AI Paper Atlas

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

Deep Attention Neural Tensor Network for Visual Question Answering

Yalong Bai, Jianlong Fu, Tiejun Zhao, Tao Mei

ECCV 2018 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 68 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 neural tensor network (k=6) over image-question-answer tripletsMUTAN · VQA-2.0 valoverall accuracy: 62.84 -> 63.83Improved
add attention module for reasoning to NTN (k=6) (ablation)MUTAN + NTN · VQA-2.0 valoverall accuracy: 63.83 -> 64.16Improved
add attention module for reasoning to NTN (k=3) (ablation)MUTAN + NTN · VQA-2.0 valoverall accuracy: 63.74 -> 64.07Improved
add attention module for reasoning to NTN (k=10) (ablation)MUTAN + NTN · VQA-2.0 valoverall accuracy: 63.86 -> 64.07Improved
increase number of tensor slices k from 3 to 10 (ablation)MUTAN + NTN · VQA-2.0 valoverall accuracy: 63.74 -> 63.86No clear effect
increase number of tensor slices k from 3 to 6 to 10 (ablation)MUTAN + DA-NTN · VQA-2.0 valoverall accuracy: 64.07 -> 64.16 -> 64.07No clear effect
add DA-NTNMLB · VQA-2.0 valoverall accuracy: 62.98 -> 64.58Improved
add DA-NTNMUTAN · VQA-2.0 test-devoverall accuracy: 66.01 -> 67.15Improved
add DA-NTNMLB · VQA-2.0 test-devoverall accuracy: 66.27 -> 67.56Improved
add DA-NTNMLB · VQA-2.0 test-standardoverall accuracy: 66.62 -> 67.94Improved
add DA-NTNMUTAN (bottom-up) · VQA-1.0 test-devoverall accuracy: 65.7 -> 67.1Improved
add DA-NTNMLB (bottom-up) · VQA-1.0 test-devoverall accuracy: 65.9 -> 67.9Improved

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