AI Paper Atlas

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

Interpretable Visual Reasoning via Probabilistic Formulation under Natural Supervision

Xinzhe Han, Shuhui Wang, Chi Su, Weigang Zhang, Qingming Huang, Qi Tian

ECCV 2020 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 11 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 TRN to UpDnUpDn · VQA v2.0 test-devaccuracy (All): 65.82 -> 67.00Improved
add TRN to BAN-3BAN-3 · VQA v2.0 test-devaccuracy (All): 68.43 -> 68.38No clear effect
add TRN to BAN-3BAN-3 · VQA v2.0 test-stdaccuracy: 68.47 -> 68.76Improved
add TRN to UpDnUpDn · CLEVR valaccuracy: 78.1% -> 87.7%Improved
add TRN to UpDnUpDn · CLEVR-Humansaccuracy: 56.6% -> 69.5%Improved
add TRN to BAN-5BAN-5 · CLEVR valaccuracy: 83.1% -> 85.2%Improved
add TRN to BAN-5BAN-5 · CLEVR-Humansaccuracy: 60.5% -> 65.4%Improved
add TRN to DFAF-5DFAF-5 · CLEVR valaccuracy: 95.5% -> 96.7%Improved
add TRN to DFAF-5DFAF-5 · CLEVR-Humansaccuracy: 63.2% -> 72.9%Improved
add Generative Reconstruction to UpDn+TRN (ablation)UpDn+TRN · CLEVR valaccuracy: 82.3% -> 87.7%Improved
add State Inference and State Transition to UpDn (ablation)UpDn+TRN · CLEVR valaccuracy: 78.1% -> 87.7%Improved
use a different partial component subset (Table 3 rows 84.3 and 77.6) versus full TRN (ablation)UpDn+TRN · CLEVR valaccuracy: 84.3% -> 87.7%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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