Audience Centric Internet Marketing and Online Advertising
Search
Home
Tools
Audience Intelligence
Demographics ...
Detecting Online ...
Explore MSN
Keyword Research
Entity Association ...
Keyword Forecast
Keyword Group ...
Keyword Mutation ...
Search Funnels
Content Analysis
Ad Text Writer
Content Categorization
Context-Based ...
Cross-Language ...
Entity Analysis
Location Platform
People Name Detection
Product Classification
Sensitive Webpage ...
Visual Product Browsing
Video & Interactive Media
Intelligent Bug ads
Video Hyperlink
All Tools
Blog
About
About Us
News & Happenings
Contact Us
Resources
Select your favorite service
Related Tools
Ad Text Writer
Automatically generate text ads for an input URL
Content Categorization
Classify web sites into categories
Context-Based Acronym Resolution
Expand acronyms and abbreviations based on related search keywords
Cross-Language Keyword Suggestion
Suggest relevant queries in a different language based on the query logs
Entity Analysis
Analyze multiple-word entities in a search query
Location Platform
Demonstrate key technologies on location intelligence, such as query dominant location detection, local intent, and location-based query suggestion
People Name Detection
Detect names of people in a query
Product Classification
Classify products into categories
Sensitive Webpage Detection
Detect whether a webpage contains sensitive content
Visual Product Browsing
This tool uses computer vision algorithms to browse and categorize images as a human might, without the need for manual data tagging. Online shoppers could use this technology to visually browse categorized product images (such as lamps) and narrow their search to find 'more like this' options.
To start, select a category on the left-hand navigation. Corresponding product images will display in the results area, clicking on an image will lead user to other similar images. To filter the results by color, select a color from the drop-down menu in the upper-right corner.
This project addresses the problem of reaching the target audience for advertisers whose products are buried inside a large categorized product database. The product images are retrieved based on attributes such as text and color and arranged into a hierarchical structure for more efficient browsing based on visual similarity. While users navigate through the tree-like structure, advertisers have a chance to reach their audience in a more targeted manner. The system also has the option to display complementary ads on the right-side of the browser window. Image clusters are generated on-the-fly instead of being built offline.
<< Back
SponsoredLinks