Using Attributes to Describe What People Wear Andy Gallagher October 14, 2013 with Huizhong Chen and Bernd Girod.

Using Attributes to Describe What People

WearAndy Gallagher

October 14, 2013 with Huizhong Chen and Bernd Girod

Objective

List of attributesMen’sBlack colorSweaterLong sleeveSolid patternLow skin exposure…

Attribute learning

3

Outline Attributes Describing Clothing with Attributes ! Miscellaneous Topics !

Attributes

Attributes Describing objects by their attributes, A

Farhadi, I Endres, D Hoiem, D ForsythComputer Vision and Pattern Recognition, 2009. CVPR 2009

Learning To Detect Unseen Object Classes by Between-Class Attribute Transfer, C. Lampert, H. Nickisch, S. Harmeling, CVPR 2009

Many others

Computer Vision

image

features

classification

Computer Vision

image

features

classification

[ .1 -.9.1.231-.1]

?

Computer Vision

image

features

classification

What feature representation should we use?

Computer Vision

image

features

classification

[ .1 -.9.1.231-.1]

Now we can talk…

attributes Has hair, has skin, has ear, has eye, has arms

Attributes Properties shared by many objects Explicit semantics Facilitate human-CPU communication Materials (glass, fur, wood, etc.) Parts (has wheel, has tail, etc.) Shape (boxy, cylindrical, etc.)

11Based on a slide by David Forsyth

Example AttributesFace Tracer Image Search

“Smiling Asian Men With Glasses”

Kumar et al., 200812

Example Attributes

Farhadi et al. 2009 13

Example Attributes

Lampert et al. 200914

Slide credit: Devi Parikh

Example Attributes

Welinder et al. 201015


16

Attribute Models Classifiers for binary attributes

Kumar et al. 2010


17

Why attributes? How humans naturally describe visual

concepts Image search I want elegant

silver sandals with high heels


Example Attributes

Verification

classifier

SAMEKumar et al., 2010

Why attributes? An okapi is a mammal with a reddish dark

back, with striking horizontal white stripes on the front and back legs. (Wikipedia)

19



20



21

Zero-shot Learning Aye-ayes

Are nocturnal Live in trees Have large eyes Have long middle fingers

Which one of these is an aye-aye?

Humans can learn from descriptions (zero examples).

Slide adapted from Christoph Lampert by Devi Parikh 22

Is this a giraffe? No.

Is this a giraffe? Yes.

Is this a giraffe? No.

23Slide credit: Devi Parikh

I think this is a giraffe. What do you think?

No, its neck is too short for it to be a giraffe.

Ah! These must not be giraffes

either then.

[Animals with even shorter necks]

……

Current belief Focused feedbackKnowledge of the world

Feedback on one, transferred to many

Learner learns better from its mistakes Accelerated discriminative learning with few

examples

Parkash and Parikh, 2012

24Slide credit: Devi Parikh

Which Attributes to Describe?

25

(a) (b) (c)

(d)(e)

(f)

Please choose a person to the left of the person who is frowning

Sadovnik et al. 2013

Describing Clothing with Attributes

Objective

List of attributesMen’sBlack colorSweaterLong sleeveSolid patternLow skin exposure…

Attribute learning

Recommend and Analyze

Formal Sport

Recommendations

Related Work Person identification with clothing

Bounding box under face [Anguelov, 2007]

Clothing segmentation [Gallagher, 2008]

Dataset Preparation 1856 people from the web. Images are unconstrained.

Dataset Preparation$400 spent for collecting 283,107 labels on Amazon Mechanical Turk (AMT).

Dataset Statistics23

Bin

ary

3 M

ultic

lass

The System

Pose estimation

Feature extraction & quantization

Attribute classifier 1


Attribute classifier M

…

Multi-attribute CRF inference

Feature 1

Feature N

… SVM1

SVMN

… Combine features SVM

PredictionsBlueSolid patternOuterwearWear scarfLong sleeve

A: attribute

F: feature

A2

A1

A3

F1

F2

F3

F4

A4

…

…

Pose Estimation [Eichner et. al., 2010] Perform upper body detection, by using complementary results

from face detector and deformable part models. Foreground highlighting within the enlarged upper body bounding

box. Parse the upper body into head, torso, upper and lower parts of the

left and right arms.

SIFT descriptor extracted over the sampling grid.

Similar procedure for the arm regions.

Feature Extraction

Feature Extraction Maximum Response Filters [Varma 2005]

LAB color Skin probability

RGB image

Skin probability

MRF bank

Feature Extraction Raw features are quantized using soft K-

means (K=5 in our implementation). Quantized features are aggregated over

various body regions, by max or average pooling.

For learning color attributes, the feature is LAB color aggregated from non-skin regions.

Feature type Region Pooling method

SIFT Torso Average

Texture Left upper arm Max

Color Right upper arm

Skin probability Left lower arm

Right lower arm

Feature Fusion SVM is a kernel-based classification technique. Feature fusion solution: combined SVM is

trained using weighted sum of the kernels. Combining features consistently outperforms

the single best feature.

SVM 1

SVM 2

SVM N

K1

K2

KN

Predict accuracy 2

K1

K2

KN

SVM Combined

Predict accuracy 1

…

Predict accuracy N

Attribute prediction

Recap

Pose estimation

Feature extraction & quantization



Attribute classifier M

…

Multi-attribute CRF inference

Feature 1

Feature N

… SVM1

SVMN

… Combine features SVM

PredictionsBlueSolid patternOuterwearWear scarfLong sleeve

A: attribute

F: feature

A2

A1

A3

F1

F2

F3

F4

A4

…

…

Attribute Dependencies

Necktie and T-Shirt?

Attribute Inference with CRF Each attribute is a node. All nodes are pair-wise

connected. The edge connecting 2 nodes corresponds to the

joint probability of these 2 attributes.

Ai: Attribute iFi: Features for Ai

A6

F6

A2

A1

A3

A5

A4

F1

F2

F3

F4

F5

CRF for Attribute Learning

44

For a fully connected CRF, we maximize:

The CRF potential is maximized using standard belief propagation technique [Tappen et. al. 2003] .

),(),,(),,( 2121212121 AAPAAFFPFFAAP

CAAPAP

FAP

AP

FAPFFAAP

AAAA

),(

potential Edge

21

)(potential 2 Node

2

22

)(potential 1 Node

1

112121

2121

),(log)(

)(log

)(

)(log),,(log

[Following CRF model]),()()( 212211 AAPAFPAFP

),()(

)(

)(

)(21

2

22

1

11 AAPAP

FAP

AP

FAP

A1 AM

F1 FM

A2

F2

…

…

EAA

jiSA

i

jii

AAA),(

),()(

Node potential Edge potential

No necktie (Wear necktie)Has collar

Men’s Has placket

Low exposure No scarf

Solid patternBlack

Short sleeve (Long sleeve)V-shape neckline

Dress (Suit)

Wear necktieHas collar

Men’sHas placket

High exposure (Low exposure)No scarf

Solid patternGray & blackLong sleeve

V-shape neckline Suit

No necktieHas collar

Men’sHas placket

Low exposureWear scarf

Solid patternBrown & black

No sleeve (long sleeve)V-shape neckline

Tank top (outerwear)

Experimental Results Questions that we are interested in:

Does combining features improve performance?

Does the pose model help? Does the CRF work?

Pose Vs No Pose - Experiment Setup Positive and negative examples are

balanced. SVM classification

Chi-squared kernel Leave-1-out cross validation

Comparison with attribute learning without pose model. Features are extracted within a scaled

clothing mask under the face. Evaluation performed under the same

experiment settings. The clothing mask [Gallagher 2008]

Neckti

e

Gender

Skin ex

posure

Pattern

solid

Pattern

spot

Pattern

plaid

Color red

Color gree

n

Color blue

Color bro

wn

Color gray

>2 co

lors

neckli

ne45%

50%

55%

60%

65%

70%

75%

80%

85%

90%

95%

Best feature (with pose) Combined feature (with pose)Combined feature (no pose)

Accu

racy

(bin

ary-

clas

s) /

MAP

(mul

ti-cl

ass)

Multiclass Confusion Matrix

Neckti

e

Gender

Skin ex

posure

Pattern

solid

Pattern

spot

Pattern

plaid

Color red

Color gree

n

Color blue

Color bro

wn

Color gray

>2 co

lors

neckli

ne45%

50%

55%

60%

65%

70%

75%

80%

85%

90%

95%

Before CRF After CRFG

-mea

n

Steve Jobs:“solid pattern, men’s clothing, black color, long sleeves, round neckline, outerwear, wearing scarf”

The predicted dressing style of weddings: Male: “solid pattern, suit, long-sleeves, V-

shape neckline, wearing necktie, wearing scarf, has collar, has placket”

Female: “high skin exposure, no sleeves, dress, other neckline shapes, white, >2 colors, floral pattern”

Gender RecognitionFace-based: Project faces in the Fisher space.Clothing-based: The gender output of our system.Better gender recognition is achieved by combining face and clothing.

Conclusions Clothing attributes can be better learned

with a human pose model. CRF offers improved performance by

exploring attribute relations. Proposed novel applications that exploit

the predicted attributes.

Miscellaneous

56

What do you have?

57

58

59

AutoCropping

60

AutoCropping

61Auction Probability: 97%

AutoCropping

62

Eigenvector

Quantized Eigenvector

63

How do photos affect value?

64

Angled, high contrast: ~$115

How do photos affect value?

65

Frontal, Flash reflection~$88

Thank You!

66

Future Work Expect even better performance by using

the (almost) ground truth pose estimated by Kinect sensors [Shotton et. al., Best Paper CVPR 2011].

Incorporate clothing information in person identification.

68

The Loop

Images and Computer Vision

What we know about people

69

The Loop: This talk Examples of how social data has helped

understand images of people Some things I’ve learned about people

from computer vision

75

What is context?

76

Context

77

Which monster is larger?

Shepard RN (1990) Mind Sights: Original Visual Illusions, Ambiguities, and other Anomalies, New York: WH Freeman and Company

78

Your brain specializes in faces

79

Find The Face In the beans:

http://www.michaelbach.de/ot/sze_muelue/index.html



80

Understanding images of people

Using Attributes to Describe What People Wear Andy Gallagher October 14, 2013 with Huizhong Chen and Bernd Girod.

Documents

arms slide

multiclass slide

devi parikh slide

feature extraction slide

david forsyth slide

bernd girod slide

high heels slide credit

semantic attributes