+ All Categories
Home > Education > Iccv2009 recognition and learning object categories p2 c03 - objects and annotations

Iccv2009 recognition and learning object categories p2 c03 - objects and annotations

Date post: 10-May-2015
Category:
Upload: zukun
View: 402 times
Download: 1 times
Share this document with a friend
Popular Tags:
43
Pictures and Words
Transcript
Page 1: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Pictures and Words

Page 2: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Vision and language in human brain

FFA

LOCV1

PPABrocaArea

WernickeArea

Language Vision

Page 3: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Vision and language in human brain

figure modified from: http://www.colorado.edu/intphys/Class/IPHY3730

Page 4: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Vision and language in human brain

figure modified from: http://www.colorado.edu/intphys/Class/IPHY3730

(Translation: “This is not a pipe.”)

?

Page 5: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations
Page 6: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations
Page 7: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Fei-Fei, Iyer, Koch, Perona, JoV, 2007

What can you see in a glance of a scene?

Page 8: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

I think I saw two people on a field. (Subject: RW)

Outdoor scene. There were some kind of animals, maybe dogs or horses, in the middle of the picture. It looked like they were running in the middle of a grassy field. (Subject: IV)

two people, whose profile was toward me. looked like they were on a field of some sort and engaged in some sort of sport (their attire suggested soccer, but it looked like there was too much contact for that). (Subject: AI)

Some kind of game or fight. Two groups of two men? The foregound pair looked like one was getting a fist in the face. Outdoors seemed like because i have an impression of grass and maybe lines on the grass? That would be why I think perhaps a game, rough game though, more like rugby than football because they pairs weren't in pads and helmets, though I did get the impression of similar clothing. maybe some trees? in the background. (Subject: SM)

PT = 500ms

PT = 27ms

PT = 40ms

PT = 67ms

This was a picture with some dark sploches in it. Yeah. . .that's about it. (Subject: KM)

PT = 107ms

Fei-Fei, Iyer, Koch, Perona, JoV, 2007

Page 9: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Section outline

• Early “pictures and words” work• Content-based retrieval• Beyond nouns, towards total scene annotation

Page 10: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

“Pictures and words”• Barnard, Duygulu, de Freitas, Forsyth, Blei, Jordan,

Matching words and pictures, JMLR, 2003• Duygulu, Barnard, de Freitas, Forsyth, Object Recognition

as Machine Translation: Learning a lexicon for a fixed image vocabulary , ECCV, 2003

• Blei & Jordan, Modeling annotated data, ACM SIGIR, 2003

• Chang, Goh, Sychay, & Wu, Soft annotation using Bayes point machines, IEEE Transactions on Circuits and Systems for Video Technology, 2003

• Goh, Chang, & Cheng, Ensemble of SVM-based classifiers for annotation, 2003

• ….

Page 11: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Barnard et al. JMLR, 2005

• Images are composed of multimodal “concepts”.

• Images are clustered based on priors over concepts.

• Learning determines localized concepts models from global annotations.– Addresses the correspondence

problem – One possible assumption:

concept models simultaneously generate both a word and blob

sun

sunskywaterwaves

Slide courtesy of Kobus Barnard (1 hour ago!)

Page 12: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Barnard et al. JMLR, 2005

sun

sunskywaterwaves

Slide courtesy of Kobus Barnard (1 hour ago!)

• A generative model for assembling image data sets from multimodal clusters– Chose an image cluster by p(c)– Chose multimodal concept

clusters using p(s|c)– From each multimodal cluster,

sample a Gaussian for blob features, p(b|s), and a multinomial for words, p(w|s)

– (Skip with some probability to account for mismatched numbers of words and blobs)

– For a given correspondence*

p({w b}) p(c)c p(w | l)p(b | l)p(l | c)

l

wb

Page 13: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Barn

ard

et a

l. JM

LR, 2

005

Page 14: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Section outline

• Early “pictures and words” work• Content-based retrieval• Beyond nouns, towards total scene annotation

Page 15: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Content-based retrieval

Rose

FlowerPetals

Australian Floribunda Rose

Love

CorollaTower France

Eiffel Tower

Paris

Elegance

Symmetry

Slide courtesy of Ritendra Datta, Jia Li, James Z. Wang

Page 16: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Literature – MANY!!!

• A. W. Smeulders, M. Worring, S. Santini, A. Gupta, R. Jain, Content-Based Image Retrieval at the End of the Early Years, IEEE Trans. Pattern Analysis and Machine Intelligence , 22(12):1349-1380, 2000.

• R. Datta, D. Joshi, J. Li, and J. Z. Wang, Image Retrieval: Ideas, Influences, and Trends of the New Age, ACM Computing Surveys, vol. 40, no. 2, pp. 5:1-60, 2008.

Page 17: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Try out Alipr (www.alipr.com)

Page 18: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Try out Alipr (www.alipr.com)

Page 19: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Automatic Image Annotation: ALIP

Slide courtesy of Ritendra Datta, Jia Li, James Z. Wang

Page 20: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Automatic Image Annotation: ALIP

Slide courtesy of Ritendra Datta, Jia Li, James Z. Wang

Page 21: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Automatic Image Annotation: ALIP

Classification results form the basis Salient words appearing in the classification favored more

Annotation Process

Building, sky, lake, landscape,

Europe, tree

Food, indoor, cuisine, dessert

Snow, animal, wildlife, sky,

cloth, ice, people

Slide courtesy of Ritendra Datta, Jia Li, James Z. Wang

Page 22: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Section outline• Early “pictures and words” work• Content-based retrieval• Beyond nouns, towards total scene annotation

– PropositionsA. Gupta and L. S. Davis, Beyond Nouns: Exploiting prepositions and

comparative adjectives for learning visual classifiers, ECCV, 2008

– Objects, scenes, activitiesL.-J. Li and L. Fei-Fei. What, where and who? Classifying event by

scene and object recognition. ICCV, 2007L.-J. Li, R. Socher and L. Fei-Fei. Towards Total Scene

Understanding:Classification, Annotation and Segmentation in an Automatic Framework. CVPR, 2009

Page 23: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Section outline• Early “pictures and words” work• Content-based retrieval• Beyond nouns, towards total scene annotation

– PropositionsA. Gupta and L. S. Davis, Beyond Nouns: Exploiting prepositions and

comparative adjectives for learning visual classifiers, ECCV, 2008

– Objects, scenes, activitiesL.-J. Li and L. Fei-Fei. What, where and who? Classifying event by

scene and object recognition. ICCV, 2007L.-J. Li, R. Socher and L. Fei-Fei. Towards Total Scene

Understanding:Classification, Annotation and Segmentation in an Automatic Framework. CVPR, 2009

Page 24: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Gupta & Davis, EECV, 2008

“Beyond nouns”

Page 25: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Gupta & Davis, EECV, 2008

“Beyond nouns”

Page 26: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Gupta & Davis, EECV, 2008

Page 27: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Section outline• Early “pictures and words” work• Content-based retrieval• Beyond nouns, towards total scene annotation

– PropositionsA. Gupta and L. S. Davis, Beyond Nouns: Exploiting prepositions and

comparative adjectives for learning visual classifiers, ECCV, 2008

– Objects, scenes, activitiesL.-J. Li and L. Fei-Fei. What, where and who? Classifying event by

scene and object recognition. ICCV, 2007L.-J. Li, R. Socher and L. Fei-Fei. Towards Total Scene

Understanding:Classification, Annotation and Segmentation in an Automatic Framework. CVPR, 2009

Page 28: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

What, where and who? Classifying events by scene and object recognition

L-J Li & L. Fei-Fei, ICCV 2007

Page 29: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

scene pathway object pathway

event

L.-J. Li & L. Fei-Fei ICCV 2007

“where” pathway

“what” pathway

PFC

Page 30: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

scene pathway

“Polo Field”

L.-J. Li & L. Fei-Fei ICCV 2007

Fei-Fei & Perona, CVPR, 2005

Page 31: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

object pathway

O= ‘horse’

L.-J. Li & L. Fei-Fei ICCV 2007

L.-J. Li , G. Wang & L. Fei-Fei, CVPR, 2007

G. Wang & L. Fei-Fei, CVPR, 2006

L. Cao & L. Fei-Fei, ICCV, 2007

Page 32: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

The 3W stories

what who where

L.-J. Li & L. Fei-Fei ICCV 2007

Page 33: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Classification Annotation Segmentation

Horse

Horse

Horse

HorseHorse

SkyTree

Grass

AthleteHorseGrassTreesSkySaddle

Horse

Athlete

class: Polo

L-J Li , R. Socher & L. Fei-Fei, CVPR, 2009

Page 34: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Total Scene

Our model: a hierarchical representation of the image and its semantic contents

Class: Polo

AthleteHorseGrassTreesSkySaddle

HorseHorseHorse

Horse

SkyTree

GrassHorse

Athlete

noisy images and tags

Learning

Recognition

GenerativeModel

initialization

Sky

Athlete

Tree

Mountain

Rock Class:

Rock climbing

AthleteMountainTreesRockSkyAscent

Sky

Athlete

Water

Treesailboat

Class: Sailing

AthleteSailboatTreesWaterSkyWind

L-J Li , R. Socher & L. Fei-Fei, CVPR, 2009

Page 35: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Total Scene

Our model: a hierarchical representation of the image and its semantic contents

Class: Polo

AthleteHorseGrassTreesSkySaddle

HorseHorseHorse

Horse

SkyTree

GrassHorse

Athlete

noisy images and tags

Learning

Recognition

GenerativeModel

initialization

Sky

Athlete

Tree

Mountain

Rock Class:

Rock climbing

AthleteMountainTreesRockSkyAscent

Sky

Athlete

Water

Treesailboat

Class: Sailing

AthleteSailboatTreesWaterSkyWind

GenerativeModel

L-J Li , R. Socher & L. Fei-Fei, CVPR, 2009

Page 36: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Total Scene

The model: a hierarchical representation of the image and its semantic contents

AthleteHorseGrassTreesSkySaddle

C

Polo

O

horse

RNF

XAr ZNr Nt

S

T

D

Horse

“Switch variable”VisibleNot visible

“Connector variable”

Visual

Text

Page 37: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Total Scene

Our model: a hierarchical representation of the image and its semantic contents

Class: Polo

AthleteHorseGrassTreesSkySaddle

HorseHorseHorse

Horse

SkyTree

GrassHorse

Athlete

noisy images and tags

Learning

Recognition

GenerativeModel

initialization

Sky

Athlete

Tree

Mountain

Rock Class:

Rock climbing

AthleteMountainTreesRockSkyAscent

Sky

Athlete

Water

Treesailboat

Class: Sailing

AthleteSailboatTreesWaterSkyWind

GenerativeModel

Learning

initialization

L-J Li , R. Socher & L. Fei-Fei, CVPR, 2009

Page 38: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Total Scene

Need some good, initial “guestimate” of O

C

RNF

XAr Nr

ZNt

T

S

O

Scene/Event imagesfrom the Internet

L-J Li , R. Socher & L. Fei-Fei, CVPR, 2009

Page 39: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Total Scene

Scene/Event imagesfrom the Internet

Athlete

HorseGrassTree

SaddleWind

+

GenerativeModel

Auto-semi-supervised learning: Small # of initialized images + Large # of uninitialized images

Large # of uninitialized images

Small # of initialized images

L-J Li , R. Socher & L. Fei-Fei, CVPR, 2009

Page 40: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Total Scene

Our model: a hierarchical representation of the image and its semantic contents

Class: Polo

AthleteHorseGrassTreesSkySaddle

HorseHorseHorse

Horse

SkyTree

GrassHorse

Athlete

noisy images and tags

Learning

Recognition

GenerativeModel

initialization

Sky

Athlete

Tree

Mountain

Rock Class:

Rock climbing

AthleteMountainTreesRockSkyAscent

Sky

Athlete

Water

Treesailboat

Class: Sailing

AthleteSailboatTreesWaterSkyWind

L-J Li , R. Socher & L. Fei-Fei, CVPR, 2009

Page 41: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

Badminton

Bocce

Croquet

Polo

8 Event/Scene Classes

Rockclimbing

Rowing

Sailing

Snowboarding

Page 42: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

43

Class: Croquet Class: Bocce Class: Snowboarding Class: Polo

Class: Sailing Class: Badminton Class: Rock Climbing Class: Rowing

Total Scene

Some sample results

L-J Li , R. Socher & L. Fei-Fei, CVPR, 2009

Page 43: Iccv2009 recognition and learning object categories   p2 c03 - objects and annotations

I think I saw two people on a field. (Subject: RW)

Outdoor scene. There were some kind of animals, maybe dogs or horses, in the middle of the picture. It looked like they were running in the middle of a grassy field. (Subject: IV)

two people, whose profile was toward me. looked like they were on a field of some sort and engaged in some sort of sport (their attire suggested soccer, but it looked like there was too much contact for that). (Subject: AI)

Some kind of game or fight. Two groups of two men? The foregound pair looked like one was getting a fist in the face. Outdoors seemed like because i have an impression of grass and maybe lines on the grass? That would be why I think perhaps a game, rough game though, more like rugby than football because they pairs weren't in pads and helmets, though I did get the impression of similar clothing. maybe some trees? in the background. (Subject: SM)

PT = 500ms

PT = 27ms

PT = 40ms

PT = 67ms

This was a picture with some dark sploches in it. Yeah. . .that's about it. (Subject: KM)

PT = 107ms

Fei-Fei, Iyer, Koch, Perona, JoV, 2007


Recommended