AI Paper Atlas

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

On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering

Xinyu Wang, Yuliang Liu, Chunhua Shen, Chun Chet Ng, Canjie Luo, Lianwen Jin, Chee Seng Chan, Anton van den Hengel, Liangwei Wang

CVPR 2020 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 76 citations (OpenAlex)

Check 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 heuristic manual rules and other tricks to QA R-CNN (ablation)QA R-CNN · STE-VQA test, CLC Acc (Bi.)accuracy (%): 6.0 -> 5.7Hurt
Add heuristic manual rules and other tricks to QA R-CNN (ablation)QA R-CNN · STE-VQA test, LC Acc (Bi.)accuracy (%): 12.8 -> 12.8No clear effect
Add heuristic manual rules and other tricks to QA R-CNN (ablation)QA R-CNN · STE-VQA test, TC Acc (Bi.)accuracy (%): 7.3 -> 11.0Improved
Require answers to be supported by predicted image-region evidenceVQA evaluation under EvE · STE-VQAaccuracyHurt
Use a larger answer vocabulary instead of a small onePythia and LoRRA · STE-VQA, English questionsaccuracyImproved

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