Multimodal Attention Branch Network for Perspective-Free Sentence Generation [article]

Aly Magassouba and Komei Sugiura and Hisashi Kawai
2019 arXiv   pre-print
In this paper, we address the automatic sentence generation of fetching instructions for domestic service robots. Typical fetching commands such as "bring me the yellow toy from the upper part of the white shelf" includes referring expressions, i.e., "from the white upper part of the white shelf". To solve this task, we propose a multimodal attention branch network (Multi-ABN) which generates natural sentences in an end-to-end manner. Multi-ABN uses multiple images of the same fixed scene to
more » ... erate sentences that are not tied to a particular viewpoint. This approach combines a linguistic attention branch mechanism with several attention branch mechanisms. We evaluated our approach, which outperforms the state-of-the-art method on a standard metrics. Our method also allows us to visualize the alignment between the linguistic input and the visual features.
arXiv:1909.05664v1 fatcat:wpvrdmtdafbibieoknwo6aoioq