.png){kind=icon}
.png){kind=icon}
Return
When Amazon Meets Google: Product Visualization by Exploring Multiple Web Sources
.png){kind=icon}
OA
AI
DOI：10.1145/2492690.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Product visualization is able to help users easily get knowledge about the visual appearance of a product. It is useful in many application and commercialization scenarios. However, the existing product image search on e-commerce Web sites or general search engines usually get insufficient search results or return images that are redundant and not relevant enough. In this article, we present a novel product visualization approach that automatically collects a set of diverse and relevant product images by exploring multiple Web sources. Our approach simultaneously leverages Amazon and Google image search engines, which represent domain-specific knowledge resource and general Web information collection, respectively. We propose a conditional clustering approach that is formulated as an affinity propagation problem regarding the Amazon examples as information prior. The ranking information of Google image search results is also explored. In this way, a set of exemplars can be found from the Google search results and they are provided together with the Amazon example images for product visualization. Experiments demonstrate the feasibility and effectiveness of our approach.
Keywords:
Algorithms
Experimentation
Human Factors
Product visualization
Web source
image search
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.1
Papers:
896
Citations:
1.9K