A Mamba-based model with focal loss and ground-truth-anchored window regularization improves online take/release endpoint detection from 25.16 to 45.48 mp-mAP on EPIC-KITCHENS-100.
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
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
-
Mamba-OTR: a Mamba-based Solution for Online Take and Release Detection from Untrimmed Egocentric Video
A Mamba-based model with focal loss and ground-truth-anchored window regularization improves online take/release endpoint detection from 25.16 to 45.48 mp-mAP on EPIC-KITCHENS-100.