SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.15550 · ICCV · 2021

Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue

Komei Sugiura, Michita Imai, Shoya Matsumori, Kosuke Shingyouchi, Yuki Abe, Yosuke Fukuchi

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

Building an interactive artificial intelligence that can ask questions about the real world is one of the biggest challenges for vision and language problems. In particular, goal-oriented visual dialogue, where the aim of the agent is to seek information by asking questions during a turn-taking dialogue, has been gaining scholarly attention recently. While several existing models based on the GuessWhat?! dataset [10] have been proposed, the Questioner typically asks simple category-based questions or absolute spatial questions. This might be problematic for complex scenes where the objects share attributes, or in cases where descriptive questions are required to distinguish objects. In this paper, we propose a novel Questioner architecture, called Unified Questioner Transformer (UniQer), for descriptive question generation with referring expressions. In addition, we build a goal-oriented visual dialogue task called CLEVR Ask. It synthesizes complex scenes that require the Questioner to generate descriptive questions. We train our model with two variants of CLEVR Ask datasets. The results of the quantitative and qualitative evaluations show that UniQer outperforms the baseline.

For agents

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

get_harvested_code_for_paper("2106.15550")
get_code_for_paper("2106.15550")
have("2106.15550")

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

curl https://syntology.ai/api/ran/2106.15550.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.15550.svg)](https://syntology.ai/paper/2106.15550)

Connect an agent — have() is free.