AI Paper Atlas

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

Pano-AVQA: Grounded Audio-Visual Question Answering on 360deg Videos

Heeseung Yun, Youngjae Yu, Wonsuk Yang, Kangil Lee, Gunhee Kim

ICCV 2021 · Vision-language and multimodal › Visual question answering · approach: Multimodal question answering datasets · 2 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 unimodal encoders before multimodal fusion (ablation)LAViT · Pano-AVQA testaccuracy (all): 44.14 -> 50.49Improved
add visual input to audio+language (ablation)LAViT · Pano-AVQA testaccuracy (all): 47.99 -> 50.49Improved
add audio input to visual+language (ablation)LAViT · Pano-AVQA testaccuracy (all): 48.73 -> 50.49Improved
use both equirectangular and NFoV views instead of single NFoV (ablation)LAViT · Pano-AVQA testaccuracy (all): 48.50 -> 50.49Improved
add NFoV views to equirectangular only (ablation)LAViT · Pano-AVQA testaccuracy (all): 49.18 -> 50.49Improved
add equirectangular view to dense NFoV (ablation)LAViT · Pano-AVQA testaccuracy (all): 49.79 -> 50.49Improved
use quaternion instead of Cartesian spatial embedding (ablation)LAViT · Pano-AVQA testaccuracy (all): 49.89 -> 50.49Improved
use quaternion instead of spherical coordinates embedding (ablation)LAViT · Pano-AVQA testaccuracy (all): 50.21 -> 50.49No clear effect
use quaternion instead of unit sphere embedding (ablation)LAViT · Pano-AVQA testaccuracy (all): 49.83 -> 50.49Improved
use early multimodal transformer fusion instead of late fusion (LAViT vs AVSD) (ablation)LAViT · Pano-AVQA testaccuracy (all): 24.60 -> 50.49Improved
use LAViT with audio instead of LXMERT (ablation)LAViT vs LXMERT · Pano-AVQA testaccuracy (all): 48.48 -> 50.49Improved

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