DYTO combines hierarchical frame clustering with bipartite token merging to compress video inputs for frozen image-language models, yielding modest, inconsistent gains over training-free baselines.
Is space-time attention all you need for video understanding? In ICML, page 4, 2021
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
-
Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
DYTO combines hierarchical frame clustering with bipartite token merging to compress video inputs for frozen image-language models, yielding modest, inconsistent gains over training-free baselines.