Bi3 is a new multimodal dataset for social robot navigation with biperson encounters, bicultural participants, biplatform robots, and five algorithms, totaling 10.5 hours of motion tracks plus video and impressions.
End-to-end recurrent multi-object tracking and trajectory prediction with relational reasoning,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
dataset 1polarities
background 1representative citing papers
Permutation-equivariant training via matched random channel shuffling improves SDR and reduces microphone bleed in multi-channel music source separation under unseen conditions.
The authors created and released the largest public dataset of road-user trajectories from high-density urban intersections using enhanced drone-based tracking and automated calibration.
citing papers explorer
-
Bi3: A Biplatform, Bicultural, Biperson Dataset for Social Robot Navigation
Bi3 is a new multimodal dataset for social robot navigation with biperson encounters, bicultural participants, biplatform robots, and five algorithms, totaling 10.5 hours of motion tracks plus video and impressions.
-
Learning Input-Channel Permutation Equivariance for Multi-Channel Source Separation: Reducing Bleeding in Small Music Ensembles
Permutation-equivariant training via matched random channel shuffling improves SDR and reduces microphone bleed in multi-channel music source separation under unseen conditions.
-
Drone Data Analytics for Measuring Traffic Metrics at Intersections in High-Density Areas
The authors created and released the largest public dataset of road-user trajectories from high-density urban intersections using enhanced drone-based tracking and automated calibration.