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

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

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.
BibTeX
@inproceedings{yun2021pano,
  author = {Heeseung Yun and Youngjae Yu and Wonsuk Yang and Kangil Lee and Gunhee Kim},
  title = {{Pano-AVQA: Grounded Audio-Visual Question Answering on 360° Videos}},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year = {2021},
  doi = {10.1109/iccv48922.2021.00204},
}
Figure