image Resizing
Creating and Exploring a Large Photorealistic Virtual Space

Image Retrieval

Image Retrieval: Ideas, Influences, and Trends of the New Age
PageRank for Product Image Search
Learning Object Categories from Google's Image Search
Towards scalable dataset construction: An active learning approach
SIMPLIcity: Semantics-sensitive Integrated Matching for Picture LIbraries
Small Codes and Large Image Databases for Recognition
Scalable recognition with a vocabulary tree

Photo Quality Estimation

Photo Quality Assessment
Studying Aesthetics in Photographic Images Using a Computational Approach
Computing Iconic Summaries for General Visual Concepts

Combining Words & Pictures

Object Recognition as Machine Translation: Learning a lexicon for a fixed image vocabulary
Clustering Art
Finding Visual Concepts by Web Image Mining
Names & Faces in the News
Animals on the Web


Photo Tourism
Photo Synth
How Flickr Helps us Make Sense of the World: Context and Content in Community-Contributed Media Collections
Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs
Photo Pop-Up
IM2GPS: estimating geographic information from a single image

Objects & People

Face Swapping: Automatically Replacing Faces in Photographs
Data-Driven Enhancement of Facial Attractiveness
Video Google
Finding people in repeated shots of the same scene
Learning Realistic Human Actions from Movies

The Role of Social Networks & Human Interaction

Autotagging facebook: Social Network Context Improves Photo Annotation
Human labeling - ESP game, Peekaboom, Peekaboom: A Game for Locating Objects in Images
Utility data annotation with Amazon Mechanical Turk
Introduction to a large scale general purpose groundtruth dataset: methodology, annotation tool, and benchmarks
Label Me