WSABIE: Scaling Up to Large Vocabulary Image Annotation
Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 2764-2769.
Abstract
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.
Jason Weston, Samy Bengio, and Nicolas Usunier. 2011. WSABIE: Scaling Up to Large Vocabulary Image Annotation. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11. IJCAI, 2764–2769. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-460
Weston, J., Bengio, S., & Usunier, N. (2011). WSABIE: Scaling Up to Large Vocabulary Image Annotation. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11 (pp. 2764–2769). IJCAI. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-460
@inproceedings{ijcai2011p460,
title = {WSABIE: Scaling Up to Large Vocabulary Image Annotation},
author = {Weston, Jason and Bengio, Samy and Usunier, Nicolas},
booktitle = {Proceedings of the Twenty-Second International Joint Conference on
Artificial Intelligence, {IJCAI-11}},
publisher = {AAAI Press/International Joint Conferences on Artificial Intelligence},
editor = {Toby Walsh},
pages = {2764--2769},
year = {2011},
month = {7},
doi = {10.5591/978-1-57735-516-8/IJCAI11-460},
url = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-460},
}
TY - CPAPER TI - WSABIE: Scaling Up to Large Vocabulary Image Annotation AU - Weston, Jason AU - Bengio, Samy AU - Usunier, Nicolas T2 - Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11 PB - AAAI Press/International Joint Conferences on Artificial Intelligence PY - 2011 SP - 2764 EP - 2769 DO - 10.5591/978-1-57735-516-8/IJCAI11-460 UR - https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-460 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
