作者: Nicolas Usunier , Samy Bengio , Jason Weston
DOI: 10.5591/978-1-57735-516-8/IJCAI11-460
关键词:
摘要: Image annotation datasets are becoming larger and larger, with tens of millions images thousands possible annotations. We propose a strongly performing method that scales to such by simultaneously learning optimize precision at the top ranked list annotations for given image low-dimensional joint embedding space both Our method, called WSABIE, outperforms several baseline methods is faster consumes less memory.