Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks.

Kuan Fang Alexander Toshev Li Fei-Fei Silvio Savarese

Published in: CVPR (2019)

Keyphrases

embodied agents
episodic memory
video sequences
d scene
input image
single image
fault diagnosis
memory requirements
multiple images
complex scenes
real scenes
memory usage
three dimensional
user experience