AdaCM2 adaptively evicts low-attention video tokens using cross-modality attention scores, keeping memory bounded while improving accuracy on long-video QA, captioning, and classification.
Chen and William B
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
AdaCM2 adaptively evicts low-attention video tokens using cross-modality attention scores, keeping memory bounded while improving accuracy on long-video QA, captioning, and classification.