STAR improves 1-shot action recognition by up to 8.1% on SSv2-Full through semantic-temporal alignment and Mamba-based prototype refinement.
Vmamba: Visual state space model,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
RSGMamba introduces a reliability-aware self-gated Mamba block for dynamic cross-modal feature selection in semantic segmentation, delivering state-of-the-art mIoU on RGB-D and RGB-T benchmarks with 48.6M parameters.
Natural Selection (NS) dynamically reweights DNN training losses by estimating each sample's competitive status inside groups assembled as composite images.
citing papers explorer
-
STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR improves 1-shot action recognition by up to 8.1% on SSv2-Full through semantic-temporal alignment and Mamba-based prototype refinement.
-
RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation
RSGMamba introduces a reliability-aware self-gated Mamba block for dynamic cross-modal feature selection in semantic segmentation, delivering state-of-the-art mIoU on RGB-D and RGB-T benchmarks with 48.6M parameters.
-
Evolution-Inspired Sample Competition for Deep Neural Network Optimization
Natural Selection (NS) dynamically reweights DNN training losses by estimating each sample's competitive status inside groups assembled as composite images.