AI Paper Atlas

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

IVQA: Inverse Visual Question Answering

Feng Liu, Tao Xiang, Timothy M. Hospedales, Wankou Yang, Changyin Sun

CVPR 2018 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 41 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 dynamic multi-modal attention to the image-and-answer model (ablation)iVQA · iVQA validationAcc@1: 29.929 -> 32.547Improved
add global semantic image features (ablation)iVQA with dynamic attention · iVQA validationAcc@1: 32.547 -> 33.636Improved
add dynamic multi-modal attention and global semantic image features (ablation)I+A · iVQA validationCIDEr: 1.541 -> 1.750Improved
combine VQA answers with iVQA scores using score fusionMLB-att · VQA 2.0 validationaccuracy: 57.85 -> 58.86Improved
combine VQA answers with iVQA scores using score fusionMLB-att · VQA 2.0 validation, number typeaccuracy: 34.94 -> 38.71Improved
use image and answer rather than answer aloneiVQA · iVQA testAcc@1: 14.589 -> 32.899Improved
provide the answer type in addition to the imageiVQA image-only model · iVQA testAcc@1: 13.012 -> 20.277Improved
use image-plus-answer-type instead of the full image-and-answer modeliVQA · iVQA testAcc@1: 20.277 -> 32.899Hurt
use the proposed dynamic multi-modal iVQA model instead of SATiVQA · iVQA testAcc@1: 29.722 -> 32.899Improved
use the proposed dynamic multi-modal iVQA model instead of VQG+VQAiVQA · iVQA testAcc@1: 16.529 -> 32.899Improved

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