A cross-modal transformer using heterogeneous scene graphs predicts VR user trajectories more accurately than gaze- and point-cloud-only baselines on the CREATTIVE3D dataset.
IEEE Transactions on Neural Networks and Learning Systems (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DiVR: incorporating context from diverse VR scenes for human trajectory prediction
A cross-modal transformer using heterogeneous scene graphs predicts VR user trajectories more accurately than gaze- and point-cloud-only baselines on the CREATTIVE3D dataset.