AI Paper Atlas

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

A Diagram is Worth a Dozen Images

Aniruddha Kembhavi, Mike Salvato, Eric Kolve, Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi

ECCV 2016 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 373 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
use sequential LSTM-based DPG inference instead of A* searchDSDP-Net · AI2D diagram parsing (test)JIG score: 41.02 -> 51.45Improved
use sequential LSTM-based DPG inference instead of greedy searchDSDP-Net · AI2D diagram parsing (test)JIG score: 28.96 -> 51.45Improved
use DPG-based attention (DQA-Net) instead of LSTM Q+I baseline, both trained on AI2Ddiagram QA · AI2D diagram QA (test)accuracy: 32.90 -> 38.47Improved
train the VQA baseline on AI2D instead of VQALSTM Q+I baseline · AI2D diagram QA (test)accuracy: 29.06 -> 32.90Improved
use RF blob proposals instead of Edge Boxesconstituent proposals · AI2D blob proposalsaverage precision: 0.02 -> 0.7829Improved
use single-character localizer plus OCR instead of Tesseract end-to-endtext detection · AI2D text localizationprecision: 0.2 -> 0.89Improved
use single-character localizer plus OCR instead of Tesseract end-to-endtext detection · AI2D text localizationrecall: 0.46 -> 0.75Improved

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