Stereotype-based Semantic Expansion for Image Retrieval

by JungIn Lee, OSung Kwon, Youngwoon Lee, and Sung-eui Yoon.

KAIST Tech. Report (WST-TR-2013-001)
(To appear ICME 2013 short paper)

This figure shows the framework and brief results about SSE.


We present a novel, stereotype-based semantic expansion approach to identify various image sets that stereotypically represent different aspects of a given keyword. Specifically, given an adjective keyword query, our method expands it to a set of noun sub-keywords, which are stereotypical examples that can be described by the given adjective (e.g., ˇ°cuteˇ± to ˇ°{infant, kitten, ...}ˇ±). We also perform a similar process for given noun keywords with adjectives (e.g., ˇ°infantˇ± to ˇ°{cute, sweet, ...}ˇ±). To perform such expansion, we use Google Books n-grams, a new corpus of 500 million digitized books. We harvest stereotypical relationships among nouns and adjectives by utilizing useful lexical patterns such as similes on n-grams. In order to demonstrate benefits of our method, we have applied our method to image retrieval. By suggesting our expanded sub-keywords additionally to commonly co-occurring terms our method can explore unusual concepts and their corresponding images that are stereotypically related to the keyword.


Paper: Stereotype-based Semantic Expansion for Image Retrieval,
KAIST Tech. Report (WST-TR-2013-001), 2013 (Accepted to ICME 2013 short paper)

Related Links


Dept. of Computer Science
373-1 Guseong-dong, Yuseong-gu, Daejeon, 305-701
South Korea
sglabkaist dot gmail dot com