SEAL compresses long videos into scene, object, and action tokens, then selects a query-relevant, diverse subset, reporting improvements on LVBench, MovieChat-1K, and Ego4D.
Eva: Exploring the limits of masked visual representa- tion learning at scale
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SEAL: Semantic Attention Learning for Long Video Representation
SEAL compresses long videos into scene, object, and action tokens, then selects a query-relevant, diverse subset, reporting improvements on LVBench, MovieChat-1K, and Ego4D.