An Information-Theoretic Definition of Similarity
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Probability Estimates for Multi-class Classification by Pairwise Coupling
The Journal of Machine Learning Research
Finding parts in very large corpora
ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
Cross-Generalization: Learning Novel Classes from a Single Example by Feature Replacement
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
One-Shot Learning of Object Categories
IEEE Transactions on Pattern Analysis and Machine Intelligence
Novel association measures using web search with double checking
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
OTM '08 Proceedings of the OTM 2008 Confederated International Conferences, CoopIS, DOA, GADA, IS, and ODBASE 2008. Part II on On the Move to Meaningful Internet Systems
Learning systems of concepts with an infinite relational model
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Wisdom of crowds versus wisdom of linguists – measuring the semantic relatedness of words
Natural Language Engineering
Hi-index | 0.00 |
Knowledge transfer between object classes has been identified as an important tool for scalable recognition. However, determining which knowledge to transfer where remains a key challenge. While most approaches employ varying levels of human supervision, we follow the idea of mining linguistic knowledge bases to automatically infer transferable knowledge. In contrast to previous work, we explicitly aim to design robust semantic relatedness measures and to combine different language sources for attribute-based knowledge transfer. On the challenging Animals with Attributes (AwA) data set, we report largely improved attribute-based zero-shot object class recognition performance that matches the performance of human supervision.