AI Paper Atlas

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

A Read-Write Memory Network for Movie Story Understanding

Seil Na, Sangho Lee, Jisung Kim, Gunhee Kim

ICCV 2017 · Vision-language and multimodal › Visual question answering · approach: Visual reasoning diagnostics · 100 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 read and write convolutional networks (ablation)RWMN · MovieQA video+subtitle valaccuracy: 34.20 -> 38.67Improved
add read network on top of write network (ablation)RWMN-noR · MovieQA video+subtitle valaccuracy: 36.50 -> 38.67Improved
add write network (ablation)RWMN-noRW · MovieQA video+subtitle valaccuracy: 34.20 -> 36.50Improved
add query-dependent memory embedding (ablation)RWMN · MovieQA video+subtitle valaccuracy: 38.17 -> 38.67Improved
add video input (ablation)RWMN · MovieQA video+subtitle valaccuracy: 37.20 -> 38.67Improved
bagging 30 bootstrapped modelsRWMN · MovieQA video+subtitle valaccuracy: 38.67 -> 38.37No clear effect
ensemble of 20 random-init modelsRWMN · MovieQA video+subtitle valaccuracy: 38.67 -> 38.30No clear effect
use RWMN instead of MEMN2NRWMN · MovieQA DVS valaccuracy: 33.0 -> 40.0Improved
use RWMN instead of MEMN2NRWMN · MovieQA Plot Synopses valaccuracy: 40.6 -> 37.0Hurt
increase write stride from 30 to 60 (ablation)RWMN write network · MovieQA video+subtitle valaccuracy: 38.6 -> 33.6Hurt
use two write layers instead of one (ablation)RWMN · MovieQA video+subtitle valaccuracy: 38.6 -> 37.2Hurt
use three write layers (40,3,3),(10,3,3),(10,3,3) (ablation)RWMN · MovieQA video+subtitle valaccuracy: 38.6 -> 37.9Hurt

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