AI Paper Atlas

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

Learning Trimodal Relation for Audio-Visual Question Answering with Missing Modality

Kyu Ri Park, Hong Joo Lee, Jung Uk Kim

ECCV 2024 · Vision-language and multimodal › Visual question answering · approach: Multimodal question answering datasets · 7 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 RMM generator plus AVR diffusion to AVQA networks under missing modalityAVST · MUSIC-AVQA (audio missing)All Avg accuracy: 36.60 -> 69.71Improved
add RMM generator plus AVR diffusionAVST · MUSIC-AVQA (visual missing)All Avg accuracy: 59.14 -> 67.98Improved
add RMM generator alone (ablation)AVST · MUSIC-AVQA (audio missing)All Avg accuracy: 36.60 -> 60.38Improved
add AVR diffusion alone (ablation)AVST · MUSIC-AVQA (audio missing)All Avg accuracy: 36.60 -> 66.03Improved
combine RMM generator with AVR diffusion instead of AVR alone (ablation)AVST · MUSIC-AVQA (audio missing)All Avg accuracy: 66.03 -> 69.71Improved
combine RMM generator with AVR diffusion instead of AVR alone (ablation)AVST · MUSIC-AVQA (visual missing)All Avg accuracy: 65.62 -> 67.98Improved
set slot number to 75 instead of 25, 50 or 100 (ablation)RMM generator · MUSIC-AVQA (audio missing)All Avg accuracy: 68.85 -> 69.71Improved
use 10 diffusion time steps instead of 5 or 20 (ablation)AVR diffusion · MUSIC-AVQA (audio missing)All Avg accuracy: 68.20 -> 69.71Improved
proposed method versus existing missing-modality methods on AVST (visual missing)AVST · MUSIC-AVQA (visual missing)All Avg accuracy: 67.18 -> 67.98Mixed
apply method on AVSD where baseline had higher single-column scoresAVSD · AVQA dataset (visual missing)All Avg accuracy: 45.80 -> 46.35Mixed

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