Publication

Structured prediction with output embeddings for semantic image annotation

Conference Article

Conference

Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT)

Edition

2016

Pages

552-557

Doc link

https://aclweb.org/anthology/N/N16/N16-1068.pdf

File

Download the digital copy of the doc pdf document

Abstract

We address the task of annotating images with semantic tuples. Solving this problem requires an algorithm able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key challenge. We propose handling this sparsity by incorporating feature representations of both the inputs (images) and outputs (argument classes) into a factorized log-linear model.

Categories

computer vision.

Author keywords

natural language processing

Scientific reference

A. Quattoni, A. Ramisa, P. Swaroop, E. Simo-Serra and F. Moreno-Noguer. Structured prediction with output embeddings for semantic image annotation, 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , 2016, San Diego, pp. 552-557.