Memory Storyboard groups recent video frames into temporal segments and replays them from a two-tier memory, improving self-supervised representation learning on egocentric video streams.
The results here demonstrate that applying the temporal contrastive loss only on data from long-term memory or on the entire training batch achieves the best performance
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
-
Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos
Memory Storyboard groups recent video frames into temporal segments and replays them from a two-tier memory, improving self-supervised representation learning on egocentric video streams.