AI Paper Atlas

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

Movie Question Answering: Remembering the Textual Cues for Layered Visual Contents

Bo Wang, Youjiang Xu, Yahong Han, Richang Hong

AAAI 2018 · Vision-language and multimodal › Visual question answering · approach: Multimodal question answering datasets · 44 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
Use LMN frame-level visual representations instead of MemN2NMovieQA video-only · MovieQA Videoaccuracy: 23.1 -> 38.6Improved
Use LMN with video and subtitles instead of MemN2NMovieQA Video+Subtitles · MovieQA Video+Subtitlesaccuracy: 34.2 -> 39.6Improved
Add 2-hop Static Word Memory (ablation)LMN · MovieQA Video+Subtitlesaccuracy: 39.3 -> 39.6; 39.6 -> 39.6No clear effect
Add 3-hop Static Word Memory (ablation)LMN · MovieQA Video+Subtitlesaccuracy: 39.3 -> 40.1; 39.6 -> 39.9Improved
Add 2 update-mechanism hops to Dynamic Subtitle Memory (ablation)LMN · MovieQA Video+Subtitlesaccuracy: 39.3 -> 41.4; 39.6 -> 41.6Improved
Use 3 update-mechanism hops in Dynamic Subtitle Memory instead of 2 (ablation)LMN · MovieQA Video+Subtitlesaccuracy: 41.4 -> 41.5; 41.6 -> 41.4No clear effect
Add question-guided subtitle attention (ablation)LMN · MovieQA Video+Subtitlesaccuracy: 39.3 -> 40.6; 39.6 -> 40.1Improved
Add question-guided subtitle attention to LMN with 2 update-mechanism hops (ablation)LMN + UM² · MovieQA Video+Subtitlesaccuracy: 41.4 -> 42.3; 41.6 -> 42.5Improved
Use LMN with update mechanism and question-guided attention instead of RWMNMovieQA online evaluation · MovieQA online test Video+Subtitlesaccuracy: 36.25 -> 39.03Improved

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