# Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos

Source: [Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos](<https://www.sota2.com/research/paper/68fa6aff1e209131cea2b9ce>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:38:16.503Z

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

Published: 2021-10-11T09:58:05.000Z

## Abstract

360$^\\circ$ videos convey holistic views for the surroundings of a scene. It provides audio-visual cues beyond pre-determined normal field of views and displays distinctive spatial relations on a sphere. However, previous benchmark tasks for panoramic videos are still limited to evaluate the semantic understanding of audio-visual relationships or spherical spatial property in surroundings. We propose a novel benchmark named Pano-AVQA as a large-scale grounded audio-visual question answering dataset on panoramic videos. Using 5.4K 360$^\\circ$ video clips harvested online, we collect two types of novel question-answer pairs with bounding-box grounding: spherical spatial relation QAs and audio-visual relation QAs. We train several transformer-based models from Pano-AVQA, where the results suggest that our proposed spherical spatial embeddings and multimodal training objectives fairly contribute to a better semantic understanding of the panoramic surroundings on the dataset.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2110.05122>)

[PDF](<https://arxiv.org/pdf/2110.05122.pdf>)