GS-STVSR achieves state-of-the-art continuous spatio-temporal video super-resolution quality with nearly constant inference time at standard scales and over 3x speedup at extreme scales using 2D Gaussian Splatting.
Temporal-guided spiking neural networks for event-based human action recognition
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
other 1polarities
unclear 1representative citing papers
LoRSP integrates spiking neurons with low-rank factorization to produce sparse visual prompts for efficient adaptation of vision models across tasks.
A neuromorphic edge system using event vision and sparse SNNs on Loihi 2 achieves up to 84% F1 score at 90 mW for privacy-preserving fall detection.
citing papers explorer
-
GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting
GS-STVSR achieves state-of-the-art continuous spatio-temporal video super-resolution quality with nearly constant inference time at standard scales and over 3x speedup at extreme scales using 2D Gaussian Splatting.
-
Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorization
LoRSP integrates spiking neurons with low-rank factorization to produce sparse visual prompts for efficient adaptation of vision models across tasks.
-
Privacy-preserving fall detection at the edge using Sony IMX636 event-based vision sensor and Intel Loihi 2 neuromorphic processor
A neuromorphic edge system using event vision and sparse SNNs on Loihi 2 achieves up to 84% F1 score at 90 mW for privacy-preserving fall detection.