A construction-based video distillation pipeline selects teacher-confident clips, allocates slots to feature-space clusters, and blends prototype-anchor pairs with matched soft labels, avoiding gradient updates of stored videos.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Video Dataset Distillation via Cluster-Guided Prototype Blending
A construction-based video distillation pipeline selects teacher-confident clips, allocates slots to feature-space clusters, and blends prototype-anchor pairs with matched soft labels, avoiding gradient updates of stored videos.