Upload
others
View
10
Download
0
Embed Size (px)
Citation preview
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications
Tutorial at CVPR 2014 June 23rd, 1:00pm-5:00pm, Columbus, OH
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Introduction
Instructors:
Shih-Fu Chang John Smith Rogerio Feris Liangliang Cao
Columbia University IBM T. J. Watson Research Center
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Introduction
1970s
Early Days of Computer Vision
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Introduction
First Digital Camera (1975)
0.01 Megapixels
23 seconds to record a photo to cassette
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Introduction
Datasets with 5 or 10 images
Large-Scale Experiment: 800 photos (Takeo Kanade Thesis, 1973)
[D. Marr, 1976]
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Introduction
Today
Visual Data is Exploding!
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Introduction
Announcement of Pope Benedict in 2005
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Introduction
Announcement of Pope Francis in 2013
Rapid proliferation of mobile devices equipped with cameras
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Introduction
Billions of cell phones equipped with cameras
~500 billion consumer photos are taken each year world-wide ~500 million photos taken per year in NYC alone
Hundreds of millions of Facebook photo uploads per day
Era of Big Visual Data
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Introduction
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Introduction
Exciting Time for Computer Vision
+ DATA
+ Computational Processing
+ Advances in Computer Vision and Machine Learning
Major opportunities for systems that automatically extract visual semantics from images and videos
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Examples of Practical Application Areas
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Examples of Application Areas
Smart Surveillance “Show me all images of people matching the suspect description from time
X to time Y from all cameras in area Z.”
Visual Semantics: Fine-grained person attributes
Slide credit: Rogerio Feris
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Examples of Application Areas
Medical Imaging
MRI Brain Axial
DX Torso DX Cervical Spine
PET Color DX Appendage
MRI Knee
Visual Semantics: Medical Image Modality and Anatomy
Slide credit: John Smith
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Examples of Application Areas
Astronomy [Cui et al, WACV 2015] http://www.galaxyzoo.org/
Visual Semantics: morphological galaxy attributes
Slide credit: Rogerio Feris
Huge dataset of galaxy images makes manual labeling infeasible
(important to understand star formation, gas fraction, galaxy evolution, …)
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Examples of Application Areas
Nature / Ecology
http://www.youtube.com/watch?v=AUL03ivS8bY
http://www.snapshotserengeti.org/
Understanding how competing species coexist is a fundamental theme in ecology, with important implications for biodiversity, and the sustainability of life on Earth
Snapshot Serengeti
Visual Semantics: species of animals from camera traps
Slide credit: Rogerio Feris
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Examples of Application Areas
Nature / Ecology
Slide credit: Rogerio Feris
Plant Species
[Kumar et al, ECCV 2012]
Bird Species
http://www.vision.caltech.edu/visipedia/
Understanding of migration, conservation, … Used by botanists, educators, …
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Examples of Application Areas
Social Media: Visual Sentiment Analysis
Colorful clouds Misty night
Colorful butterfly Crying Baby
[Borth et al, ACM MM 2013]
Slide credit: Rogerio Feris
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Many more applications …
Google Goggles
Amazon
[Kovashka et al, CVPR 2012]
Slide credit: Rogerio Feris
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Tutorial Overview
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Tutorial Overview
Objectives:
Cover state-of-the-art techniques for learning visual semantics from images and videos
Focus on intuitive, semantic visual representations
Provide tools for scalable learning of semantic models
Cover innovative and practical applications
Provide pointers to related source code and datasets
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Tutorial Overview
Part I: Feature Extraction, Coding, and Pooling (Liangliang)
Brief Introduction to local feature descriptors, coding ,and pooling
Focus on modern representations such as Fisher Vector and Sparse Coding
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Tutorial Overview
Part I: Feature Extraction, Coding, and Pooling (Liangliang)
Connections to feature learning approaches (e.g., deep convolutional neural networks)
Picture credit: Kai Yu
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Tutorial Overview
Part II: Large-Scale Semantic Modeling (John Smith)
Semantic Concept Modeling: Historic Overview
Picture credit: John Smith
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Tutorial Overview
Part II: Large-Scale Semantic Modeling (John Smith)
How to deal with class imbalance? How to scale to millions of semantic unit models?
Picture credit: John Smith
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Tutorial Overview
Part III: Shifting from naming to describing: semantic attribute models (Rogerio Feris)
Scalable learning with Attribute Models / Zero-Shot Learning
[Lampert et al, CVPR 2009]
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Tutorial Overview
Part III: Shifting from naming to describing: semantic attribute models (Rogerio Feris)
Attribute-based Search
Slide credit: Rogerio Feris
Learning Visual Semantics: Models, Massive Computation, and Innovative Applications CVPR 2014
Tutorial Overview
Part IV: High-level Semantic Modeling: Visual Sentiment Analysis (Shih-Fu Chang)
Semantic models for encoding emotions in social media