EAGOR reformulates embodied 360-degree directional reasoning as recursive Bayesian estimation on a spherical manifold using spherical harmonics, achieving training-free, rotation-equivariant target tracking.
Pano-avqa: Grounded audio-visual question answering on 360 ◦ videos
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
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.
years
2026 2representative citing papers
PanoWorld adds spherical spatial cross-attention and pano-native training data to MLLMs for improved spatial reasoning on ERP panoramas, outperforming baselines on new and existing benchmarks.
citing papers explorer
-
EAGOR: Embodied Reasoning in Omni-direction
EAGOR reformulates embodied 360-degree directional reasoning as recursive Bayesian estimation on a spherical manifold using spherical harmonics, achieving training-free, rotation-equivariant target tracking.
-
PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World
PanoWorld adds spherical spatial cross-attention and pano-native training data to MLLMs for improved spatial reasoning on ERP panoramas, outperforming baselines on new and existing benchmarks.