HiCE with grasp-aware loss and soft labels outperforms baselines by 16.91% AP on the new TouchMoment dataset for frame-level hand contact detection in first-person video.
Decoupled weight decay regularization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SwiftPie enables one-step diffusion for fast, high-quality subject-driven image personalization comparable to slower multi-step methods.
citing papers explorer
-
Detecting Precise Hand Touch Moments in Egocentric Video
HiCE with grasp-aware loss and soft labels outperforms baselines by 16.91% AP on the new TouchMoment dataset for frame-level hand contact detection in first-person video.
-
SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion
SwiftPie enables one-step diffusion for fast, high-quality subject-driven image personalization comparable to slower multi-step methods.