AI Paper Atlas

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

Learning to Disambiguate by Asking Discriminative Questions

Yining Li, Chen Huang, Xiaoou Tang, Chen Change Loy

ICCV 2017 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 23 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
add question similarity term to attribute contrast (ablation)ACQG · VDQG (full)BLEU: 52.9 -> 59.1Improved
add visual dissimilarity term (ablation)ACQG · VDQG (full)BLEU: 59.1 -> 59.4Improved
add visual dissimilarity term (ablation)ACQG · VDQG (full)Delta BLEU: 40.1 -> 40.6Improved
add question similarity term to attribute contrast (ablation)ACQG · VDQG (hard subset)BLEU: 44.3 -> 53.2Improved
add visual dissimilarity term (ablation)ACQG · VDQG (hard subset)BLEU: 53.2 -> 53.6Improved
add visual dissimilarity term (ablation)ACQG · VDQG (hard subset)Delta BLEU: 32.6 -> 33.5Improved
add question similarity term to attribute contrast (ablation)ACQG · VDQG (full)Delta BLEU: 29.4 -> 40.1Improved
add question similarity term to attribute contrast (ablation)ACQG · VDQG (hard subset)Delta BLEU: 13.5 -> 32.6Improved
attribute score contrast alone instead of CNN-LSTM (no attributes guidance via similarity) (ablation)ACQG · VDQG (full)BLEU: 56.2 -> 52.9Hurt
full attribute-guided model vs CNN-LSTM baselineACQG · VDQG (full)BLEU: 56.2 -> 59.4Improved
full attribute-guided model vs CNN-LSTM baselineACQG · VDQG (hard subset)BLEU: 47.8 -> 53.6Improved
full attribute-guided model vs CNN-LSTM baselineACQG · VDQG (hard subset)Delta BLEU: 20.3 -> 33.5Improved

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