AI Paper Atlas

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

MUTAN: Multimodal Tucker Fusion for Visual Question Answering

Hedi Ben-younes, Remi Cadene, Matthieu Cord, Nicolas Thome

ICCV 2017 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 755 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 rank sparsity constraint (R=10) to the Tucker core tensor (ablation)MUTAN_noR · VQA test-devAll accuracy: 59.92 -> 60.17Improved
add rank sparsity constraint (R=10) to the Tucker core tensor (ablation)MUTAN_noR · VQA valAll accuracy: 57.94 -> 58.16Improved
replace MLB identity core tensor with a learned full core tensor (MUTAN_noR)MLB · VQA test-devAll accuracy: 60.08 -> 59.92No clear effect
replace MLB with MUTAN fusion (Tucker with rank constraint)MLB · VQA test-devAll accuracy: 60.08 -> 60.17Improved
late fusion of MUTAN with MLBMUTAN · VQA test-devAll accuracy: 60.17 -> 61.02Improved
late fusion of MUTAN with MLBMUTAN · VQA valAll accuracy: 58.16 -> 58.76Improved
use MUTAN_noR learned core tensor instead of identity tensor for t from 20 to 220 (ablation)low-dimensional bilinear fusion · VQA valaccuracyImproved
lower rank R=20 instead of R=60 (ablation)MUTAN with t_q=t_v=210 · VQA valaccuracyImproved
ensemble of 5 models (with MLB) instead of 3 MUTAN modelsMUTAN ensemble · VQA test-devAll accuracy: 67.03 -> 67.42Improved
turn off all but one rank projection z_r (ablation)MUTAN R=20 · VQA valaccuracy per question typeMixed

Later papers that compared with this method

6 later accepted papers report MUTAN as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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