Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction.

Inhwan Bae Jin-Hwi Park Hae-Gon Jeon

Published in: ECCV (22) (2022)

Keyphrases

multi modal
learning process
multi modality
learning algorithm
high dimensional
image annotation
semantic concepts
active learning
higher level
visual cues
visual recognition
video search
cross modal
uni modal
auto annotation