PKS^4 adds a kinematic-prior-driven parallel state space scanner module to 2D vision backbones for linear-complexity temporal modeling in videos, delivering SOTA action recognition with 10x lower training compute and convergence in 20 epochs.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
CoLoRSMamba steers AudioMamba using video CLS-guided conditional LoRA to adapt selective state-space parameters, outperforming baselines on audio-filtered NTU-CCTV and DVD subsets with 88.63% and 75.77% accuracy respectively.
citing papers explorer
-
$\text{PKS}^4$:Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding
PKS^4 adds a kinematic-prior-driven parallel state space scanner module to 2D vision backbones for linear-complexity temporal modeling in videos, delivering SOTA action recognition with 10x lower training compute and convergence in 20 epochs.
-
CoLoRSMamba: Conditional LoRA-Steered Mamba for Supervised Multimodal Violence Detection
CoLoRSMamba steers AudioMamba using video CLS-guided conditional LoRA to adapt selective state-space parameters, outperforming baselines on audio-filtered NTU-CCTV and DVD subsets with 88.63% and 75.77% accuracy respectively.