1. Discovering Pictorial Brand Associations from Large-Scale Online Image Data
Gunhee Kim* Eric P. Xing
School of Computer Science, Carnegie Mellon University *: (now with Disney Research Pittsburgh)
December 7, 2013

2. Outline Problem Statement Dataset Algorithm
Visualization – Brand Association Maps
Results
Conclusion

3. Brand Equity
A set of values or assets linked to a brand's name and symbol
Bearing competitive advantage over its competitors
Boosting efficiency and effectiveness of marketing programs
Attaining price premium due to increased customer satisfaction and loyalty
Interbrand (2013)

4. Brand Equity
A set of values or assets linked to a brand's name and symbol
Bearing competitive advantage over its competitors
Boosting efficiency and effectiveness of marketing programs
Attaining price premium due to increased customer satisfaction and loyalty
[Keller 1993]
Brand Knowledge
Brand Awareness
Brand Image
Brand recall
Brand Recognition
Types of brand association
Favorability of brand association
Strength of brand association
Uniqueness of brand association
[Aaker 1991]
Brand Equity
Name awareness
Brand loyalty
Perceived quality
Brand association
Other properties (ex. trademarks, patens)

5. Brand Equity
A set of values or assets linked to a brand's name and symbol
Bearing competitive advantage over its competitors
Boosting efficiency and effectiveness of marketing programs
Attaining price premium due to increased customer satisfaction and loyalty
[Keller 1993]
Brand Knowledge
Brand Awareness
Brand Image
Brand recall
Brand Recognition
Types of brand association
Favorability of brand association
Strength of brand association
Uniqueness of brand association
[Aaker 1991]
Brand Equity
Name awareness
Brand loyalty
Perceived quality
Brand association
Other properties (ex. trademarks, patens)

6. Brand Associations (What Comes to Mind When You Think of …)
A set of associations that consumers perceive with the brand
Top-of-mind attitudes or feelings toward the brand
basketball, golf, …
soccer, national teams, …
swimming, diving, beach, …

7. Brand Associations (What Comes to Mind When You Think of …)
A set of associations that consumers perceive with the brand
Top-of-mind attitudes or feelings toward the brand
Consumer-driven brand equity
I associate
with
I need a men’s golf shirts… What would I buy?
How can we find out people’s brand associations?

8. A Traditional Way to Brand Associations
Collect direct consumer responses to carefully-designed questionnaires
Reese’s
[Till et al. 2011]
In-N-Out
[Dane et al. 2010]
Expensive and time-consuming
Cheap and immediate
Sampling bias /common methods bias
Candid impression from a large crowd of potential customers
Can Web data save us?

9. ‘ ’s Brand Association Map
The most important concepts and themes that consumers have
Built from consumer-generated text data on online social media (eg. Weblogs, Boards, Wiki)

10. Our Idea: Photo-based Brand Associations
Take advantage of large-scale online photo collections
No previous attempts so far to leverage the pictures
Our underlying rational
Take a picture and tag as burger+king
Pictorial opinion on burger+king
Crawl millions of online images tagged as burger+king
We can read people’s candid pictorial opinions on burger+king
Pictures cannot replace texts. They are complementary.
ex) Nike shoes are too expensive. Their design is tacky!

11. Our Idea: Photo-based Brand Associations
Take advantage of large-scale online photo collections
No previous attempts so far to leverage the pictures
Why are online images helpful to discover brand associations?
1. Brands are recognized by images.
2. Take or bookmark pictures of the products you wish to buy.

12. Our Idea: Photo-based Brand Associations
Take advantage of large-scale online photo collections
No previous attempts so far to leverage the pictures
Why are online images helpful to discover brand associations?
3. Capture interactions between users and products in natural social context

13. Objective of This Paper
Two visualization tasks as a first technical step
1. (Image-level) Detect and visualize key pictorial concepts associated with brands
Identifying a small number of exemplars / image clusters
Project the clusters into a circular layout

14. Objective of This Paper
Two visualization tasks as a first technical step
2. (Subimage-level) Localize the regions of brand in images
A basic function to reveal interactions between users and products
Potential benefits: content-based retrieval and online multimedia ad

15. Outline Problem Statement Dataset Algorithm
Visualization – Brand Association Maps
Results
Conclusion

16. Image Dataset from Five Websites
4,720,724 images of 48 brands of four categories
Luxury
Sports
Beer
Fastfood
Two largest and most popular photo sharing Web communities
Various forms of artwork by users
Pictures bookmarked by users
Photo hosted for twitter

17. Outline Problem Statement Dataset Algorithm
Visualization – Brand Association Maps
Results
Conclusion

18. Approach – KNN Graph Generation
Input: a set of images of a brand (e.g. louis+vuitton):
Feature extraction
Dense feature extraction of Color SIFT and HOG
Histogram intersection for similarity measure
KNN Similarity graph
Approximate method (Multiple random divide-and-conquer using meta-data) [Wang et al. 2012] in O(NlogN)

19. Approach – Exemplar Detection/Clustering
Detecting L number of exemplars
A small set of representative images
Diversity ranking algorithm (temperature maximization) [Kim & Xing 2011]
Solving submodular optimization on

20. Approach – Exemplar Detection/Clustering
Each image I is associated with its closest exemplar
Random walk model (What exemplar is most likely reachable from each I?)

21. Approach – Brand Localization via Cosegmentation
Find the regions that are most relevant to the brand
Use MFC algorithm [Kim&Xing. 2012] to each cluster of coherent images
Make parallelization easy and prevent cosegmenting images of no commonality
Optionally, generate bounding boxes

22. Approach – Closing a Loop
Go back to graph generation
(Our argument) even imperfect segmentation helps obtain better image similarity measurement.
Not robust against the location and scale change
Image similarity as the mean of best matched segment similarity

23. Outline Problem Statement Dataset Algorithm
Visualization – Brand Association Maps
Results
Conclusion

24. Embedding on a Circular Layout
Goal: Compute two coordinates of key clusters
Radial distance: a larger cluster closer to the center
(Based on Nielson’s BAM)
Angular distance: the smaller, the higher correlation
Radial distance
Compute stationary distribution of nodes
Sum of stationary distributions of nodes of each cluster  the probability that a random walker stays
Angular distance
Radial distances

25. Embedding on a Circular Layout
Goal: Compute two coordinates of key clusters
Radial distance: a larger cluster closer to the center
(Based on Nielson’s BAM)
Angular distance: the smaller, the higher correlation
Angular distance
Pairwise similarity btw clusters S using the random walk with restart [Sun et al. 2005]
Using spherical Laplacian eigenmap [Carter et al ]
Angular distance
Similar clusters should have smaller angle difference
Penalty to avoid a trivial solution
Radial distances

26. Outline Problem Statement Dataset Algorithm
Visualization – Brand Association Maps
Results
Examples of Brand Association Maps
Quantitative results for exemplar detection/clustering
Quantitative results for brand localization
Correlations btw Web image data and actual sales data
Conclusion

27. Experiments – Brand Association Maps
Weddings
Events sponsored by brands
Brands' characteristic visual themes

28. Experiments – Exemplar Detection/Clustering
Groundtruth for clustering accuracy
Randomly select 100 sets of three (i,j,k) images per class
Manually select which of (j,k) is closer to i :
Accuracy is measured by how many sets are correctly clustered
Similarity btw the clusters of image i and j
Wilcoxon-Mann-Whitney statistics
100
Sub-M: Multiple runs of our clustering + cosegmentation
Sub: Our clustering without cosegmentation Kmean/Spect: K-mean clustering / Spectral clustering
LP: Label propagation [Raghavan et al. 2007] AP: Affinity propagation [Frey & Dueck 2008]

29. Experiments – Brand Localization
Task: Foreground detection
Manually annotate 50 images per class
Accuracy is measured by intersection-over-union
MFC-M: Multiple runs of our clustering + cosegmentation
MFC-S: Single run of our clustering + cosegmentation MFC: Random partition + our cosegmentation
COS: Submodular optimization [Kim et al. ICCV11] LDA: LDA-based localization [Russell et al. CVPR06]

30. Experiments – Brand Localization
Task: Foreground detection
Manually annotate 50 images per class
Accuracy is measured by intersection-over-union
Examples

31. Experiments – Correlation with Sales Data
Photo volumes vs. Market share
Nike’s market share is 57.6% in sports brands. How’s about image volumes?
Based on brands’ annual reports
Observations
Ranking are roughly similar, but the proportions do not agree.
Guinness : premium beer (more photo data) Taco+bell : cheap fastfood brand (fewer photo data)

32. Outline Problem Statement Dataset Algorithm
Visualization – Brand Association Maps
Results
Conclusion

33. Conclusion Study of brand associations from millions of Web images
Complementary views on the brand associations beyond texts
Experiments on 5 Millions images of
48 brands from five popular websites
Jointly achieving two levels of visualization tasks
Visualizing core pictorial concepts associated with brands
Localizing the regions of brand in images
Various potential applications
Online multimedia contextual advertisement, competitor mining

34. Thank You! Extended version will be presented in Press Release