![Page 1: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/1.jpg)
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
![Page 2: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/2.jpg)
2
• Problem Statement • Dataset • Algorithm• Visualization – Brand Association Maps• Results• Conclusion
Outline
![Page 3: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/3.jpg)
3
A set of values or assets linked to a brand's name and symbol
Brand Equity
• 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)
![Page 4: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/4.jpg)
4
• [Keller 1993]
• [Aaker 1991]
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
Brand Equity
Name awareness
Brand loyalty
Perceived quality
Brand association
Other properties (ex. trademarks, patens)
A set of values or assets linked to a brand's name and symbol
Brand Equity
• Bearing competitive advantage over its competitors• Boosting efficiency and effectiveness of marketing programs• Attaining price premium due to increased customer satisfaction and loyalty
![Page 5: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/5.jpg)
5
• [Keller 1993]
• [Aaker 1991]
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
Brand Equity
Name awareness
Brand loyalty
Perceived quality
Brand association
Other properties (ex. trademarks, patens)
A set of values or assets linked to a brand's name and symbol
Brand Equity
• Bearing competitive advantage over its competitors• Boosting efficiency and effectiveness of marketing programs• Attaining price premium due to increased customer satisfaction and loyalty
![Page 6: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/6.jpg)
6
Brand Associations(What Comes to Mind When You Think of …)
soccer, national teams, …
basketball, golf, …
swimming, diving, beach, …
A set of associations that consumers perceive with the brand• Top-of-mind attitudes or feelings toward the brand
![Page 7: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/7.jpg)
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 need a men’s golf shirts… What would I buy?
I associate with
How can we find out people’s brand associations?
![Page 8: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/8.jpg)
8
A Traditional Way to Brand Associations
Collect direct consumer responses to carefully-designed questionnaires
In-N-Out [Dane et al. 2010] Reese’s [Till et al. 2011]
• Expensive and time-consuming
• Sampling bias /common methods bias
Can Web data save us?
Cheap and immediate
Candid impression from a large crowd of potential customers
![Page 9: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/9.jpg)
9
• Built from consumer-generated text data on online social media (eg. Weblogs, Boards, Wiki)
‘ ’s Brand Association Map
The most important concepts and themes that consumers have
![Page 10: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/10.jpg)
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!
![Page 11: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/11.jpg)
11
2. Take or bookmark pictures of the products you wish to buy.
1. Brands are recognized by images.
Why are online images helpful to discover brand associations?
Our Idea: Photo-based Brand Associations
Take advantage of large-scale online photo collections• No previous attempts so far to leverage the pictures
![Page 12: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/12.jpg)
12
Why are online images helpful to discover brand associations?
Our Idea: Photo-based Brand Associations
Take advantage of large-scale online photo collections• No previous attempts so far to leverage the pictures
3. Capture interactions between users and products
in natural social context
![Page 13: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/13.jpg)
13
• Identifying a small number of exemplars / image clusters
• Project the clusters into a circular layout
Objective of This Paper
1. (Image-level) Detect and visualize key pictorial concepts associated with brands
Two visualization tasks as a first technical step
![Page 14: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/14.jpg)
14
• A basic function to reveal interactions between users and products
• Potential benefits: content-based retrieval and online multimedia ad
Objective of This Paper
2. (Subimage-level) Localize the regions of brand in images
Two visualization tasks as a first technical step
![Page 15: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/15.jpg)
15
• Problem Statement • Dataset• Algorithm• Visualization – Brand Association Maps• Results• Conclusion
Outline
![Page 16: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/16.jpg)
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
Pictures bookmarked by users
Various forms of artwork by users
Photo hosted for twitter
![Page 17: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/17.jpg)
17
• Problem Statement • Dataset • Algorithm• Visualization – Brand Association Maps• Results• Conclusion
Outline
![Page 18: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/18.jpg)
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)
![Page 19: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/19.jpg)
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
![Page 20: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/20.jpg)
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?)
Clustering
![Page 21: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/21.jpg)
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
![Page 22: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/22.jpg)
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
![Page 23: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/23.jpg)
23
• Problem Statement • Dataset• Algorithm• Visualization – Brand Association Maps• Results• Conclusion
Outline
![Page 24: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/24.jpg)
24
Embedding on a Circular Layout
Goal: Compute two coordinates of key clusters
• Compute stationary distribution of nodes
Radial distance
• Radial distance: a larger cluster closer to the center• Angular distance: the smaller, the higher correlation
Radial distances
Angular distance• Sum of stationary distributions of nodes of each cluster the probability that a random walker stays
(Based on Nielson’s BAM)
![Page 25: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/25.jpg)
25
Embedding on a Circular Layout
Angular distance
Radial distances
Angular distance
• Using spherical Laplacian eigenmap [Carter et al. 2009.]
• Pairwise similarity btw clusters S using the random walk with restart [Sun et al. 2005]
Similar clusters should havesmaller angle difference
Penalty to avoid a trivial solution
Goal: Compute two coordinates of key clusters• Radial distance: a larger cluster closer to the center• Angular distance: the smaller, the higher correlation
(Based on Nielson’s BAM)
![Page 26: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/26.jpg)
26
• 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
Outline
![Page 27: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/27.jpg)
27
Experiments – Brand Association Maps
Brands' characteristic visual themes
Events sponsored by brands
Weddings
![Page 28: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/28.jpg)
28
Sub-M: Multiple runs of our clustering + cosegmentation Sub: Our clustering without cosegmentation Kmean/Spect: K-mean clustering / Spectral clusteringLP: Label propagation [Raghavan et al. 2007] AP: Affinity propagation [Frey & Dueck 2008]
Experiments – Exemplar Detection/Clustering
Groundtruth for clustering accuracy
• Randomly select 100 sets of three (i,j,k) images per class
• Accuracy is measured by how many sets are correctly clustered
• Manually select which of (j,k) is closer to i :
Wilcoxon-Mann-Whitney statistics
Similarity btw the clusters of image i and j
100
![Page 29: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/29.jpg)
29
Experiments – Brand Localization
Task: Foreground detection
MFC-M: Multiple runs of our clustering + cosegmentationMFC-S: Single run of our clustering + cosegmentationMFC: Random partition + our cosegmentationCOS: Submodular optimization [Kim et al. ICCV11] LDA: LDA-based localization [Russell et al. CVPR06]
• Manually annotate 50 images per class
• Accuracy is measured by intersection-over-union
![Page 30: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/30.jpg)
30
Experiments – Brand Localization
Task: Foreground detection
• Manually annotate 50 images per class
• Accuracy is measured by intersection-over-union
Examples
![Page 31: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/31.jpg)
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)
![Page 32: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/32.jpg)
32
• Problem Statement • Dataset• Algorithm• Visualization – Brand Association Maps• Results• Conclusion
Outline
![Page 33: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/33.jpg)
33
• Visualizing core pictorial concepts associated with brands
Study of brand associations from millions of Web images
• Experiments on 5 Millions images of 48 brands from five popular websites
Conclusion
• Complementary views on the brand associations beyond texts
Jointly achieving two levels of visualization tasks
• Localizing the regions of brand in images
Various potential applications
• Online multimedia contextual advertisement, competitor mining
![Page 34: Discovering Pictorial Brand Associations from Large-Scale Online Image Data](https://reader035.vdocuments.mx/reader035/viewer/2022062815/568168f7550346895de0062d/html5/thumbnails/34.jpg)
34
Press Release
Thank You!
Extended version will be presented in
http://www.cs.cmu.edu/news/carnegie-mellon-researchers-create-brand-associations-mining-millions-images-social-media-sites