AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

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

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

ICCV 2021 · Vision-language and multimodal › Visual question answering · approach: Visual reasoning diagnostics · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
unify the Guesser and question generator in one transformer (vs Not Unified) (ablation)UniQer · CLEVR Ask3 (new image)task success ratio: 50.61 -> 84.10Improved
unify the Guesser and question generator in one transformer (vs Not Unified) (ablation)UniQer · CLEVR Ask4 (new image)task success ratio: 65.15 -> 83.47Improved
use transformer Guesser instead of MLP Guesser (vs Not Unified MLP Guesser) (ablation)UniQer · CLEVR Ask3 (new image)task success ratio: 69.43 -> 84.10Improved
use transformer Guesser instead of MLP Guesser (vs Not Unified MLP Guesser) (ablation)UniQer · CLEVR Ask4 (new image)task success ratio: 72.89 -> 83.47Improved
use transformer encoder/decoder instead of GRU/LSTM (vs Vanilla) (ablation)UniQer · CLEVR Ask3 (new image)task success ratio: 72.98 -> 84.10Improved
use transformer encoder/decoder instead of GRU/LSTM (vs Vanilla) (ablation)UniQer · CLEVR Ask4 (new image)task success ratio: 67.38 -> 83.47Improved
learn the OTM with RL instead of random actions (ablation)UniQer · CLEVR Ask3 (new image)task success ratio: 1.73 -> 84.10Improved
learn when to submit instead of forced stop at dialogue end (ablation)UniQer · CLEVR Ask3 (new image)task success ratio: 68.78 -> 84.10Improved
learn when to submit instead of forced stop at dialogue end (ablation)UniQer · CLEVR Ask4 (new image)task success ratio: 68.99 -> 83.47Improved
increase top-k from 5 to 7 (ablation)UniQer · CLEVR Ask3 (new image)task success ratio: 84.10 -> 82.66Hurt
increase top-k from 4 to 7 (ablation)UniQer · CLEVR Ask4 (new image)task success ratio: 83.47 -> 76.47Hurt
increase top-k from 4 to 5 (ablation)UniQer · CLEVR Ask4 (new image)task success ratio: 83.47 -> 81.20Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy