AI Paper Atlas

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

Multi-Modality Latent Interaction Network for Visual Question Answering

Peng Gao, Haoxuan You, Zhanpeng Zhang, Xiaogang Wang, Hongsheng Li

ICCV 2019 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 87 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
stack 8 MLI blocks instead of 1 (ablation)MLIN · VQA v2.0 valaccuracy: 66.04 -> 66.53Improved
use 6 by 6 summarization vectors instead of 3 by 3 (ablation)MLIN · VQA v2.0 valaccuracy: 65.63 -> 66.04Improved
use 12 by 12 summarization vectors instead of 6 by 6 (ablation)MLIN · VQA v2.0 valaccuracy: 66.04 -> 66.21Improved
use element-wise product instead of addition as interaction operator (ablation)MLIN · VQA v2.0 valaccuracy: 65.69 -> 66.04Improved
use MUTAN bilinear fusion instead of product as interaction operator (ablation)MLIN · VQA v2.0 valaccuracy: 66.04 -> 66.20Improved
use product instead of concatenation as interaction operator (ablation)MLIN · VQA v2.0 valaccuracy: 65.99 -> 66.04No clear effect
use embedding dimension 1024 instead of 512 (ablation)MLIN · VQA v2.0 valaccuracy: 66.04 -> 66.18Improved
use linear propagation instead of self attention (ablation)MLIN · VQA v2.0 valaccuracy: 65.84 -> 66.04Improved
use linear propagation instead of dual attention (ablation)MLIN · VQA v2.0 valaccuracy: 66.01 -> 66.04No clear effect
use key-query feature gathering instead of transpose attention (ablation)MLIN · VQA v2.0 valaccuracy: 65.78 -> 66.04Improved
use 16 parallel heads instead of 8 (ablation)MLIN · VQA v2.0 valaccuracy: 65.84 -> 66.19Improved
finetune BERT at lr 1/10 instead of freezing (ablation)MLI-8 + BERT · VQA v2.0 valaccuracy: 65.51 -> 67.83Improved

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