Stereotype-based Semantic Expansion for Image Retrieval
KAIST Tech. Report (WST-TR-2013-001)
(To appear ICME 2013 short paper)
|
|
This figure shows the framework and brief results about SSE.
Abstract
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.
Contents
Paper:
Stereotype-based Semantic Expansion for Image Retrieval,
KAIST Tech. Report (WST-TR-2013-001), 2013 (Accepted to ICME 2013 short paper)
Related Links
SGLab
Dept. of Computer Science
KAIST
373-1 Guseong-dong, Yuseong-gu, Daejeon, 305-701
South Korea
sglabkaist dot gmail dot com