Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Designing games with a purpose
Communications of the ACM - Designing games with a purpose
Proceedings of the 18th international conference on World wide web
KissKissBan: a competitive human computation game for image annotation
Proceedings of the ACM SIGKDD Workshop on Human Computation
Webpage segmentation for extracting images and their surrounding contextual information
MM '09 Proceedings of the 17th ACM international conference on Multimedia
User needs for metadata management in mobile multimedia content services
Mobility '09 Proceedings of the 6th International Conference on Mobile Technology, Application & Systems
Classification of violent web images using context based analysis
Proceedings of the 2010 ACM Symposium on Applied Computing
Frontiers of a paradigm: exploring human computation with digital games
Proceedings of the ACM SIGKDD Workshop on Human Computation
Automatic generation of video narratives from shared UGC
Proceedings of the 22nd ACM conference on Hypertext and hypermedia
On the role of user-generated metadata in audio visual collections
Proceedings of the sixth international conference on Knowledge capture
Automatic Image Annotation Using Global and Local Features
SMAP '11 Proceedings of the 2011 Sixth International Workshop on Semantic Media Adaptation and Personalization
Games with a Purpose: User Generated Valid Metadata for Personal Archives
SMAP '11 Proceedings of the 2011 Sixth International Workshop on Semantic Media Adaptation and Personalization
CBSA: content-based soft annotation for multimodal image retrieval using Bayes point machines
IEEE Transactions on Circuits and Systems for Video Technology
Semantics Discovery via Human Computation Games
International Journal on Semantic Web & Information Systems
Human computation: Image metadata acquisition based on a single-player annotation game
International Journal of Human-Computer Studies
Hi-index | 0.00 |
An effective search and organization of personal multimedia repositories demands very specific, owner-related metadata (e.g. person names, places, events). Only the resource owners and their social circles are able to provide these metadata, but are often not motivated to do so. To increase their motivation, we introduce a game-based personal image annotation framework. Today's crowd-based games with a purpose (GWAP) are able to harness human labor to acquire metadata for general domain multimedia resources. However, their deployment in such specific domain as one's personal multimedia is hindered by the issue of extremely small number of competent potential workers. Therefore, a traditional cross-worker agreement filtering of wrong answers cannot be effectively applied. In our approach (which is an extension of an existing image tagging game), we overcome this issue by inviting user to play for his own good i.e. annotate his own images while enjoying the game. This additional motivation causes an overall increase of quality of user-generated metadata and thus allows the use of less strict tag extraction algorithms for producing final set of tags. We show that our approach is able to yield valid image annotations, specific to the context of the resource owner. We also examine its performance with different types of annotated images and tags.