A language model trained on continuous motion features, video, and text with text-guided frame selection improves scores on motion understanding benchmarks.
Gpt-3.5: Generative pre-trained transformer 3.5,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Human Motion Instruction Tuning
A language model trained on continuous motion features, video, and text with text-guided frame selection improves scores on motion understanding benchmarks.