×

WSABIE

swMATH ID: 30600
Software Authors: Weston, J., Bengio, S., Usunier, N.
Description: WSABIE: scaling up to large vocabulary image annotation. Image annotation datasets are becoming larger and larger, with tens of millions of images and tens of thousands of possible annotations. We propose a strongly performing method that scales to such datasets by simultaneously learning to optimize precision at the top of the ranked list of annotations for a given image and learning a low-dimensional joint embedding space for both images and annotations. Our method, called WSABIE, both outperforms several baseline methods and is faster and consumes less memory.
Homepage: https://dl.acm.org/citation.cfm?id=2283856
Related Software: word2vec; NUS-WIDE; ImageNet; Im2Text; GloVe; GitHub; DiSMEC; AnnexML; FastXML; PROPACK; TagProp; AnchorNet; Soft scissors; MVSNet; NIMA; EfficientNet; Fashion-MNIST; CamNet; Face2Face; DISN
Cited in: 8 Documents

Citations by Year