SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1712.03449 · 2017

Modulating and attending the source image during encoding improves Multimodal Translation

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a new and fully end-to-end approach for multimodal translation where the source text encoder modulates the entire visual input processing using conditional batch normalization, in order to compute the most informative image features for our task. Additionally, we propose a new attention mechanism derived from this original idea, where the attention model for the visual input is conditioned on the source text encoder representations. In the paper, we detail our models as well as the image analysis pipeline. Finally, we report experimental results. They are, as far as we know, the new state of the art on three different test sets.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1712.03449")
get_code_for_paper("1712.03449")
have("1712.03449")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1712.03449.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1712.03449.svg)](https://syntology.ai/paper/1712.03449)

Connect an agent — have() is free.