Mobius: A High Efficient Spatial-Temporal Parallel Training Paradigm for Text-to-Video Generation Task.

Yiran Yang Jinchao Zhang Ying Deng Jie Zhou

Published in: CoRR (2024)

Keyphrases

spatial temporal
video shots
spatio temporal
spatial and temporal
temporal information
action recognition
video sequences
information retrieval
computer vision
human actions
video clips
video data
text documents
video database