TY - GEN
T1 - Searching for design examples with crowdsourcing
AU - Spirin, Nikita
AU - Eslami, Motahhare
AU - Ding, Jie
AU - Jain, Pooja
AU - Bailey, Brian
AU - Karahalios, Karrie
N1 - Publisher Copyright:
© Copyright 2014 by the International World Wide Web Conferences Steering Committee.
PY - 2014/4/7
Y1 - 2014/4/7
N2 - Examples are very important in design, but existing tools for design example search still do not cover many cases. For instance, long tail queries containing subtle and subjective design concepts, like "calm and quiet", "elegant", "dark back- ground with a hint of color to make it less boring", are poorly supported. This is mainly due to the inherent complexity of the task, which so far has been tackled only algorithmi- cally using general image search techniques. We propose a powerful new approach based on crowdsourcing, which complements existing algorithmic approaches and addresses their shortcomings. Out of many explored crowdsourcing configurations we found that (1) a design need should be represented via several query images and (2) AMT crowd workers should assess a query-specific relevance of a candi- date example from a pre-built design collection. To test the utility of our approach, we compared it with Google Images in a query-by-example mode. Based on feedback from expert designers, the crowd selects more relevant design examples.
AB - Examples are very important in design, but existing tools for design example search still do not cover many cases. For instance, long tail queries containing subtle and subjective design concepts, like "calm and quiet", "elegant", "dark back- ground with a hint of color to make it less boring", are poorly supported. This is mainly due to the inherent complexity of the task, which so far has been tackled only algorithmi- cally using general image search techniques. We propose a powerful new approach based on crowdsourcing, which complements existing algorithmic approaches and addresses their shortcomings. Out of many explored crowdsourcing configurations we found that (1) a design need should be represented via several query images and (2) AMT crowd workers should assess a query-specific relevance of a candi- date example from a pre-built design collection. To test the utility of our approach, we compared it with Google Images in a query-by-example mode. Based on feedback from expert designers, the crowd selects more relevant design examples.
KW - AMTurk
KW - Crowdsourcing
KW - Design search
KW - Query-by-example
UR - http://www.scopus.com/inward/record.url?scp=84990884951&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84990884951&partnerID=8YFLogxK
U2 - 10.1145/2567948.2577371
DO - 10.1145/2567948.2577371
M3 - Conference contribution
AN - SCOPUS:84990884951
T3 - WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web
SP - 381
EP - 382
BT - WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web
PB - Association for Computing Machinery
T2 - 23rd International Conference on World Wide Web, WWW 2014
Y2 - 7 April 2014 through 11 April 2014
ER -