DAViD uses Q-learning to pick a per-class temporal resolution for synthetic videos in dataset distillation, improving distilled-video recognition accuracy on UCF101, HMDB51, SSv2, and K400.
Burnetas and Michael N
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dynamic-Aware Video Distillation: Optimizing Temporal Resolution Based on Video Semantics
DAViD uses Q-learning to pick a per-class temporal resolution for synthetic videos in dataset distillation, improving distilled-video recognition accuracy on UCF101, HMDB51, SSv2, and K400.