AI Paper Atlas

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

Query-Guided Spatial–Temporal–Frequency Interaction for Music Audio–Visual Question Answering

Kun Li, Michael Ying Yang, Sami Sebastian Brandt

ICLR 2026 · Vision-language and multimodal › Visual question answering · approach: Multimodal question answering datasets · 0 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 query-guided multimodal correlation (QGMC) (ablation)QSTar · MUSIC-AVQA testoverall accuracy (%): 76.80 -> 78.98Improved
add query context reasoning (QCR) prompting block (ablation)QSTar · MUSIC-AVQA testoverall accuracy (%): 78.19 -> 78.98Improved
add spatial-temporal interaction (STI) (ablation)QSTar · MUSIC-AVQA testoverall accuracy (%): 77.80 -> 78.98Improved
add temporal-frequency interaction (TFI, AST features) (ablation)QSTar · MUSIC-AVQA testoverall accuracy (%): 77.41 -> 78.98Improved
add query guidance at the beginning stage (ablation)QSTar · MUSIC-AVQA testoverall accuracy (%): 77.93 -> 78.98Improved
add question embeddings in TFI (middle-stage guidance) (ablation)QSTar · MUSIC-AVQA testoverall accuracy (%): 78.55 -> 78.98Improved
use AST-only features for the temporal audio pathway instead of VGGish (ablation)QSTar · MUSIC-AVQA testoverall accuracy (%): 78.98 -> 78.14Hurt
combine VGGish and AST features in the audio pathway (ablation)QSTar · MUSIC-AVQA testoverall accuracy (%): 78.98 -> 78.65No clear effect
use alternative prompts (translation, caption, GPT-4o generative) instead of unified keyword prompts (ablation)QSTar · MUSIC-AVQA testoverall accuracy (%): 78.98 -> 78.44 / 78.28 / 78.37Hurt
QA-TIGER-style sequential early processing instead of QGMC (ablation)QSTar · MUSIC-AVQA testoverall accuracy (%): 78.98 -> 78.89No clear effect
add prompting to QSTar (ablation)QSTar · AVQA testtotal accuracy (%): 90.9 -> 91.2Improved
QSTar vs QA-TIGER on Visual QAQSTar · MUSIC-AVQA test Visual QAaccuracy (%): 85.14 (QA-TIGER) vs 84.17Hurt

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