What makes Big Visual Data hard?



Similar documents
Pixels Description of scene contents. Rob Fergus (NYU) Antonio Torralba (MIT) Yair Weiss (Hebrew U.) William T. Freeman (MIT) Banksy, 2006

Clustering Big Data. Anil K. Jain. (with Radha Chitta and Rong Jin) Department of Computer Science Michigan State University November 29, 2012

Introduction. Selim Aksoy. Bilkent University

Character Image Patterns as Big Data

INTRO TO BIG DATA. Djoerd Hiemstra. Big Data in Clinical Medicinel, 30 June 2014

An Introduction to Data Mining. Big Data World. Related Fields and Disciplines. What is Data Mining? 2/12/2015

Machine Learning and Data Mining. Fundamentals, robotics, recognition

MA2823: Foundations of Machine Learning

CSC384 Intro to Artificial Intelligence

Fast Matching of Binary Features

A Genetic Algorithm-Evolved 3D Point Cloud Descriptor

CLUSTER ANALYSIS WITH R

Object Recognition. Selim Aksoy. Bilkent University

TIETS34 Seminar: Data Mining on Biometric identification

Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 269 Class Project Report

Unsupervised Discovery of Mid-Level Discriminative Patches

A Systemic Artificial Intelligence (AI) Approach to Difficult Text Analytics Tasks

How To Use A Near Neighbor To A Detector

Applications of Deep Learning to the GEOINT mission. June 2015

The Delicate Art of Flower Classification

Master of Science in Computer Science

MLg. Big Data and Its Implication to Research Methodologies and Funding. Cornelia Caragea TARDIS November 7, Machine Learning Group

What Makes a Great Picture?

Digital Collections as Big Data. Leslie Johnston, Library of Congress Digital Preservation 2012

Course Overview. CSCI 480 Computer Graphics Lecture 1. Administrative Issues Modeling Animation Rendering OpenGL Programming [Angel Ch.

The Data Mining Process

Graduate Co-op Students Information Manual. Department of Computer Science. Faculty of Science. University of Regina

Big Data Hope or Hype?

Information Management course

An interdisciplinary model for analytics education

Recognizing Cats and Dogs with Shape and Appearance based Models. Group Member: Chu Wang, Landu Jiang

Example application (1) Telecommunication. Lecture 1: Data Mining Overview and Process. Example application (2) Health

The University of Jordan

CAP4773/CIS6930 Projects in Data Science, Fall 2014 [Review] Overview of Data Science

Optimizing content delivery through machine learning. James Schneider Anton DeFrancesco

Super-resolution from Internet-scale Scene Matching

Introduction to Data Mining

Software Development Training Camp 1 (0-3) Prerequisite : Program development skill enhancement camp, at least 48 person-hours.

Discovering objects and their location in images

USTC Course for students entering Clemson F2013 Equivalent Clemson Course Counts for Clemson MS Core Area. CPSC 822 Case Study in Operating Systems

Discovering objects and their location in images

Machine Learning, Data Mining, and Knowledge Discovery: An Introduction

Statistics for BIG data

Debugging the Hype about Big Data and Business Service Metrics

System Behavior Analysis by Machine Learning

3D Model based Object Class Detection in An Arbitrary View

Professional Organization Checklist for the Computer Science Curriculum Updates. Association of Computing Machinery Computing Curricula 2008

Data, Measurements, Features

Data Mining and Knowledge Discovery in Databases (KDD) State of the Art. Prof. Dr. T. Nouri Computer Science Department FHNW Switzerland

Canonical Image Selection for Large-scale Flickr Photos using Hadoop

Computational Science and Informatics (Data Science) Programs at GMU

International Journal of Computer Science Trends and Technology (IJCST) Volume 2 Issue 3, May-Jun 2014

An Energy-Based Vehicle Tracking System using Principal Component Analysis and Unsupervised ART Network

Introduction to Data Mining and Machine Learning Techniques. Iza Moise, Evangelos Pournaras, Dirk Helbing

In this presentation, you will be introduced to data mining and the relationship with meaningful use.

Probabilistic Latent Semantic Analysis (plsa)

Behavior Analysis in Crowded Environments. XiaogangWang Department of Electronic Engineering The Chinese University of Hong Kong June 25, 2011

Foundations of Artificial Intelligence. Introduction to Data Mining

Big Graph Processing: Some Background

A SURVEY ON WEB MINING TOOLS

Local features and matching. Image classification & object localization

Computer-Based Text- and Data Analysis Technologies and Applications. Mark Cieliebak

Master s Program in Information Systems

Pitfalls and Best Practices in Role Engineering

Computational Cognitive Science. Lecture 1: Introduction

MACHINE LEARNING BASICS WITH R

Cees Snoek. Machine. Humans. Multimedia Archives. Euvision Technologies The Netherlands. University of Amsterdam The Netherlands. Tree.

Towards better understanding Cybersecurity: or are "Cyberspace" and "Cyber Space" the same?

PSG College of Technology, Coimbatore Department of Computer & Information Sciences BSc (CT) G1 & G2 Sixth Semester PROJECT DETAILS.

An Overview of Knowledge Discovery Database and Data mining Techniques

The Power of Social Data: Transforming Big Data into Decisions. Andreas Weigend

Doctor of Philosophy in Computer Science

Semantic Recognition: Object Detection and Scene Segmentation

Mining Big Data. Pang-Ning Tan. Associate Professor Dept of Computer Science & Engineering Michigan State University

Web 3.0 image search: a World First

Industrial Challenges for Content-Based Image Retrieval

Machine Learning and Statistics: What s the Connection?

A Review of Data Mining Techniques

LONG BEACH CITY COLLEGE MEMORANDUM

Network Big Data: Facing and Tackling the Complexities Xiaolong Jin

Recognition. Sanja Fidler CSC420: Intro to Image Understanding 1 / 28

Healthcare data analytics. Da-Wei Wang Institute of Information Science

COMP9321 Web Application Engineering

Transcription:

What makes Big Visual Data hard? Quint Buchholz Alexei (Alyosha) Efros Carnegie Mellon University

My Goals 1. To make you fall in love with Big Visual Data She is a fickle, coy mistress but holds the key to achieving real visual understanding 2. To ask for help in tackling this Big Interdisciplinary Problem

Driven by Visual Data Texture Synthesis Dating Historical Images Seeing Through Water Unsupervised Object Discovery Action Recognition Illumination Estimation Inferring 3D from 2D Geo-location

Texture: microcosm of Big Data radishes rocks yogurt

Texture Synthesis

Classical Texture Synthesis Synthesis Novel texture Parametric Texture Model This is hard! Analysis Sample texture

Throwing away too much too soon? input texture synthesized texture

Non-parametric Approach Synthesis Novel texture Analysis Sample texture

[Efros & Leung, 99, Efros & Freeman 01] p non-parametric sampling Input image

Texture Growing

Portilla & Simoncelli Xu, Guo & Shum input image Wei & Levoy Our algorithm

Two Kinds of Things in the World Navier-Stokes Equation + weather + location +

Lots of data available

Unreasonable Effectiveness of Data Parts of our world can be explained by elegant mathematics: physics, chemistry, astronomy, etc. But much cannot: [Halevy, Norvig, Pereira 2009] psychology, genetics, economics, visual understanding? Enter: The Magic of Data Great advances in several fields: e.g. speech recognition, machine translation, Google

The A.I. for the postmodern world

The Good News Really stupid algorithms + Lots of Data = Unreasonable Effectiveness

140 billion images 6 billion added monthly 6 billion images 1 billion images served daily 72 hours uploaded every minute 3.5 trillion photographs 90% of net traffic will be visual!

Physics Dating Drugs Scientific Experiments Psychology Social Graphs Collaborative Filters Genetics Web Text Medical Data Data Mining Search Disease Tracking Policy Economic Data Business Intelligence Business Data Marketing Visual Data?

Bad News Visual Data is difficult to handle text: clean, segmented, compact, 1D, indexable Visual data: Noisy, unsegmented, high entropy, 2D/3D

Computing distances is hard CLIME - CRIME = hamming distance of 1 letter y y x - x = Euclidian distance of 5 units - = Grayvalue distance of 50 values - =?

How similar are two pictures?? =

Medici Fountain, Paris

INDEXING VIA VISUAL WORDS

VISUAL WORD MATCHING [SIFT: Lowe, 2004]

letter VISUAL WORD MATCHING [SIFT: Lowe, 2004]

Medici Fountain, Paris (winter)

Visual Garbage Heap It irritated him that the dog of 3:14 in the afternoon, seen in profile, should be indicated by the same noun as the dog of 3:15, seen frontally My memory, sir, is like a garbage heap. -- from Funes the Memorious Jorge Luis Borges Organizing the Garbage Heap : Finding visual correspondences across data Mining Visual Data Connecting visual data to enable understanding (Visual Memex)

Improving Visual Correspondence

Improving Visual Correspondence

Lots of Tiny Images 80 million tiny images: a large dataset for nonparametric object and scene recognition Antonio Torralba, Rob Fergus and William T. Freeman. PAMI 2008.

Lots Of Images A. Torralba, R. Fergus, W.T.Freeman. PAMI 2008

Lots Of Images A. Torralba, R. Fergus, W.T.Freeman. PAMI 2008

Lots Of Images

Automatic Colorization Grayscale input High resolution Colorization of input using average A. Torralba, R. Fergus, W.T.Freeman. 2008

[Hays & Efros, SIGGRAPH 07]

Scene Descriptor

Scene Descriptor Scene Gist Descriptor (Oliva and Torralba 2001)

2 Million Flickr Images

200 scene matches

Improving Visual Correspondence

Improving Visual Correspondence

Visual Data has a Long Tail The rare is common!

LEARNING BETTER VISUAL CORRESPONDENCES ABHINAV SRIVASTAVA, TOMASZ MALISIEWICZ, ABHINAV GUPTA, ALEXEI EFROS SIGGRAPH ASIA 11

Input Query Top Matches

Input Query Top Matches

Input Query Top Matches

IMPORTANT PARTS? Input Query Important Parts

Input Query Top Matches

72

Way more efficient approaches: [Ramanan et al 2012, Durand et al 2012]

SEARCH USING PAINTINGS GIST Input Painting Bag-of-Words Tiny Images Our Approach HOG

SEARCH USING PAINTINGS Input Painting Top Matches

SEARCH USING PAINTINGS Input Painting Top Matches

SEARCH USING SKETCHES Tiny Images Input Sketch GIST Bag-of-Words Our Approach 81

SEARCH USING SKETCHES

APPLICATIONS

RE-PHOTOGRAPHY Computational Re-photography (Bae et al., 2010) Historical Image of Boston Station Re-photographed Image

RE-PHOTOGRAPHY Computational Re-photography (Bae et al., 2010) Historical Image of Boston Station Re-photographed Image Then & Now View

INTERNET RE-PHOTOGRAPHY Computational Re-photography (Bae et al., 2010) Historical Image of Boston Station Re-photographed Image Then & Now View Our Approach Search 10,000 Flickr Images of Boston Historical Image of Boston Station Top Match

INTERNET RE-PHOTOGRAPHY Computational Re-photography (Bae et al., 2010) Historical Image of Boston Station Re-photographed Image Our Approach Then & Now View Historical Image of Boston Station Top Match From 10,000 Flickr Images Then & Now View

WHERE WAS THE PAINTER STANDING? Input Painting

PAINTING2GPS Input Painting Retrieval set 10,000 Geo-tagged Flickr Images 100 top matches used to estimation

PAINTING2GPS Input Painting Estimated Geo-location Estimated using 100 top matches

VISUAL SCENE EXPLORATION

VISUAL SCENE EXPLORATION 96

Query image FINDING SIMILAR IMAGES

PAIRWISE SIMILARITY MATRIX...........

TRAVERSING THE GRAPH