notesum.ai

Published at November 19

AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction

cs.CV
cs.AI

Released Date: November 19, 2024

Authors: Yuanbin Man1, Ying Huang1, Chengming Zhang2, Bingzhe Li3, Wei Niu4, Miao Yin1

Aff.: 1Department of CSE, UT Arlington; 2Department of CS, University of Houston; 3Department of CS, UT Dallas; 4School of Computing, University of Georgia

Arxiv: http://arxiv.org/abs/2411.12593v1