Peekaboom: a game for locating objects in images
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Web Information Retrieval in Collaborative Tagging Systems
WI '06 Proceedings of the 2006 IEEE/WIC/ACM International Conference on Web Intelligence
Collective knowledge systems: Where the Social Web meets the Semantic Web
Web Semantics: Science, Services and Agents on the World Wide Web
Integrating Folksonomies with the Semantic Web
ESWC '07 Proceedings of the 4th European conference on The Semantic Web: Research and Applications
| Hi-index | 0.00 |
In this paper, we present the web-based resource sharing system KnownStyleNoLife, which allows users explicitly annotate fashion-related images. KnownStyleNoLife harnesses human power and collects image metadata such as object locations, object labels, image rating and semantic relationships among images. Metadata of that type are invaluable as it is difficult for ordinary computer software to extract equivalent metadata from the Web. Acquiring image metadata such as the type and location of objects in images requires a computer to use machine learning techniques, needing training with sample images and Web search techniques, with the outcome that only limited image metadata are extracted. Furthermore, the semantic image relationship metadata is based upon people’s image perception, hence user feedback is required to acquire it. KnownStyleNoLife provides a social value to users in return for their explicit annotations. It is a novel approach to harness human power to acquire relevant image metadata.