General-purpose video foundation models, adapted with lightweight readout heads, reach state-of-the-art performance on three of five scientific video benchmarks.
Revisiting feature prediction for learning visual rep- resentations from video.TMLR, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications
General-purpose video foundation models, adapted with lightweight readout heads, reach state-of-the-art performance on three of five scientific video benchmarks.